1
|
McMurry AJ, Zipursky AR, Geva A, Olson KL, Jones JR, Ignatov V, Miller TA, Mandl KD. Moving Biosurveillance Beyond Coded Data Using AI for Symptom Detection From Physician Notes: Retrospective Cohort Study. J Med Internet Res 2024; 26:e53367. [PMID: 38573752 PMCID: PMC11027052 DOI: 10.2196/53367] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/06/2023] [Revised: 11/30/2023] [Accepted: 02/27/2024] [Indexed: 04/05/2024] Open
Abstract
BACKGROUND Real-time surveillance of emerging infectious diseases necessitates a dynamically evolving, computable case definition, which frequently incorporates symptom-related criteria. For symptom detection, both population health monitoring platforms and research initiatives primarily depend on structured data extracted from electronic health records. OBJECTIVE This study sought to validate and test an artificial intelligence (AI)-based natural language processing (NLP) pipeline for detecting COVID-19 symptoms from physician notes in pediatric patients. We specifically study patients presenting to the emergency department (ED) who can be sentinel cases in an outbreak. METHODS Subjects in this retrospective cohort study are patients who are 21 years of age and younger, who presented to a pediatric ED at a large academic children's hospital between March 1, 2020, and May 31, 2022. The ED notes for all patients were processed with an NLP pipeline tuned to detect the mention of 11 COVID-19 symptoms based on Centers for Disease Control and Prevention (CDC) criteria. For a gold standard, 3 subject matter experts labeled 226 ED notes and had strong agreement (F1-score=0.986; positive predictive value [PPV]=0.972; and sensitivity=1.0). F1-score, PPV, and sensitivity were used to compare the performance of both NLP and the International Classification of Diseases, 10th Revision (ICD-10) coding to the gold standard chart review. As a formative use case, variations in symptom patterns were measured across SARS-CoV-2 variant eras. RESULTS There were 85,678 ED encounters during the study period, including 4% (n=3420) with patients with COVID-19. NLP was more accurate at identifying encounters with patients that had any of the COVID-19 symptoms (F1-score=0.796) than ICD-10 codes (F1-score =0.451). NLP accuracy was higher for positive symptoms (sensitivity=0.930) than ICD-10 (sensitivity=0.300). However, ICD-10 accuracy was higher for negative symptoms (specificity=0.994) than NLP (specificity=0.917). Congestion or runny nose showed the highest accuracy difference (NLP: F1-score=0.828 and ICD-10: F1-score=0.042). For encounters with patients with COVID-19, prevalence estimates of each NLP symptom differed across variant eras. Patients with COVID-19 were more likely to have each NLP symptom detected than patients without this disease. Effect sizes (odds ratios) varied across pandemic eras. CONCLUSIONS This study establishes the value of AI-based NLP as a highly effective tool for real-time COVID-19 symptom detection in pediatric patients, outperforming traditional ICD-10 methods. It also reveals the evolving nature of symptom prevalence across different virus variants, underscoring the need for dynamic, technology-driven approaches in infectious disease surveillance.
Collapse
Affiliation(s)
- Andrew J McMurry
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, United States
- Department of Pediatrics, Harvard Medical School, Boston, MA, United States
| | - Amy R Zipursky
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, United States
- Division of Pediatric Emergency Medicine, Department of Pediatrics, The Hospital for Sick Children, Toronto, ON, Canada
| | - Alon Geva
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, United States
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, MA, United States
- Department of Anaesthesia, Harvard Medical School, Boston, MA, United States
| | - Karen L Olson
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, United States
- Department of Pediatrics, Harvard Medical School, Boston, MA, United States
| | - James R Jones
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, United States
| | - Vladimir Ignatov
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, United States
| | - Timothy A Miller
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, United States
- Department of Pediatrics, Harvard Medical School, Boston, MA, United States
| | - Kenneth D Mandl
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, United States
- Department of Pediatrics, Harvard Medical School, Boston, MA, United States
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, United States
| |
Collapse
|
2
|
Atreya MR, Bennett TD, Geva A, Faustino EVS, Rogerson CM, Lutfi R, Cvijanovich NZ, Bigham MT, Nowak J, Schwarz AJ, Baines T, Haileselassie B, Thomas NJ, Luo Y, Sanchez-Pinto LN. Biomarker Assessment of a High-Risk, Data-Driven Pediatric Sepsis Phenotype Characterized by Persistent Hypoxemia, Encephalopathy, and Shock. Pediatr Crit Care Med 2024:00130478-990000000-00322. [PMID: 38465952 DOI: 10.1097/pcc.0000000000003499] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/12/2024]
Abstract
OBJECTIVES Identification of children with sepsis-associated multiple organ dysfunction syndrome (MODS) at risk for poor outcomes remains a challenge. We sought to the determine reproducibility of the data-driven "persistent hypoxemia, encephalopathy, and shock" (PHES) phenotype and determine its association with inflammatory and endothelial biomarkers, as well as biomarker-based pediatric risk strata. DESIGN We retrained and validated a random forest classifier using organ dysfunction subscores in the 2012-2018 electronic health record (EHR) dataset used to derive the PHES phenotype. We used this classifier to assign phenotype membership in a test set consisting of prospectively (2003-2023) enrolled pediatric septic shock patients. We compared profiles of the PERSEVERE family of biomarkers among those with and without the PHES phenotype and determined the association with established biomarker-based mortality and MODS risk strata. SETTING Twenty-five PICUs across the United States. PATIENTS EHR data from 15,246 critically ill patients with sepsis-associated MODS split into derivation and validation sets and 1,270 pediatric septic shock patients in the test set of whom 615 had complete biomarker data. INTERVENTIONS None. MEASUREMENTS AND MAIN RESULTS The area under the receiver operator characteristic curve of the modified classifier to predict PHES phenotype membership was 0.91 (95% CI, 0.90-0.92) in the EHR validation set. In the test set, PHES phenotype membership was associated with both increased adjusted odds of complicated course (adjusted odds ratio [aOR] 4.1; 95% CI, 3.2-5.4) and 28-day mortality (aOR of 4.8; 95% CI, 3.11-7.25) after controlling for age, severity of illness, and immunocompromised status. Patients belonging to the PHES phenotype were characterized by greater degree of systemic inflammation and endothelial activation, and were more likely to be stratified as high risk based on PERSEVERE biomarkers predictive of death and persistent MODS. CONCLUSIONS The PHES trajectory-based phenotype is reproducible, independently associated with poor clinical outcomes, and overlapped with higher risk strata based on prospectively validated biomarker approaches.
Collapse
Affiliation(s)
- Mihir R Atreya
- Division of Critical Care Medicine, Cincinnati Children's Hospital Medical Center and Cincinnati Children's Research Foundation, Cincinnati, OH
- Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, OH
| | - Tellen D Bennett
- Departments of Pediatrics and Biomedical Informatics, University of Colorado School of Medicine, Aurora, CO
| | - Alon Geva
- Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, MA
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA
| | | | - Colin M Rogerson
- Department of Pediatrics, Riley Hospital for Children, Indianapolis, IN
| | - Riad Lutfi
- Department of Pediatrics, Riley Hospital for Children, Indianapolis, IN
| | | | | | - Jeffrey Nowak
- Department of Pediatrics, Children's Hospital and Clinics of Minnesota, Minneapolis, MN
| | - Adam J Schwarz
- Department of Pediatrics, University of Calfornia Irvine School of Medicine, Orange, CA
| | - Torrey Baines
- Department of Pediatrics, Shands Children's Hospital, University of Florida Health, Gainesville, FL
| | | | - Neal J Thomas
- Department of Pediatrics, Penn State Hershey Children's Hospital, Hershey, PA
| | - Yuan Luo
- Department of Pediatrics, Northwestern University Feinberg School of Medicine, Chicago, IL
- Department of Health and Biomedical Informatics, Northwestern University Feinberg School of Medicine, Chicago, IL
| | - L Nelson Sanchez-Pinto
- Department of Pediatrics, Northwestern University Feinberg School of Medicine, Chicago, IL
- Department of Health and Biomedical Informatics, Northwestern University Feinberg School of Medicine, Chicago, IL
| |
Collapse
|
3
|
Akhondi-Asl A, Yang Y, Luchette M, Burns JP, Mehta NM, Geva A. Comparing the Quality of Domain-Specific Versus General Language Models for Artificial Intelligence-Generated Differential Diagnoses in PICU Patients. Pediatr Crit Care Med 2024:00130478-990000000-00310. [PMID: 38329382 DOI: 10.1097/pcc.0000000000003468] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/09/2024]
Abstract
OBJECTIVES Generative language models (LMs) are being evaluated in a variety of tasks in healthcare, but pediatric critical care studies are scant. Our objective was to evaluate the utility of generative LMs in the pediatric critical care setting and to determine whether domain-adapted LMs can outperform much larger general-domain LMs in generating a differential diagnosis from the admission notes of PICU patients. DESIGN Single-center retrospective cohort study. SETTING Quaternary 40-bed PICU. PATIENTS Notes from all patients admitted to the PICU between January 2012 and April 2023 were used for model development. One hundred thirty randomly selected admission notes were used for evaluation. INTERVENTIONS None. MEASUREMENTS AND MAIN RESULTS Five experts in critical care used a 5-point Likert scale to independently evaluate the overall quality of differential diagnoses: 1) written by the clinician in the original notes, 2) generated by two general LMs (BioGPT-Large and LLaMa-65B), and 3) generated by two fine-tuned models (fine-tuned BioGPT-Large and fine-tuned LLaMa-7B). Differences among differential diagnoses were compared using mixed methods regression models. We used 1,916,538 notes from 32,454 unique patients for model development and validation. The mean quality scores of the differential diagnoses generated by the clinicians and fine-tuned LLaMa-7B, the best-performing LM, were 3.43 and 2.88, respectively (absolute difference 0.54 units [95% CI, 0.37-0.72], p < 0.001). Fine-tuned LLaMa-7B performed better than LLaMa-65B (absolute difference 0.23 unit [95% CI, 0.06-0.41], p = 0.009) and BioGPT-Large (absolute difference 0.86 unit [95% CI, 0.69-1.0], p < 0.001). The differential diagnosis generated by clinicians and fine-tuned LLaMa-7B were ranked as the highest quality in 144 (55%) and 74 cases (29%), respectively. CONCLUSIONS A smaller LM fine-tuned using notes of PICU patients outperformed much larger models trained on general-domain data. Currently, LMs remain inferior but may serve as an adjunct to human clinicians in real-world tasks using real-world data.
Collapse
Affiliation(s)
- Alireza Akhondi-Asl
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, MA
- Perioperative and Critical Care-Center for Outcomes (PC-CORE), Boston Children's Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA
| | - Youyang Yang
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, MA
- Perioperative and Critical Care-Center for Outcomes (PC-CORE), Boston Children's Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA
| | - Matthew Luchette
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, MA
- Perioperative and Critical Care-Center for Outcomes (PC-CORE), Boston Children's Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA
| | - Jeffrey P Burns
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, MA
- Perioperative and Critical Care-Center for Outcomes (PC-CORE), Boston Children's Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA
| | - Nilesh M Mehta
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, MA
- Perioperative and Critical Care-Center for Outcomes (PC-CORE), Boston Children's Hospital, Boston, MA
| | - Alon Geva
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, MA
- Perioperative and Critical Care-Center for Outcomes (PC-CORE), Boston Children's Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA
| |
Collapse
|
4
|
Wösten-van Asperen RM, la Roi-Teeuw HM, van Amstel RBE, Bos LDJ, Tissing WJE, Jordan I, Dohna-Schwake C, Bottari G, Pappachan J, Crazzolara R, Comoretto RI, Mizia-Malarz A, Moscatelli A, Sánchez-Martín M, Willems J, Rogerson CM, Bennett TD, Luo Y, Atreya MR, Faustino ES, Geva A, Weiss SL, Schlapbach LJ, Sanchez-Pinto LN. Distinct clinical phenotypes in paediatric cancer patients with sepsis are associated with different outcomes-an international multicentre retrospective study. EClinicalMedicine 2023; 65:102252. [PMID: 37842550 PMCID: PMC10570699 DOI: 10.1016/j.eclinm.2023.102252] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/27/2023] [Revised: 09/14/2023] [Accepted: 09/15/2023] [Indexed: 10/17/2023] Open
Abstract
Background Identifying phenotypes in sepsis patients may enable precision medicine approaches. However, the generalisability of these phenotypes to specific patient populations is unclear. Given that paediatric cancer patients with sepsis have different host response and pathogen profiles and higher mortality rates when compared to non-cancer patients, we determined whether unique, reproducible, and clinically-relevant sepsis phenotypes exist in this specific patient population. Methods We studied patients with underlying malignancies admitted with sepsis to one of 25 paediatric intensive care units (PICUs) participating in two large, multi-centre, observational cohorts from the European SCOTER study (n = 383 patients; study period between January 1, 2018 and January 1, 2020) and the U.S. Novel Data-Driven Sepsis Phenotypes in Children study (n = 1898 patients; study period between January 1, 2012 and January 1, 2018). We independently used latent class analysis (LCA) in both cohorts to identify phenotypes using demographic, clinical, and laboratory data from the first 24 h of PICU admission. We then tested the association of the phenotypes with clinical outcomes in both cohorts. Findings LCA identified two distinct phenotypes that were comparable across both cohorts. Phenotype 1 was characterised by lower serum bicarbonate and albumin, markedly increased lactate and hepatic, renal, and coagulation abnormalities when compared to phenotype 2. Patients with phenotype 1 had a higher 90-day mortality (European cohort 29.2% versus 13.4%, U.S. cohort 27.3% versus 11.4%, p < 0.001) and received more vasopressor and renal replacement therapy than patients with phenotype 2. After adjusting for severity of organ dysfunction, haematological cancer, prior stem cell transplantation and age, phenotype 1 was associated with an adjusted OR of death at 90-day of 1.9 (1.04-3.34) in the European cohort and 1.6 (1.2-2.2) in the U.S. cohort. Interpretation We identified two clinically-relevant sepsis phenotypes in paediatric cancer patients that are reproducible across two international, multicentre cohorts with prognostic implications. These results may guide further research regarding therapeutic approaches for these specific phenotypes. Funding Part of this study is funded by the Eunice Kennedy Shriver National Institute of Child Health and Human Development.
Collapse
Affiliation(s)
- Roelie M. Wösten-van Asperen
- Department of Paediatric Intensive Care, University Medical Centre Utrecht/Wilhelmina Children’s Hospital, Utrecht, the Netherlands
| | - Hannah M. la Roi-Teeuw
- Department of Paediatric Intensive Care, University Medical Centre Utrecht/Wilhelmina Children’s Hospital, Utrecht, the Netherlands
| | - Rombout BE. van Amstel
- Intensive Care, Amsterdam UMC—location AMC, University of Amsterdam, Amsterdam, the Netherlands
| | - Lieuwe DJ. Bos
- Intensive Care, Amsterdam UMC—location AMC, University of Amsterdam, Amsterdam, the Netherlands
| | - Wim JE. Tissing
- Princess Máxima Centre for Pediatric Oncology, Utrecht, the Netherlands
- Department of Paediatric Oncology, University of Groningen, University Medical Centre Groningen, Groningen, the Netherlands
| | - Iolanda Jordan
- Department of Paediatric Intensive Care and Institut de Recerca, Hospital Sant Joan de Déu, University of Barcelona, Barcelona, Spain
- Consorcio de Investigación Biomédica en Red de Epidemiología y Salud Pública, Madrid, Spain
| | - Christian Dohna-Schwake
- Department of Paediatrics I, Paediatric Intensive Care, Children’s Hospital Essen, Germany
- West German Centre for Infectious Diseases, University Hospital Essen, University Duisburg-Essen, Essen, Germany
| | - Gabriella Bottari
- Paediatric Intensive Care Unit, Children’s Hospital Bambino Gesù, IRCSS, Rome, Italy
| | - John Pappachan
- Department of Paediatric Intensive Care, Southampton Children’s Hospital, UK
| | - Roman Crazzolara
- Department of Paediatrics, Paediatric Intensive Care Unit, Medical University of Innsbruck, Innsbruck, Austria
| | - Rosanna I. Comoretto
- Department of Paediatric Intensive Care, Department of Woman's and Child's Health, Padua University Hospital, Padua, Italy
| | - Agniezka Mizia-Malarz
- Department of Paediatric Oncology, Haematology and Chemotherapy Unit, Medical University of Silesia, Katowice, Poland
| | - Andrea Moscatelli
- Neonatal and Paediatric Intensive Care Unit, IRCCS Istituto Giannina Gaslini, Genova, Italy
| | - María Sánchez-Martín
- Department of Paediatric Intensive Care, Hospital Universitario La Paz, Madrid, Spain
| | - Jef Willems
- Department of Paediatric Intensive Care, Ghent University Hospital, Ghent, Belgium
| | - Colin M. Rogerson
- Department of Paediatrics, Division of Critical Care, Indianapolis University School of Medicine, Indianapolis, IN, USA
| | - Tellen D. Bennett
- Departments of Biomedical Informatics and Paediatrics, University of Colorado School of Medicine, Aurora, CO, USA
| | - Yuan Luo
- Department of Preventive Medicine, Northwestern University Feinberg School of Medicine, Chicago, IL, USA
| | - Mihir R. Atreya
- Department of Paediatrics (Critical Care), University of Cincinnati College of Medicine, Cincinnati Children’s Hospital Medical Centre, Cincinnati, OH, USA
| | | | - Alon Geva
- Department of Anaesthesiology, Critical Care, and Pain Medicine and Computational Health Informatics Program, Boston Children's Hospital, USA
- Department of Anaesthesia, Harvard Medical School, Boston, MA, USA
| | - Scott L. Weiss
- Division of Critical Care, Department of Paediatrics, Nemours Children’s Health, Delaware, USA
| | - Luregn J. Schlapbach
- Department of Intensive Care and Neonatology and Children’s Research Centre, University Children’s Hospital Zurich, University of Zurich, Zurich, Switzerland
- Child Health Research Centre, The University of Queensland, Brisbane, Queensland, Australia
| | - L Nelson Sanchez-Pinto
- Department of Paediatrics (Critical Care) and Preventive Medicine (Health & Biomedical Informatics), Northwestern University Feinberg School of Medicine and Ann & Robert H Lurie Children’s Hospital of Chicago, Chicago, IL, USA
| |
Collapse
|
5
|
Zipursky AR, Olson KL, Bode L, Geva A, Jones J, Mandl KD, McMurry A. Emergency department visits and boarding for pediatric patients with suicidality before and during the COVID-19 pandemic. PLoS One 2023; 18:e0286035. [PMID: 37910582 PMCID: PMC10619773 DOI: 10.1371/journal.pone.0286035] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2023] [Accepted: 08/15/2023] [Indexed: 11/03/2023] Open
Abstract
OBJECTIVE To quantify the increase in pediatric patients presenting to the emergency department with suicidality before and during the COVID-19 pandemic, and the subsequent impact on emergency department length of stay and boarding. METHODS This retrospective cohort study from June 1, 2016, to October 31, 2022, identified patients ages 6 to 21 presenting to the emergency department at a pediatric academic medical center with suicidality using ICD-10 codes. Number of emergency department encounters for suicidality, demographic characteristics of patients with suicidality, and emergency department length of stay were compared before and during the COVID-19 pandemic. Unobserved components models were used to describe monthly counts of emergency department encounters for suicidality. RESULTS There were 179,736 patient encounters to the emergency department during the study period, 6,215 (3.5%) for suicidality. There were, on average, more encounters for suicidality each month during the COVID-19 pandemic than before the COVID-19 pandemic. A time series unobserved components model demonstrated a temporary drop of 32.7 encounters for suicidality in April and May of 2020 (p<0.001), followed by a sustained increase of 31.2 encounters starting in July 2020 (p = 0.003). The average length of stay for patients that boarded in the emergency department with a diagnosis of suicidality was 37.4 hours longer during the COVID-19 pandemic compared to before the COVID-19 pandemic (p<0.001). CONCLUSIONS The number of encounters for suicidality among pediatric patients and the emergency department length of stay for psychiatry boarders has increased during the COVID-19 pandemic. There is a need for acute care mental health services and solutions to emergency department capacity issues.
Collapse
Affiliation(s)
- Amy R. Zipursky
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, Massachusetts, United States of America
- Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, United States of America
- Division of Emergency Medicine, Boston Children’s Hospital, Boston, Massachusetts, United States of America
| | - Karen L. Olson
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, Massachusetts, United States of America
- Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, United States of America
| | - Louisa Bode
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, Massachusetts, United States of America
- Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School, Hannover, Lower Saxony, Germany
| | - Alon Geva
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, Massachusetts, United States of America
- Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, United States of America
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children’s Hospital, Boston, Massachusetts, United States of America
| | - James Jones
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, Massachusetts, United States of America
- Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, United States of America
| | - Kenneth D. Mandl
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, Massachusetts, United States of America
- Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, United States of America
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, United States of America
| | - Andrew McMurry
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, Massachusetts, United States of America
- Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, United States of America
| |
Collapse
|
6
|
Xiong X, Sweet SM, Liu M, Hong C, Bonzel CL, Panickan VA, Zhou D, Wang L, Costa L, Ho YL, Geva A, Mandl KD, Cheng S, Xia Z, Cho K, Gaziano JM, Liao KP, Cai T, Cai T. Knowledge-Driven Online Multimodal Automated Phenotyping System. medRxiv 2023:2023.09.29.23296239. [PMID: 37873131 PMCID: PMC10593060 DOI: 10.1101/2023.09.29.23296239] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/25/2023]
Abstract
Though electronic health record (EHR) systems are a rich repository of clinical information with large potential, the use of EHR-based phenotyping algorithms is often hindered by inaccurate diagnostic records, the presence of many irrelevant features, and the requirement for a human-labeled training set. In this paper, we describe a knowledge-driven online multimodal automated phenotyping (KOMAP) system that i) generates a list of informative features by an online narrative and codified feature search engine (ONCE) and ii) enables the training of a multimodal phenotyping algorithm based on summary data. Powered by composite knowledge from multiple EHR sources, online article corpora, and a large language model, features selected by ONCE show high concordance with the state-of-the-art AI models (GPT4 and ChatGPT) and encourage large-scale phenotyping by providing a smaller but highly relevant feature set. Validation of the KOMAP system across four healthcare centers suggests that it can generate efficient phenotyping algorithms with robust performance. Compared to other methods requiring patient-level inputs and gold-standard labels, the fully online KOMAP provides a significant opportunity to enable multi-center collaboration.
Collapse
|
7
|
Sanchez-Pinto LN, Bennett TD, Stroup EK, Luo Y, Atreya M, Bubeck Wardenburg J, Chong G, Geva A, Faustino EVS, Farris RW, Hall MW, Rogerson C, Shah SS, Weiss SL, Khemani RG. Derivation, Validation, and Clinical Relevance of a Pediatric Sepsis Phenotype With Persistent Hypoxemia, Encephalopathy, and Shock. Pediatr Crit Care Med 2023; 24:795-806. [PMID: 37272946 PMCID: PMC10540758 DOI: 10.1097/pcc.0000000000003292] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 06/06/2023]
Abstract
OBJECTIVES Untangling the heterogeneity of sepsis in children and identifying clinically relevant phenotypes could lead to the development of targeted therapies. Our aim was to analyze the organ dysfunction trajectories of children with sepsis-associated multiple organ dysfunction syndrome (MODS) to identify reproducible and clinically relevant sepsis phenotypes and determine if they are associated with heterogeneity of treatment effect (HTE) to common therapies. DESIGN Multicenter observational cohort study. SETTING Thirteen PICUs in the United States. PATIENTS Patients admitted with suspected infections to the PICU between 2012 and 2018. INTERVENTIONS None. MEASUREMENTS AND MAIN RESULTS We used subgraph-augmented nonnegative matrix factorization to identify candidate trajectory-based phenotypes based on the type, severity, and progression of organ dysfunction in the first 72 hours. We analyzed the candidate phenotypes to determine reproducibility as well as prognostic, therapeutic, and biological relevance. Overall, 38,732 children had suspected infection, of which 15,246 (39.4%) had sepsis-associated MODS with an in-hospital mortality of 10.1%. We identified an organ dysfunction trajectory-based phenotype (which we termed persistent hypoxemia, encephalopathy, and shock) that was highly reproducible, had features of systemic inflammation and coagulopathy, and was independently associated with higher mortality. In a propensity score-matched analysis, patients with persistent hypoxemia, encephalopathy, and shock phenotype appeared to have HTE and benefit from adjuvant therapy with hydrocortisone and albumin. When compared with other high-risk clinical syndromes, the persistent hypoxemia, encephalopathy, and shock phenotype only overlapped with 50%-60% of patients with septic shock, moderate-to-severe pediatric acute respiratory distress syndrome, or those in the top tier of organ dysfunction burden, suggesting that it represents a nonsynonymous clinical phenotype of sepsis-associated MODS. CONCLUSIONS We derived and validated the persistent hypoxemia, encephalopathy, and shock phenotype, which is highly reproducible, clinically relevant, and associated with HTE to common adjuvant therapies in children with sepsis.
Collapse
Affiliation(s)
- L Nelson Sanchez-Pinto
- Department of Pediatrics, Northwestern University Feinberg School of Medicine and Ann and Robert H. Lurie Children's Hospital of Chicago, Chicago, IL
- Department of Preventive Medicine, Northwestern University Feinberg School of Medicine, Chicago, IL
| | - Tellen D Bennett
- Departments of Biomedical Informatics and Pediatrics, University of Colorado School of Medicine, Aurora, CO
| | - Emily K Stroup
- Department of Pharmacology, Northwestern University Feinberg School of Medicine, Chicago, IL
| | - Yuan Luo
- Department of Preventive Medicine, Northwestern University Feinberg School of Medicine, Chicago, IL
| | - Mihir Atreya
- Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati Children's Hospital Medical Center, Cincinnati, OH
| | | | - Grace Chong
- Department of Pediatrics, University of Chicago Pritzker School of Medicine, Chicago, IL
| | - Alon Geva
- Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, MA
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA
| | | | - Reid W Farris
- Department of Pediatrics, University of Washington and Seattle Children's Hospital, Seattle, WA
| | - Mark W Hall
- Department of Pediatrics, The Ohio State University and Nationwide Children's Hospital, Columbus, OH
| | - Colin Rogerson
- Department of Pediatrics, Indiana University School of Medicine, Riley Hospital for Children, Indianapolis, IN
| | - Sareen S Shah
- Department of Pediatrics, Cohen Children's Medical Center, Donald and Barbara Zucker School of Medicine at Hofstra/Northwell, New Hyde Park, NY
| | - Scott L Weiss
- Department of Anesthesiology and Critical Care, Children's Hospital of Philadelphia, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA
| | - Robinder G Khemani
- Department of Anesthesiology and Critical Care Medicine, Children's Hospital of Los Angeles, Los Angeles, CA
| |
Collapse
|
8
|
Wang L, Zipursky AR, Geva A, McMurry AJ, Mandl KD, Miller TA. A computable case definition for patients with SARS-CoV2 testing that occurred outside the hospital. JAMIA Open 2023; 6:ooad047. [PMID: 37425487 PMCID: PMC10322650 DOI: 10.1093/jamiaopen/ooad047] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2023] [Revised: 06/13/2023] [Accepted: 06/30/2023] [Indexed: 07/11/2023] Open
Abstract
Objective To identify a cohort of COVID-19 cases, including when evidence of virus positivity was only mentioned in the clinical text, not in structured laboratory data in the electronic health record (EHR). Materials and Methods Statistical classifiers were trained on feature representations derived from unstructured text in patient EHRs. We used a proxy dataset of patients with COVID-19 polymerase chain reaction (PCR) tests for training. We selected a model based on performance on our proxy dataset and applied it to instances without COVID-19 PCR tests. A physician reviewed a sample of these instances to validate the classifier. Results On the test split of the proxy dataset, our best classifier obtained 0.56 F1, 0.6 precision, and 0.52 recall scores for SARS-CoV2 positive cases. In an expert validation, the classifier correctly identified 97.6% (81/84) as COVID-19 positive and 97.8% (91/93) as not SARS-CoV2 positive. The classifier labeled an additional 960 cases as not having SARS-CoV2 lab tests in hospital, and only 177 of those cases had the ICD-10 code for COVID-19. Discussion Proxy dataset performance may be worse because these instances sometimes include discussion of pending lab tests. The most predictive features are meaningful and interpretable. The type of external test that was performed is rarely mentioned. Conclusion COVID-19 cases that had testing done outside of the hospital can be reliably detected from the text in EHRs. Training on a proxy dataset was a suitable method for developing a highly performant classifier without labor-intensive labeling efforts.
Collapse
Affiliation(s)
- Lijing Wang
- Department of Data Science, New Jersey Institute of Technology, Newark, New Jersey, USA
| | - Amy R Zipursky
- Computational Health Informatics Program and Department of Emergency Medicine, Boston Children's Hospital, Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA
| | - Alon Geva
- Computational Health Informatics Program and Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children’s Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Andrew J McMurry
- Computational Health Informatics Program, Boston Children’s Hospital, Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA
| | - Kenneth D Mandl
- Computational Health Informatics Program, Boston Children’s Hospital, Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA
| | - Timothy A Miller
- Computational Health Informatics Program, Boston Children’s Hospital, Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|
9
|
Geva A, Akhondi-Asl A, Mehta NM. Validation and Extension of the Association Between Potentially Excess Oxygen Exposure and Death in Mechanically Ventilated Children. Pediatr Crit Care Med 2023; 24:e434-e440. [PMID: 37668503 DOI: 10.1097/pcc.0000000000003261] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 09/06/2023]
Abstract
OBJECTIVES "Cumulative excess oxygen exposure" (CEOE)-previously defined as the mean hourly administered Fio2 above 0.21 when the corresponding hourly Spo2 was 95% or above-was previously shown to be associated with mortality. The objective of this study was to examine the relationship among Fio2, Spo2, and mortality in an independent cohort of mechanically ventilated children. DESIGN Retrospective cross-sectional study. SETTING Quaternary-care PICU. PATIENTS All patients admitted to the PICU between 2012 and 2021 and mechanically ventilated via endotracheal tube for at least 24 hours. INTERVENTIONS None. MEASUREMENTS AND MAIN RESULTS Among 3,354 patients, 260 (8%) died. Higher CEOE quartile was associated with increased mortality (p = 0.001). The highest CEOE quartile had an 87% increased risk of mortality (95% CI, 7-236) compared with the first CEOE quartile. The hazard ratio for extended CEOE exposure, which included mechanical ventilation data from throughout the patients' mechanical ventilation time rather than only from the first 24 hours of mechanical ventilation, was 1.03 (95% CI, 1.02-1.03). CONCLUSIONS Potentially excess oxygen exposure in patients whose oxygen saturation was at least 95% was associated with increased mortality.
Collapse
Affiliation(s)
- Alon Geva
- Perioperative and Critical Care Center for Outcomes Research and Evaluation (PC-CORE), Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, MA
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA
| | - Alireza Akhondi-Asl
- Perioperative and Critical Care Center for Outcomes Research and Evaluation (PC-CORE), Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA
| | - Nilesh M Mehta
- Perioperative and Critical Care Center for Outcomes Research and Evaluation (PC-CORE), Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA
| |
Collapse
|
10
|
Atreya MR, Bennett TD, Geva A, Faustino EVS, Rogerson CM, Lutfi R, Cvijanovich NZ, Bigham MT, Nowak J, Schwarz AJ, Baines T, Haileselassie B, Thomas NJ, Luo Y, Sanchez-Pinto LN. External validation and biomarker assessment of a high-risk, data-driven pediatric sepsis phenotype characterized by persistent hypoxemia, encephalopathy, and shock. Res Sq 2023:rs.3.rs-3216613. [PMID: 37577648 PMCID: PMC10418531 DOI: 10.21203/rs.3.rs-3216613/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 08/15/2023]
Abstract
Objective Identification of children with sepsis-associated multiple organ dysfunction syndrome (MODS) at risk for poor outcomes remains a challenge. Data-driven phenotyping approaches that leverage electronic health record (EHR) data hold promise given the widespread availability of EHRs. We sought to externally validate the data-driven 'persistent hypoxemia, encephalopathy, and shock' (PHES) phenotype and determine its association with inflammatory and endothelial biomarkers, as well as biomarker-based pediatric risk-strata. Design We trained and validated a random forest classifier using organ dysfunction subscores in the EHR dataset used to derive the PHES phenotype. We used the classifier to assign phenotype membership in a test set consisting of prospectively enrolled pediatric septic shock patients. We compared biomarker profiles of those with and without the PHES phenotype and determined the association with established biomarker-based mortality and MODS risk-strata. Setting 25 pediatric intensive care units (PICU) across the U.S. Patients EHR data from 15,246 critically ill patients sepsis-associated MODS and 1,270 pediatric septic shock patients in the test cohort of whom 615 had biomarker data. Interventions None. Measurements and Main Results The area under the receiver operator characteristic curve (AUROC) of the new classifier to predict PHES phenotype membership was 0.91(95%CI, 0.90-0.92) in the EHR validation set. In the test set, patients with the PHES phenotype were independently associated with both increased odds of complicated course (adjusted odds ratio [aOR] of 4.1, 95%CI: 3.2-5.4) and 28-day mortality (aOR of 4.8, 95%CI: 3.11-7.25) after controlling for age, severity of illness, and immuno-compromised status. Patients belonging to the PHES phenotype were characterized by greater degree of systemic inflammation and endothelial activation, and overlapped with high risk-strata based on PERSEVERE biomarkers predictive of death and persistent MODS. Conclusions The PHES trajectory-based phenotype is reproducible, independently associated with poor clinical outcomes, and overlap with higher risk-strata based on validated biomarker approaches.
Collapse
Affiliation(s)
- Mihir R Atreya
- Division of Critical Care Medicine, Cincinnati Children's Hospital Medical Center and Cincinnati Children's Research Foundation, Cincinnati, 45229, OH, USA
- Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, OH 45267, USA
| | - Tellen D Bennett
- Departments of Pediatrics and Biomedical Informatics, University of Colorado School of Medicine, Aurora, CO
| | - Alon Geva
- Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, MA; Computational Health Informatics Program, Boston Children's Hospital, Boston, MA
| | | | - Colin M Rogerson
- Department of Pediatrics, Riley Hospital for Children, Indianapolis, IN 46202, USA
| | - Riad Lutfi
- Department of Pediatrics, Riley Hospital for Children, Indianapolis, IN 46202, USA
| | - Natalie Z Cvijanovich
- Department of Pediatrics, UCSF Benioff Children's Hospital Oakland, Oakland, CA 94609, USA
| | - Michael T Bigham
- Department of Pediatrics, Akron Children's Hospital, Akron, OH 44308, USA
| | - Jeffrey Nowak
- Department of Pediatrics, Children's Hospital and Clinics of Minnesota, Minneapolis, MN 55404, USA
| | - Adam J Schwarz
- Children's Hospital of Orange County, Orange, CA 92868, USA
| | - Torrey Baines
- University of Florida Health Shands Children's Hospital, Gainesville, FL 32610, USA
| | | | - Neal J Thomas
- Department of Pediatrics, Penn State Hershey Children's Hospital, Hershey, PA 17033, USA
| | - Yuan Luo
- Department of Pediatrics, Northwestern University Feinberg School of Medicine, Chicago, 60611, IL, USA
| | - L Nelson Sanchez-Pinto
- Department of Pediatrics, Northwestern University Feinberg School of Medicine, Chicago, 60611, IL, USA
- Department of Health and Biomedical Informatics, Northwestern University Feinberg School of Medicine, Chicago, 60611, IL, USA
| |
Collapse
|
11
|
Prince RD, Blumenthal JA, Geva A. Examining the Evidence for Escalating Antimicrobial Regimens in Febrile Oncology and Hematopoietic Stem Cell Transplant Patients Admitted to the PICU: An Observational Study. Pediatr Crit Care Med 2023; 24:e292-e296. [PMID: 37036203 DOI: 10.1097/pcc.0000000000003238] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 04/11/2023]
Abstract
OBJECTIVES To examine whether escalating antimicrobial treatment in pediatric oncology and hematopoietic cell transplantation (HSCT) patients admitted to the PICU is supported by culture data or affects patient outcomes. DESIGN Retrospective cross-sectional study. SETTING Quaternary care PICU. PATIENTS Patients younger than 18 years old who were admitted to the PICU at Boston Children's Hospital from 2012 to 2017 with a diagnosis of cancer or who had received HSCT and who had suspected sepsis at the time of PICU admission. INTERVENTIONS None. MEASUREMENTS AND MAIN RESULTS Of 791 PICU admissions for 544 patients that met inclusion criteria, 71 (9%) had escalation of antimicrobial therapy. Median Pediatric Logistic Organ Dysfunction (PELOD) score was higher in the escalation group (4 vs 3; p = 0.01). There were 14 admissions (20%) with a positive culture in the escalation group and 110 (15%) in the no escalation group ( p = 0.31). In the escalation group, there were only 2 (3%) cultures with organisms resistant to the initial antimicrobial regimen, compared with 28 (4%) cultures with resistant organisms in the no escalation group ( p = 1). Mortality in the escalation group was higher (17%) compared with the nonescalation group (5%; p < 0.001). The escalation group had more acute kidney injury (AKI) (25%) during treatment compared with the no escalation group (15%; p = 0.04), although this difference was not statistically significant when controlling for age, neutropenia, and PELOD-2 score (odds ratio, 1.75; 95% CI, 0.95-3.08; p = 0.06). CONCLUSIONS Few patients who had escalation of antimicrobials proved on culture data to have an organism resistant to the initial antimicrobials, and more patients developed AKI during escalated treatment. While the escalation group likely represents a sicker population, whether some of these patients would be safer without escalation of antimicrobial therapy warrants further study.
Collapse
Affiliation(s)
- Remi D Prince
- Tufts University School of Medicine, Boston, MA
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, MA
| | - Jennifer A Blumenthal
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, MA
| | - Alon Geva
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA
| |
Collapse
|
12
|
LaRovere KL, Luchette M, Akhondi-Asl A, DeSouza BJ, Tasker RC, Mehta NM, Geva A. Heart Rate Change as a Potential Digital Biomarker of Brain Death in Critically Ill Children With Acute Catastrophic Brain Injury. Crit Care Explor 2023; 5:e0908. [PMID: 37151893 PMCID: PMC10158912 DOI: 10.1097/cce.0000000000000908] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/09/2023] Open
Abstract
Bedside measurement of heart rate (HR) change (HRC) may provide an objective physiologic marker for when brain death (BD) may have occurred, and BD testing is indicated in children. OBJECTIVES To determine whether HRC, calculated using numeric HR measurements sampled every 5 seconds, can identify patients with BD among patients with catastrophic brain injury (CBI). DESIGN SETTING AND PARTICIPANTS Single-center, retrospective study (2008-2020) of critically ill children with acute CBI. Patients with CBI had a neurocritical care consultation, were admitted to an ICU, had acute neurologic injury on presentation or during hospitalization based on clinical and/or imaging findings, and died or survived with Glasgow Coma Scale (GCS) less than 13 at hospital discharge. Patients meeting BD criteria (BD group) were compared with those with cardiopulmonary death (CD group) or those who survived to discharge. MAIN OUTCOMES AND MEASURES HRC was calculated as the interquartile range of HR divided by median HR using 5-minute windows with 50% overlap for up to 5 days before death or end of recording. HRC was compared among the BD, CD, and survivor groups. RESULTS Of 96 patients with CBI (69% male, median age 4 years), 28 died (8 BD, 20 CD) and 20 survived (median GCS 9 at discharge). Within 24 hours before death, HRC was lower in BD compared with CD patients or survivors (0.01 vs 0.03 vs 0.04, p = 0.001). In BD patients, HRC decreased at least 1 day before death. HRC discriminated BD from CD patients and survivors with 90% sensitivity, 70% specificity, 44% positive predictive value, 96% negative predictive value (area under the receiver operating characteristic curve 0.88, 95% CI, 0.80-0.93). CONCLUSIONS AND RELEVANCE HRC is a novel digital biomarker that, with further validation, may be useful as a classifier for BD in the overall course of patients with CBI.
Collapse
Affiliation(s)
- Kerri L LaRovere
- Department of Neurology, Boston Children's Hospital and Harvard Medical School, Boston, MA
- Department of Anesthesiology, Critical Care and Pain Medicine, Perioperative and Critical Care Center for Outcomes Research and Evaluation (PC-CORE), Boston Children's Hospital, Boston, MA
| | - Matthew Luchette
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital and Department of Anesthesia, Harvard Medical School, Boston, MA
- Department of Anesthesiology, Critical Care and Pain Medicine, Perioperative and Critical Care Center for Outcomes Research and Evaluation (PC-CORE), Boston Children's Hospital, Boston, MA
| | - Alireza Akhondi-Asl
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital and Department of Anesthesia, Harvard Medical School, Boston, MA
- Department of Anesthesiology, Critical Care and Pain Medicine, Perioperative and Critical Care Center for Outcomes Research and Evaluation (PC-CORE), Boston Children's Hospital, Boston, MA
| | - Bradley J DeSouza
- Department of Critical Care Medicine, Children's Hospital Los Angeles and Keck School of Medicine, University of Southern California, Los Angeles, CA
| | - Robert C Tasker
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital and Department of Anesthesia, Harvard Medical School, Boston, MA
| | - Nilesh M Mehta
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital and Department of Anesthesia, Harvard Medical School, Boston, MA
- Department of Anesthesiology, Critical Care and Pain Medicine, Perioperative and Critical Care Center for Outcomes Research and Evaluation (PC-CORE), Boston Children's Hospital, Boston, MA
| | - Alon Geva
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital and Department of Anesthesia, Harvard Medical School, Boston, MA
- Department of Anesthesiology, Critical Care and Pain Medicine, Perioperative and Critical Care Center for Outcomes Research and Evaluation (PC-CORE), Boston Children's Hospital, Boston, MA
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA
| |
Collapse
|
13
|
Mayourian J, Sleeper L, Lee J, Lu M, Geva A, Mulder B, Babu-Narayan SV, Wald R, Sompolinsky T, Valente AM, Geva T. DEVELOPMENT AND VALIDATION OF AN OUTCOME PREDICTION MODEL FOR REPAIRED TETRALOGY OF FALLOT: THE INDICATOR COHORT. J Am Coll Cardiol 2023. [DOI: 10.1016/s0735-1097(23)01971-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/06/2023]
|
14
|
Wang L, Zipursky A, Geva A, McMurry AJ, Mandl KD, Miller TA. A computable phenotype for patients with SARS-CoV2 testing that occurred outside the hospital. medRxiv 2023:2023.01.19.23284738. [PMID: 36711461 PMCID: PMC9882620 DOI: 10.1101/2023.01.19.23284738] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/21/2023]
Abstract
Objective To identify a cohort of COVID-19 cases, including when evidence of virus positivity was only mentioned in the clinical text, not in structured laboratory data in the electronic health record (EHR). Materials and Methods Statistical classifiers were trained on feature representations derived from unstructured text in patient electronic health records (EHRs). We used a proxy dataset of patients with COVID-19 polymerase chain reaction (PCR) tests for training. We selected a model based on performance on our proxy dataset and applied it to instances without COVID-19 PCR tests. A physician reviewed a sample of these instances to validate the classifier. Results On the test split of the proxy dataset, our best classifier obtained 0.56 F1, 0.6 precision, and 0.52 recall scores for SARS-CoV2 positive cases. In an expert validation, the classifier correctly identified 90.8% (79/87) as COVID-19 positive and 97.8% (91/93) as not SARS-CoV2 positive. The classifier identified an additional 960 positive cases that did not have SARS-CoV2 lab tests in hospital, and only 177 of those cases had the ICD-10 code for COVID-19. Discussion Proxy dataset performance may be worse because these instances sometimes include discussion of pending lab tests. The most predictive features are meaningful and interpretable. The type of external test that was performed is rarely mentioned. Conclusion COVID-19 cases that had testing done outside of the hospital can be reliably detected from the text in EHRs. Training on a proxy dataset was a suitable method for developing a highly performant classifier without labor intensive labeling efforts.
Collapse
|
15
|
Nogues IE, Wen J, Lin Y, Liu M, Tedeschi SK, Geva A, Cai T, Hong C. Weakly Semi-supervised phenotyping using Electronic Health records. J Biomed Inform 2022; 134:104175. [PMID: 36064111 PMCID: PMC10112494 DOI: 10.1016/j.jbi.2022.104175] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2021] [Revised: 04/23/2022] [Accepted: 08/15/2022] [Indexed: 01/07/2023]
Abstract
OBJECTIVE Electronic Health Record (EHR) based phenotyping is a crucial yet challenging problem in the biomedical field. Though clinicians typically determine patient-level diagnoses via manual chart review, the sheer volume and heterogeneity of EHR data renders such tasks challenging, time-consuming, and prohibitively expensive, thus leading to a scarcity of clinical annotations in EHRs. Weakly supervised learning algorithms have been successfully applied to various EHR phenotyping problems, due to their ability to leverage information from large quantities of unlabeled samples to better inform predictions based on a far smaller number of patients. However, most weakly supervised methods are subject to the challenge to choose the right cutoff value to generate an optimal classifier. Furthermore, since they only utilize the most informative features (i.e., main ICD and NLP counts) they may fail for episodic phenotypes that cannot be consistently detected via ICD and NLP data. In this paper, we propose a label-efficient, weakly semi-supervised deep learning algorithm for EHR phenotyping (WSS-DL), which overcomes the limitations above. MATERIALS AND METHODS WSS-DL classifies patient-level disease status through a series of learning stages: 1) generating silver standard labels, 2) deriving enhanced-silver-standard labels by fitting a weakly supervised deep learning model to data with silver standard labels as outcomes and high dimensional EHR features as input, and 3) obtaining the final prediction score and classifier by fitting a supervised learning model to data with a minimal number of gold standard labels as the outcome, and the enhanced-silver-standard labels and a minimal set of most informative EHR features as input. To assess the generalizability of WSS-DL across different phenotypes and medical institutions, we apply WSS-DL to classify a total of 17 diseases, including both acute and chronic conditions, using EHR data from three healthcare systems. Additionally, we determine the minimum quantity of training labels required by WSS-DL to outperform existing supervised and semi-supervised phenotyping methods. RESULTS The proposed method, in combining the strengths of deep learning and weakly semi-supervised learning, successfully leverages the crucial phenotyping information contained in EHR features from unlabeled samples. Indeed, the deep learning model's ability to handle high-dimensional EHR features allows it to generate strong phenotype status predictions from silver standard labels. These predictions, in turn, provide highly effective features in the final logistic regression stage, leading to high phenotyping accuracy in notably small subsets of labeled data (e.g. n = 40 labeled samples). CONCLUSION Our method's high performance in EHR datasets with very small numbers of labels indicates its potential value in aiding doctors to diagnose rare diseases as well as conditions susceptible to misdiagnosis.
Collapse
Affiliation(s)
| | - Jun Wen
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
| | - Yucong Lin
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA; Center for Statistical Science, Tsinghua University, Beijing, China
| | - Molei Liu
- Department of Biostatistics, Harvard T. H. Chan School of Public Health, Boston, MA, USA
| | - Sara K Tedeschi
- Department of Medicine, Division of Rheumatology, Inflammation and Immunity, Brigham and Women's Hospital, Boston, MA, USA
| | - Alon Geva
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA; Department of Anesthesiology, Critical Care, and Pain Medicine, and Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, USA; Department of Anesthesia, Harvard Medical School, Boston, MA, USA
| | - Tianxi Cai
- Department of Biostatistics, Harvard T. H. Chan School of Public Health, Boston, MA, USA; Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
| | - Chuan Hong
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA.
| |
Collapse
|
16
|
Cai T, He Z, Hong C, Zhang Y, Ho YL, Honerlaw J, Geva A, Ayakulangara Panickan V, King A, Gagnon DR, Gaziano M, Cho K, Liao K, Cai T. Scalable relevance ranking algorithm via semantic similarity assessment improves efficiency of medical chart review. J Biomed Inform 2022; 132:104109. [PMID: 35660521 DOI: 10.1016/j.jbi.2022.104109] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2022] [Revised: 04/30/2022] [Accepted: 05/29/2022] [Indexed: 01/19/2023]
Abstract
OBJECTIVE Accurately assigning phenotype information to individual patients via computational phenotyping using Electronic Health Records (EHRs) has been seen as the first step towards enabling EHRs for precision medicine research. Chart review labels annotated by clinical experts, also known as "gold standard" labels, are essential for the development and validation of computational phenotyping algorithms. However, given the complexity of EHR systems, the process of chart review is both labor intensive and time consuming. We propose a fully automated algorithm, referred to as pGUESS, to rank EHR notes according to their relevance to a given phenotype. By identifying the most relevant notes, pGUESS can greatly improve the efficiency and accuracy of chart reviews. METHOD pGUESS uses prior guided semantic similarity to measure the informativeness of a clinical note to a given phenotype. We first select candidate clinical concepts from a pool of comprehensive medical concepts using public knowledge sources and then derive the semantic embedding vector (SEV) for a reference article (SEVref) and each note (SEVnote). The algorithm scores the relevance of a note as the cosine similarity between SEVnote and SEVref. RESULTS The algorithm was validated against four sets of 200 notes that were manually annotated by clinical experts to assess their informativeness to one of three disease phenotypes. pGUESS algorithm substantially outperforms existing unsupervised approaches for classifying the relevance status with respect to both accuracy and scalability across phenotypes. Averaging over the three phenotypes, the rank correlation between the algorithm ranking and gold standard label was 0.64 for pGUESS, but only 0.47 and 0.35 for the next two best performing algorithms. pGUESS is also much more computationally scalable compared to existing algorithms. CONCLUSION pGUESS algorithm can substantially reduce the burden of chart review and holds potential in improving the efficiency and accuracy of human annotation.
Collapse
Affiliation(s)
- Tianrun Cai
- Division of Rheumatology, Inflammation, and Immunity, Brigham and Women's Hospital, 60 Fenwood Road, Boston, USA; Department of Biomedical Informatics, Harvard Medical School, 10 Shattuck Street, Suite 514, Boston, USA; VA Boston Healthcare System, 150 S Huntington Ave, Boston, USA.
| | - Zeling He
- Division of Rheumatology, Inflammation, and Immunity, Brigham and Women's Hospital, 60 Fenwood Road, Boston, USA; Department of Biostatistics, Harvard T.H. Chan School of Public Health, 677 Huntington Avenue, Boston, MA, USA
| | - Chuan Hong
- Department of Biostatistics & Bioinformatics, Duke University, Duke University Medical Center 2424 Erwin Road, Suite 1102 Hock Plaza Box 2721, Durham, NC, USA
| | - Yichi Zhang
- Department of Computer Science and Statistics, University of Rhode Island, Tyler Hall, 9 Greenhouse Road, Suite 2, Kingston, RI, USA
| | - Yuk-Lam Ho
- VA Boston Healthcare System, 150 S Huntington Ave, Boston, USA
| | | | - Alon Geva
- Department of Biomedical Informatics, Harvard Medical School, 10 Shattuck Street, Suite 514, Boston, USA; Department of Anesthesiology, Boston Children's Hospital, 300 Longwood Avenue, Bader, 6th Floor, Boston, MA, USA
| | | | - Amanda King
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, 677 Huntington Avenue, Boston, MA, USA
| | - David R Gagnon
- VA Boston Healthcare System, 150 S Huntington Ave, Boston, USA; Department of Biostatistics, Boston University, School of Public Health, 801 Massachusetts Ave Crosstown Center, Boston, MA, USA
| | - Michael Gaziano
- Division of Rheumatology, Inflammation, and Immunity, Brigham and Women's Hospital, 60 Fenwood Road, Boston, USA; VA Boston Healthcare System, 150 S Huntington Ave, Boston, USA
| | - Kelly Cho
- Division of Rheumatology, Inflammation, and Immunity, Brigham and Women's Hospital, 60 Fenwood Road, Boston, USA; Department of Biomedical Informatics, Harvard Medical School, 10 Shattuck Street, Suite 514, Boston, USA; VA Boston Healthcare System, 150 S Huntington Ave, Boston, USA
| | - Katherine Liao
- Division of Rheumatology, Inflammation, and Immunity, Brigham and Women's Hospital, 60 Fenwood Road, Boston, USA; Department of Biomedical Informatics, Harvard Medical School, 10 Shattuck Street, Suite 514, Boston, USA; VA Boston Healthcare System, 150 S Huntington Ave, Boston, USA
| | - Tianxi Cai
- Department of Biomedical Informatics, Harvard Medical School, 10 Shattuck Street, Suite 514, Boston, USA; VA Boston Healthcare System, 150 S Huntington Ave, Boston, USA; Department of Biostatistics, Harvard T.H. Chan School of Public Health, 677 Huntington Avenue, Boston, MA, USA
| |
Collapse
|
17
|
Yang Y, Geva A, Madden K, Mehta NM. Implementation Science in Pediatric Critical Care - Sedation and Analgesia Practices as a Case Study. Front Pediatr 2022; 10:864029. [PMID: 35859943 PMCID: PMC9289107 DOI: 10.3389/fped.2022.864029] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/28/2022] [Accepted: 05/30/2022] [Indexed: 11/30/2022] Open
Abstract
Sedation and analgesia (SA) management is essential practice in the pediatric intensive care unit (PICU). Over the past decade, there has been significant interest in optimal SA management strategy, due to reports of the adverse effects of SA medications and their relationship to ICU delirium. We reviewed 13 studies examining SA practices in the PICU over the past decade for the purposes of reporting the study design, outcomes of interest, SA protocols used, strategies for implementation, and the patient-centered outcomes. We highlighted the paucity of evidence-base for these practices and also described the existing gaps in the intersection of implementation science (IS) and SA protocols in the PICU. Future studies would benefit from a focus on effective implementation strategies to introduce and sustain evidence-based SA protocols, as well as novel quasi-experimental study designs that will help determine their impact on relevant clinical outcomes, such as the occurrence of ICU delirium. Adoption of the available evidence-based practices into routine care in the PICU remains challenging. Using SA practice as an example, we illustrated the need for a structured approach to the implementation science in pediatric critical care. Key components of the successful adoption of evidence-based best practice include the assessment of the local context, both resources and barriers, followed by a context-specific strategy for implementation and a focus on sustainability and integration of the practice into the permanent workflow.
Collapse
Affiliation(s)
- Youyang Yang
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital and Harvard Medical School, Boston, MA, United States
| | - Alon Geva
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital and Harvard Medical School, Boston, MA, United States
| | - Kate Madden
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital and Harvard Medical School, Boston, MA, United States
| | - Nilesh M Mehta
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital and Harvard Medical School, Boston, MA, United States
| |
Collapse
|
18
|
LaRovere KL, De Souza BJ, Szuch E, Urion DK, Vitali SH, Zhang B, Graham RJ, Geva A, Tasker RC. Clinical Characteristics and Outcomes of Children with Acute Catastrophic Brain Injury: A 13-Year Retrospective Cohort Study. Neurocrit Care 2021; 36:715-726. [PMID: 34893971 DOI: 10.1007/s12028-021-01408-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2021] [Accepted: 11/19/2021] [Indexed: 11/26/2022]
Abstract
BACKGROUND The purpose of this study was to describe and analyze clinical characteristics and outcomes in children with acute catastrophic brain injury (CBI). METHODS This was a single-center, 13-year (2008-2020) retrospective cohort study of children in the pediatric and cardiac intensive care units with CBI, defined as (1) acute neurologic injury based on clinical and/or imaging findings, (2) the need for life-sustaining intensive care unit therapies, and (3) death or survival with a Glasgow Coma Scale score < 13 at discharge. Patients were excluded if they were discharged directly to home < 14 days from admission or had a chronic neurologic condition with a baseline Glasgow Coma Scale score < 13. The association between the primary outcome of death and clinical variables was analyzed by using Kaplan-Meier estimates and multivariable Cox proportional hazard models. Outcomes assessed after discharge were technology dependence, neurologic deficits, and Functional Status Score. Improved functional status was defined as a change in total Functional Status Score [Formula: see text] 2. RESULTS Of 106 patients (58% boys, median age 3.9 years) with CBI, 86 (81%) died. Withdrawal of life-sustaining therapies was the most common cause of death (60 of 86, 70%). In our multivariable analysis, each unit increase in admission pediatric sequential organ failure assessment score was associated with 10% greater hazard of death (hazard ratio 1.10, 95% confidence interval 1.04-1.17, p < .01). After controlling for admission pediatric sequential organ failure assessment scores, compared with those of patients with traumatic brain injury, all other etiologies of CBI were associated with a greater hazard of death (p = .02; hazard ratio 3.76-10). The median survival time for the cohort was 22 days (95% confidence interval 14-37 days). Of 23 survivors to hospital discharge, 20 were still alive after a median of 2 years (interquartile range 1-3 years), 6 of 20 (30%) did not have any technology dependence, 12 of 20 (60%) regained normal levels of alertness and responsiveness, and 15 of 20 (75%) had improved functional status. CONCLUSIONS Most children with acute CBI died within 1 month of hospitalization. Having traumatic brain injury as the etiology of CBI was associated with greater survival, whereas increased organ dysfunction score on admission was associated with a higher hazard of mortality. Of the survivors, some recovered consciousness and functional status and did not require permanent technology dependence. Larger prospective studies are needed to improve prediction of CBI among critically ill children, understand factors guiding clinician and family decisions on the continuation or withdrawal of life-sustaining treatments, and characterize the natural history and long-term outcomes among CBI survivors.
Collapse
Affiliation(s)
- Kerri L LaRovere
- Department of Neurology, Boston Children's Hospital, Harvard Medical School, 300 Longwood Ave., Boston, MA, 02115, USA.
| | - Bradley J De Souza
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA
| | - Eliza Szuch
- Department of Pediatrics, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA
| | - David K Urion
- Department of Neurology, Boston Children's Hospital, Harvard Medical School, 300 Longwood Ave., Boston, MA, 02115, USA
| | - Sally H Vitali
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA
| | - Bo Zhang
- Department of Neurology, Boston Children's Hospital, Harvard Medical School, 300 Longwood Ave., Boston, MA, 02115, USA
| | - Robert J Graham
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA
| | - Alon Geva
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, USA
| | - Robert C Tasker
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA
| |
Collapse
|
19
|
Geva A, Patel MM, Newhams MM, Young CC, Son MBF, Kong M, Maddux AB, Hall MW, Riggs BJ, Singh AR, Giuliano JS, Hobbs CV, Loftis LL, McLaughlin GE, Schwartz SP, Schuster JE, Babbitt CJ, Halasa NB, Gertz SJ, Doymaz S, Hume JR, Bradford TT, Irby K, Carroll CL, McGuire JK, Tarquinio KM, Rowan CM, Mack EH, Cvijanovich NZ, Fitzgerald JC, Spinella PC, Staat MA, Clouser KN, Soma VL, Dapul H, Maamari M, Bowens C, Havlin KM, Mourani PM, Heidemann SM, Horwitz SM, Feldstein LR, Tenforde MW, Newburger JW, Mandl KD, Randolph AG. Data-driven clustering identifies features distinguishing multisystem inflammatory syndrome from acute COVID-19 in children and adolescents. EClinicalMedicine 2021; 40:101112. [PMID: 34485878 PMCID: PMC8405351 DOI: 10.1016/j.eclinm.2021.101112] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/01/2021] [Revised: 08/11/2021] [Accepted: 08/13/2021] [Indexed: 12/21/2022] Open
Abstract
BACKGROUND Multisystem inflammatory syndrome in children (MIS-C) consensus criteria were designed for maximal sensitivity and therefore capture patients with acute COVID-19 pneumonia. METHODS We performed unsupervised clustering on data from 1,526 patients (684 labeled MIS-C by clinicians) <21 years old hospitalized with COVID-19-related illness admitted between 15 March 2020 and 31 December 2020. We compared prevalence of assigned MIS-C labels and clinical features among clusters, followed by recursive feature elimination to identify characteristics of potentially misclassified MIS-C-labeled patients. FINDINGS Of 94 clinical features tested, 46 were retained for clustering. Cluster 1 patients (N = 498; 92% labeled MIS-C) were mostly previously healthy (71%), with mean age 7·2 ± 0·4 years, predominant cardiovascular (77%) and/or mucocutaneous (82%) involvement, high inflammatory biomarkers, and mostly SARS-CoV-2 PCR negative (60%). Cluster 2 patients (N = 445; 27% labeled MIS-C) frequently had pre-existing conditions (79%, with 39% respiratory), were similarly 7·4 ± 2·1 years old, and commonly had chest radiograph infiltrates (79%) and positive PCR testing (90%). Cluster 3 patients (N = 583; 19% labeled MIS-C) were younger (2·8 ± 2·0 y), PCR positive (86%), with less inflammation. Radiographic findings of pulmonary infiltrates and positive SARS-CoV-2 PCR accurately distinguished cluster 2 MIS-C labeled patients from cluster 1 patients. INTERPRETATION Using a data driven, unsupervised approach, we identified features that cluster patients into a group with high likelihood of having MIS-C. Other features identified a cluster of patients more likely to have acute severe COVID-19 pulmonary disease, and patients in this cluster labeled by clinicians as MIS-C may be misclassified. These data driven phenotypes may help refine the diagnosis of MIS-C.
Collapse
Affiliation(s)
- Alon Geva
- Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston,
These authors contributed equally to this work. A complete list of members and affiliations is provided in the Supplementary Appendix. MA, USA - Computational Health Informatics Program, Boston Children's Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA, USA
| | - Manish M. Patel
- COVID-19 Response, Centers for Disease Control and Prevention, Atlanta, GA, USA
- Influenza Division, Centers for Disease Control and Prevention, Atlanta, GA, USA
| | - Margaret M. Newhams
- Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston,
These authors contributed equally to this work. A complete list of members and affiliations is provided in the Supplementary Appendix. MA, USA
| | - Cameron C. Young
- Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston,
These authors contributed equally to this work. A complete list of members and affiliations is provided in the Supplementary Appendix. MA, USA
| | - Mary Beth F. Son
- Department of Pediatrics, Division of Immunology, Boston Children's Hospital, Boston, MA, USA
| | - Michele Kong
- Division of Pediatric Critical Care Medicine, Department of Pediatrics, University of Alabama at Birmingham, Birmingham, AL, USA
| | - Aline B. Maddux
- Department of Pediatrics, Section of Critical Care Medicine, University of Colorado School of Medicine and Children's Hospital Colorado, Aurora, CO, USA
| | - Mark W. Hall
- Division of Critical Care Medicine, Department of Pediatrics, Nationwide Children's Hospital, Columbus, OH, USA
| | - Becky J. Riggs
- Department of Anesthesiology and Critical Care Medicine; Division of Pediatric Anesthesiology & Critical Care Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA
| | - Aalok R. Singh
- Pediatric Critical Care Division, Maria Fareri Children's Hospital at Westchester Medical Center and New York Medical College, Valhalla, NY, USA
| | - John S. Giuliano
- Department of Pediatrics, Division of Critical Care, Yale University School of Medicine, New Haven, CT, USA
| | - Charlotte V. Hobbs
- Department of Pediatrics, Division of Disease; Microbiology; University of Mississippi Medical Center, Jackson, MS, USA
| | - Laura L. Loftis
- Section of Critical Care Medicine, Department of Pediatrics, Texas Children's Hospital, Houston, TX, USA
| | - Gwenn E. McLaughlin
- Division of Pediatric Critical Care Medicine, Department of Pediatrics, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Stephanie P. Schwartz
- Department of Pediatrics, University of North Carolina at Chapel Hill Children's Hospital, Chapel Hill, NC, USA
| | - Jennifer E. Schuster
- Division of Pediatric Infectious Disease, Department of Pediatrics, Children's Mercy Kansas City, Kansas City, MO, USA
| | | | - Natasha B. Halasa
- Division of Pediatric Infectious Diseases, Department of Pediatrics, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Shira J. Gertz
- Division of Pediatric Critical Care, Department of Pediatrics, Saint Barnabas Medical Center, Livingston, NJ, USA
| | - Sule Doymaz
- Division of Pediatric Critical Care, Department of Pediatrics, SUNY Downstate Health Sciences University, Brooklyn, NY, USA
| | - Janet R. Hume
- Division of Pediatric Critical Care, University of Minnesota Masonic Children's Hospital, Minneapolis, MN, USA
| | - Tamara T. Bradford
- Department of Pediatrics, Division of Cardiology, Louisiana State University Health Sciences Center and Children's Hospital of New Orleans, New Orleans, LA, USA
| | - Katherine Irby
- Section of Pediatric Critical Care, Department of Pediatrics, Arkansas Children's Hospital, Little Rock, AR, USA
| | | | - John K. McGuire
- Division of Pediatric Critical Care Medicine, Department of Pediatrics, Seattle Children's Hospital and the University of Washington, Seattle, WA, USA
| | - Keiko M. Tarquinio
- Division of Critical Care Medicine, Department of Pediatrics, Emory University School of Medicine, Children's Healthcare of Atlanta, Atlanta, GA, USA
| | - Courtney M. Rowan
- Division of Pediatric Critical Care Medicine, Department of Pediatrics, Indiana University School of Medicine, Riley Hospital for Children, Indianapolis, IN, USA
| | - Elizabeth H. Mack
- Division of Pediatric Critical Care Medicine, Medical University of South Carolina, Charleston, SC, USA
| | | | - Julie C. Fitzgerald
- Division of Critical Care, Department of Anesthesiology and Critical Care, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA
| | - Philip C. Spinella
- Division of Critical Care, Department of Pediatrics, Washington University School of Medicine in St Louis, St Louis, MO, USA
| | - Mary A. Staat
- Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA
| | - Katharine N. Clouser
- Department of Pediatrics, Hackensack Meridian School of Medicine, Hackensack, NJ, USA
| | - Vijaya L. Soma
- Department of Pediatrics, Division of Infectious Diseases, New York University Grossman School of Medicine and Hassenfeld Children's Hospital, New York, NY, USA
| | - Heda Dapul
- Division of Pediatric Critical Care Medicine, Department of Pediatrics, New York University Grossman School of Medicine and Hassenfeld Children's Hospital, New York, NY, USA
| | - Mia Maamari
- Department of Pediatrics, Division of Critical Care Medicine, University of Texas Southwestern, Children's Health Medical Center Dallas, TX, USA
| | - Cindy Bowens
- Department of Pediatrics, Division of Pediatric Critical Care Medicine, University of Louisville, and Norton Children's Hospital, Louisville, KY, USA
| | - Kevin M. Havlin
- Department of Pediatrics, Division of Pediatric Critical Care Medicine, Central Michigan University, Detroit, MI, USA
| | - Peter M. Mourani
- Department of Pediatrics, Section of Critical Care Medicine, University of Colorado School of Medicine and Children's Hospital Colorado, Aurora, CO, USA
| | - Sabrina M. Heidemann
- Department of Pediatrics, Division of Pediatric Critical Care Medicine, Central Michigan University, Detroit, MI, USA
| | - Steven M. Horwitz
- Department of Pediatrics, Division of Pediatric Critical Care Medicine, Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ, USA
| | - Leora R. Feldstein
- COVID-19 Response, Centers for Disease Control and Prevention, Atlanta, GA, USA
- Influenza Division, Centers for Disease Control and Prevention, Atlanta, GA, USA
| | - Mark W. Tenforde
- COVID-19 Response, Centers for Disease Control and Prevention, Atlanta, GA, USA
- Influenza Division, Centers for Disease Control and Prevention, Atlanta, GA, USA
| | - Jane W. Newburger
- Department of Cardiology, Boston Children's Hospital, Boston, MA, USA
| | - Kenneth D. Mandl
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA
- Departments of Biomedical Informatics and Pediatrics, Harvard Medical School, Boston, MA, USA
| | - Adrienne G. Randolph
- Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston,
These authors contributed equally to this work. A complete list of members and affiliations is provided in the Supplementary Appendix. MA, USA - Departments of Anaesthesia and Pediatrics, Harvard Medical School, Boston, MA, USA
- Corresponding author at: Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Bader 634, 300 Longwood Avenue, Boston, MA 02115, USA.
| | | |
Collapse
|
20
|
Yang Y, Akhondi-Asl A, Geva A, Dwyer D, Stickney C, Kleinman ME, Madden K, Sanderson A, Mehta NM. Implementation of an Analgesia-Sedation Protocol Is Associated With Reduction in Midazolam Usage in the PICU. Pediatr Crit Care Med 2021; 22:e513-e523. [PMID: 33852546 PMCID: PMC8490269 DOI: 10.1097/pcc.0000000000002729] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Abstract
OBJECTIVES Examine the association of a revised analgesia-sedation protocol with midazolam usage in the PICU. DESIGN A single-center nonrandomized before-after study. SETTING PICU at a quaternary pediatric hospital (Boston Children's Hospital, Boston, MA). PATIENTS Children admitted to the PICU who were mechanically ventilated for greater than 24 hours. The preimplementation cohort included 190 eligible patients admitted between July 29, 2017, and February 28, 2018, and the postimplementation cohort included 144 patients admitted between July 29, 2019, and February 28, 2020. INTERVENTIONS Implementation of a revised analgesia-sedation protocol. MEASUREMENTS AND MAIN RESULTS Our primary outcome, total dose of IV midazolam administered in mechanically ventilated patients up to day 14 of ventilation, decreased by 72% (95% CI [61-80%]; p < 0.001) in the postimplementation cohort. Dexmedetomidine usage increased 230% (95% CI [145-344%]) in the postimplementation cohort. Opioid usage, our balancing metric, was not significantly different between the two cohorts. There were no significant differences in ventilator-free days, PICU length of stay, rate of unplanned extubations, failed extubations, cardiorespiratory arrest events, and 24-hour readmissions to the PICU. CONCLUSIONS We successfully implemented an analgesia-sedation protocol that primarily uses dexmedetomidine and intermittent opioids, and it was associated with significant decrease in overall midazolam usage in mechanically ventilated patients in the PICU. The intervention was not associated with changes in opioid usage or prevalence of adverse events.
Collapse
Affiliation(s)
- Youyang Yang
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital and Department of Anaesthesia, Harvard Medical School, Boston, MA
| | - Alireza Akhondi-Asl
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital and Department of Anaesthesia, Harvard Medical School, Boston, MA
| | - Alon Geva
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital and Department of Anaesthesia, Harvard Medical School, Boston, MA
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA
| | - Danielle Dwyer
- Division of Medical Critical Care, Boston Children's Hospital and Department of Pediatrics, Harvard Medical School, Boston, MA
| | - Carolyn Stickney
- Division of Medical Critical Care, Boston Children's Hospital and Department of Pediatrics, Harvard Medical School, Boston, MA
| | - Monica E Kleinman
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital and Department of Anaesthesia, Harvard Medical School, Boston, MA
| | - Kate Madden
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital and Department of Anaesthesia, Harvard Medical School, Boston, MA
| | - Amy Sanderson
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital and Department of Anaesthesia, Harvard Medical School, Boston, MA
| | - Nilesh M Mehta
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital and Department of Anaesthesia, Harvard Medical School, Boston, MA
| |
Collapse
|
21
|
Geva A, Albert BD, Hamilton S, Manning MJ, Barrett MK, Mirchandani D, Harty M, Morgan EC, Kleinman ME, Mehta NM. eSIMPLER: A Dynamic, Electronic Health Record-Integrated Checklist for Clinical Decision Support During PICU Daily Rounds. Pediatr Crit Care Med 2021; 22:898-905. [PMID: 33935271 PMCID: PMC8490208 DOI: 10.1097/pcc.0000000000002733] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
Abstract
OBJECTIVES Design, implement, and evaluate a rounding checklist with deeply embedded, dynamic electronic health record integration. DESIGN Before-after quality-improvement study. SETTING Quaternary PICU in an academic, free-standing children's hospital. PATIENTS All patients in the PICU during daily morning rounds. INTERVENTIONS Implementation of an updated dynamic checklist (eSIMPLER) providing clinical decision support prompts with display of relevant data automatically pulled from the electronic health record. MEASUREMENTS AND MAIN RESULTS The prior daily rounding checklist, eSIMPLE, was implemented for 49,709 patient-days (7,779 patients) between October 30, 2011, and October 7, 2018. eSIMPLER was implemented for 5,306 patient-days (971 patients) over 6 months. Checklist completion rates were similar (eSIMPLE: 95% [95% CI, 88-98%] vs eSIMPLER: 98% [95% CI, 92-100%] of patient-days; p = 0.40). eSIMPLER required less time per patient (28 ± 1 vs 47 ± 24 s; p < 0.001). Users reported improved satisfaction with eSIMPLER (p = 0.009). Several checklist-driven process measures-discordance between electronic health record orders for stress ulcer prophylaxis and user-recorded indication for stress ulcer prophylaxis, rate of venous thromboembolism prophylaxis prescribing, and recognition of reduced renal function-improved during the eSIMPLER phase. CONCLUSIONS eSIMPLER, a dynamic, electronic health record-informed checklist, required less time to complete and improved certain care processes compared with a prior, static checklist with limited electronic health record data. By focusing on the "Five Rights" of clinical decision support, we created a well-accepted clinical decision support tool that was integrated efficiently into daily rounds. Generalizability of eSIMPLER's effectiveness and its impact on patient outcomes need to be examined.
Collapse
Affiliation(s)
- Alon Geva
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children’s Hospital, Boston, MA
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA
| | - Ben D. Albert
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children’s Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA
| | - Susan Hamilton
- Department of Cardiovascular and Critical Care Nursing, Medical-Surgical Intensive Care Unit, Boston Children’s Hospital, Boston, MA
| | - Mary-Jeanne Manning
- Department of Cardiovascular and Critical Care Nursing, Medical-Surgical Intensive Care Unit, Boston Children’s Hospital, Boston, MA
| | - Megan K. Barrett
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children’s Hospital, Boston, MA
| | - Dimple Mirchandani
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children’s Hospital, Boston, MA
| | - Matthew Harty
- Anesthesia Information Services, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children’s Hospital, Boston, MA
| | - Erin C. Morgan
- Anesthesia Information Services, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children’s Hospital, Boston, MA
| | - Monica E. Kleinman
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children’s Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA
| | - Nilesh M. Mehta
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children’s Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA
| |
Collapse
|
22
|
Klann JG, Estiri H, Weber GM, Moal B, Avillach P, Hong C, Tan ALM, Beaulieu-Jones BK, Castro V, Maulhardt T, Geva A, Malovini A, South AM, Visweswaran S, Morris M, Samayamuthu MJ, Omenn GS, Ngiam KY, Mandl KD, Boeker M, Olson KL, Mowery DL, Follett RW, Hanauer DA, Bellazzi R, Moore JH, Loh NHW, Bell DS, Wagholikar KB, Chiovato L, Tibollo V, Rieg S, Li ALLJ, Jouhet V, Schriver E, Xia Z, Hutch M, Luo Y, Kohane IS, Brat GA, Murphy SN. Validation of an internationally derived patient severity phenotype to support COVID-19 analytics from electronic health record data. J Am Med Inform Assoc 2021; 28:1411-1420. [PMID: 33566082 PMCID: PMC7928835 DOI: 10.1093/jamia/ocab018] [Citation(s) in RCA: 23] [Impact Index Per Article: 7.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/08/2020] [Revised: 01/14/2021] [Accepted: 01/29/2021] [Indexed: 12/21/2022] Open
Abstract
OBJECTIVE The Consortium for Clinical Characterization of COVID-19 by EHR (4CE) is an international collaboration addressing coronavirus disease 2019 (COVID-19) with federated analyses of electronic health record (EHR) data. We sought to develop and validate a computable phenotype for COVID-19 severity. MATERIALS AND METHODS Twelve 4CE sites participated. First, we developed an EHR-based severity phenotype consisting of 6 code classes, and we validated it on patient hospitalization data from the 12 4CE clinical sites against the outcomes of intensive care unit (ICU) admission and/or death. We also piloted an alternative machine learning approach and compared selected predictors of severity with the 4CE phenotype at 1 site. RESULTS The full 4CE severity phenotype had pooled sensitivity of 0.73 and specificity 0.83 for the combined outcome of ICU admission and/or death. The sensitivity of individual code categories for acuity had high variability-up to 0.65 across sites. At one pilot site, the expert-derived phenotype had mean area under the curve of 0.903 (95% confidence interval, 0.886-0.921), compared with an area under the curve of 0.956 (95% confidence interval, 0.952-0.959) for the machine learning approach. Billing codes were poor proxies of ICU admission, with as low as 49% precision and recall compared with chart review. DISCUSSION We developed a severity phenotype using 6 code classes that proved resilient to coding variability across international institutions. In contrast, machine learning approaches may overfit hospital-specific orders. Manual chart review revealed discrepancies even in the gold-standard outcomes, possibly owing to heterogeneous pandemic conditions. CONCLUSIONS We developed an EHR-based severity phenotype for COVID-19 in hospitalized patients and validated it at 12 international sites.
Collapse
Affiliation(s)
- Jeffrey G Klann
- Laboratory of Computer Science, Department of Medicine, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Hossein Estiri
- Laboratory of Computer Science, Department of Medicine, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Griffin M Weber
- Department of Biomedical Informatics, Department of Medicine, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts, USA
| | - Bertrand Moal
- IAM Unit, Public Health Department , Bordeaux University Hospital, Bordeaux, France
| | - Paul Avillach
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA
| | - Chuan Hong
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA
| | - Amelia L M Tan
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA
| | - Brett K Beaulieu-Jones
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA
| | - Victor Castro
- Research Information Science and Computing, Mass General Brigham, Boston, Massachusetts, USA
| | - Thomas Maulhardt
- Institute of Medical Biometry and Statistics, Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
| | - Alon Geva
- Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, Massachusetts, USA.,Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA
| | - Alberto Malovini
- Laboratory of Informatics and Systems Engineering for Clinical Research, Istituti Clinici Scientifici Maugeri IRCCS, Pavia, Italy
| | - Andrew M South
- Section of Nephrology, Department of Pediatrics, Brenner Children's Hospital, Wake Forest School of Medicine, Winston Salem, North Carolina, USA
| | - Shyam Visweswaran
- Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Michele Morris
- Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Malarkodi J Samayamuthu
- Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Gilbert S Omenn
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, Michigan, USA
| | - Kee Yuan Ngiam
- Department of Biomedical Informatics-WisDM, National University Health System, Singapore
| | - Kenneth D Mandl
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA
| | - Martin Boeker
- Institute of Medical Biometry and Statistics, Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
| | - Karen L Olson
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA
| | - Danielle L Mowery
- Department of Biostatistics, Epidemiology, and Informatics, Institute for Biomedical Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA
| | - Robert W Follett
- Department of Medicine, David Geffen School of Medicine at UCLA, Los Angeles, California, USA
| | - David A Hanauer
- Department of Learning Health Sciences, University of Michigan Medical School, Ann Arbor, Michigan, USA
| | - Riccardo Bellazzi
- Laboratory of Informatics and Systems Engineering for Clinical Research, Istituti Clinici Scientifici Maugeri IRCCS, Pavia, Italy.,Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Italy
| | - Jason H Moore
- Department of Biostatistics, Epidemiology, and Informatics, Institute for Biomedical Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA
| | - Ne-Hooi Will Loh
- Division of Critical Care, National University Health System, Singapore
| | - Douglas S Bell
- Department of Medicine, David Geffen School of Medicine at UCLA, Los Angeles, California, USA
| | | | - Luca Chiovato
- Laboratory of Informatics and Systems Engineering for Clinical Research, Istituti Clinici Scientifici Maugeri IRCCS, Pavia, Italy.,Department of Internal Medicine and Medical Therapy, University of Pavia, Pavia, Italy
| | - Valentina Tibollo
- Laboratory of Informatics and Systems Engineering for Clinical Research, Istituti Clinici Scientifici Maugeri IRCCS, Pavia, Italy
| | - Siegbert Rieg
- Division of Infectious Diseases, Department of Medicine II, Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
| | - Anthony L L J Li
- National Center for Infectious Diseases, Tan Tock Seng Hospital, Singapore
| | - Vianney Jouhet
- ERIAS-INSERM U1219 BPH, Bordeaux University Hospital, Bordeaux, France
| | - Emily Schriver
- Data Analytics Center, Penn Medicine, Philadelphia, Pennsylvania, USA
| | - Zongqi Xia
- Department of Neurology, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Meghan Hutch
- Department of Preventive Medicine, Northwestern University Feinberg School of Medicine, Chicago, Illinois, USA
| | - Yuan Luo
- Department of Preventive Medicine, Northwestern University Feinberg School of Medicine, Chicago, Illinois, USA
| | - Isaac S Kohane
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA
| | | | - Gabriel A Brat
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA
| | - Shawn N Murphy
- Department of Neurology, Massachusetts General Hospital, Boston, Massachusetts, USA.,Research Information Science and Computing , Mass General Brigham, Boston, Massachusetts, USA
| |
Collapse
|
23
|
Deshpande SJ, Vitali S, Thiagarajan R, Brediger S, McManus M, Geva A. Coagulations Studies Do Not Correlate With Each Other or With Hematologic Complications During Pediatric Extracorporeal Membrane Oxygenation. Pediatr Crit Care Med 2021; 22:542-552. [PMID: 33660700 PMCID: PMC8178186 DOI: 10.1097/pcc.0000000000002698] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Abstract
OBJECTIVES Anticoagulation plays a key role in the management of children supported with extracorporeal membrane oxygenation. However, the ideal strategy for monitoring anticoagulation remains unclear. Our objective was to evaluate the utility of laboratory measures of anticoagulation in pediatric extracorporeal membrane oxygenation. DESIGN Retrospective cohort study. SETTING Quaternary care academic children's hospital. PATIENTS Children in a noncardiac PICU cannulated to extracorporeal membrane oxygenation in 2010-2016. INTERVENTIONS None. MEASUREMENTS AND MAIN RESULTS Demographic data, laboratory values, and heparin doses were extracted from the enterprise data warehouse. Primary diagnoses, indications for cannulation, hemorrhagic and thrombotic complications, and survival outcomes were abstracted from the local registry used for Extracorporeal Life Support Organization reporting. Statistical models accounting for repeated measures using generalized estimating equations were constructed to evaluate correlations between heparin doses and laboratory values; among laboratory values; and between heparin dose or laboratory values and clinical outcomes. One hundred thirty-three unique patients-78 neonates and 55 older patients-were included in the study. There was no significant association between antifactor Xa level, activated partial thromboplastin time, activated clotting time, or heparin dose with hemorrhage or thrombosis (odds ratio ≅ 1 for all associations). There was weak-to-moderate correlation between antifactor Xa, activated partial thromboplastin time, and activated clotting time in both neonates and older pediatric patients (R2 < 0.001 to 0.456). Heparin dose correlated poorly with laboratory measurements in both age groups (R2 = 0.010-0.063). CONCLUSIONS In children supported with extracorporeal membrane oxygenation, heparin dose correlates poorly with common laboratory measures of anticoagulation, and these laboratory measures correlate poorly with each other. Neither heparin dose nor laboratory measures correlate with hemorrhage or thrombosis. Further work is needed to identify better measures of anticoagulation in order to minimize morbidity and mortality associated with extracorporeal membrane oxygenation.
Collapse
Affiliation(s)
- Shyam J. Deshpande
- Department of Anesthesiology and Pain Medicine, University of Washington, Seattle, WA
| | - Sally Vitali
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children’s Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA
| | - Ravi Thiagarajan
- Department of Cardiology, Boston Children’s Hospital, Boston, MA
- Department of Pediatrics, Harvard Medical School, Boston, MA
| | - Steven Brediger
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children’s Hospital, Boston, MA
| | - Michael McManus
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children’s Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA
| | - Alon Geva
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children’s Hospital, Boston, MA
- Department of Anaesthesia, Harvard Medical School, Boston, MA
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, MA
| |
Collapse
|
24
|
Bourgeois FT, Gutiérrez-Sacristán A, Keller MS, Liu M, Hong C, Bonzel CL, Tan ALM, Aronow BJ, Boeker M, Booth J, Cruz Rojo J, Devkota B, García Barrio N, Gehlenborg N, Geva A, Hanauer DA, Hutch MR, Issitt RW, Klann JG, Luo Y, Mandl KD, Mao C, Moal B, Moshal KL, Murphy SN, Neuraz A, Ngiam KY, Omenn GS, Patel LP, Jiménez MP, Sebire NJ, Balazote PS, Serret-Larmande A, South AM, Spiridou A, Taylor DM, Tippmann P, Visweswaran S, Weber GM, Kohane IS, Cai T, Avillach P. International Analysis of Electronic Health Records of Children and Youth Hospitalized With COVID-19 Infection in 6 Countries. JAMA Netw Open 2021; 4:e2112596. [PMID: 34115127 PMCID: PMC8196345 DOI: 10.1001/jamanetworkopen.2021.12596] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/20/2022] Open
Abstract
IMPORTANCE Additional sources of pediatric epidemiological and clinical data are needed to efficiently study COVID-19 in children and youth and inform infection prevention and clinical treatment of pediatric patients. OBJECTIVE To describe international hospitalization trends and key epidemiological and clinical features of children and youth with COVID-19. DESIGN, SETTING, AND PARTICIPANTS This retrospective cohort study included pediatric patients hospitalized between February 2 and October 10, 2020. Patient-level electronic health record (EHR) data were collected across 27 hospitals in France, Germany, Spain, Singapore, the UK, and the US. Patients younger than 21 years who tested positive for COVID-19 and were hospitalized at an institution participating in the Consortium for Clinical Characterization of COVID-19 by EHR were included in the study. MAIN OUTCOMES AND MEASURES Patient characteristics, clinical features, and medication use. RESULTS There were 347 males (52%; 95% CI, 48.5-55.3) and 324 females (48%; 95% CI, 44.4-51.3) in this study's cohort. There was a bimodal age distribution, with the greatest proportion of patients in the 0- to 2-year (199 patients [30%]) and 12- to 17-year (170 patients [25%]) age range. Trends in hospitalizations for 671 children and youth found discrete surges with variable timing across 6 countries. Data from this cohort mirrored national-level pediatric hospitalization trends for most countries with available data, with peaks in hospitalizations during the initial spring surge occurring within 23 days in the national-level and 4CE data. A total of 27 364 laboratory values for 16 laboratory tests were analyzed, with mean values indicating elevations in markers of inflammation (C-reactive protein, 83 mg/L; 95% CI, 53-112 mg/L; ferritin, 417 ng/mL; 95% CI, 228-607 ng/mL; and procalcitonin, 1.45 ng/mL; 95% CI, 0.13-2.77 ng/mL). Abnormalities in coagulation were also evident (D-dimer, 0.78 ug/mL; 95% CI, 0.35-1.21 ug/mL; and fibrinogen, 477 mg/dL; 95% CI, 385-569 mg/dL). Cardiac troponin, when checked (n = 59), was elevated (0.032 ng/mL; 95% CI, 0.000-0.080 ng/mL). Common complications included cardiac arrhythmias (15.0%; 95% CI, 8.1%-21.7%), viral pneumonia (13.3%; 95% CI, 6.5%-20.1%), and respiratory failure (10.5%; 95% CI, 5.8%-15.3%). Few children were treated with COVID-19-directed medications. CONCLUSIONS AND RELEVANCE This study of EHRs of children and youth hospitalized for COVID-19 in 6 countries demonstrated variability in hospitalization trends across countries and identified common complications and laboratory abnormalities in children and youth with COVID-19 infection. Large-scale informatics-based approaches to integrate and analyze data across health care systems complement methods of disease surveillance and advance understanding of epidemiological and clinical features associated with COVID-19 in children and youth.
Collapse
Affiliation(s)
- Florence T. Bourgeois
- Department of Pediatrics, Harvard Medical School, Boston, Massachusetts
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, Massachusetts
| | | | - Mark S. Keller
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts
| | - Molei Liu
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, Massachusetts
| | - Chuan Hong
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts
| | - Clara-Lea Bonzel
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts
| | - Amelia L. M. Tan
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts
| | - Bruce J. Aronow
- Departments of Biomedical Informatics, Pediatrics, Cincinnati Children's Hospital Medical Center, University of Cincinnati, Ohio
| | - Martin Boeker
- Institute of Medical Biometry and Statistics, Faculty of Medicine and Medical Center, University of Freiburg, Germany
| | - John Booth
- Digital Research, Informatics and Virtual Environments (DRIVE), Great Ormond Street Hospital for Children, London, United Kingdom
| | - Jaime Cruz Rojo
- Department of Health Informatics, Hospital Universitario 12 de Octubre, Madrid, Spain
| | - Batsal Devkota
- Department of Biomedical Health Informatics and the Department of Pediatrics, The Children's Hospital of Philadelphia, Philadelphia, Pennsylvania
| | - Noelia García Barrio
- Department of Health Informatics, Hospital Universitario 12 de Octubre, Madrid, Spain
| | - Nils Gehlenborg
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts
| | - Alon Geva
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, Massachusetts
- Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children’s Hospital, Boston, Massachusetts
| | - David A. Hanauer
- Department of Learning Health Sciences, University of Michigan, Ann Arbor
| | - Meghan R. Hutch
- Department of Preventive Medicine, Northwestern University, Evanston, Illinois
| | - Richard W. Issitt
- Digital Research, Informatics and Virtual Environments (DRIVE), Great Ormond Street Hospital for Children, London, United Kingdom
| | | | - Yuan Luo
- Department of Preventive Medicine, Northwestern University, Evanston, Illinois
| | - Kenneth D. Mandl
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, Massachusetts
| | - Chengsheng Mao
- Department of Preventive Medicine, Northwestern University, Evanston, Illinois
| | - Bertrand Moal
- IAM Unit, Bordeaux University Hospital, Bordeaux, France
| | - Karyn L. Moshal
- Department of Infectious Diseases, Great Ormond Street Hospital for Children, London, United Kingdom
| | - Shawn N. Murphy
- Department of Neurology, Massachusetts General Hospital, Boston, Massachusetts
| | - Antoine Neuraz
- Department of Biomedical Informatics, Hôpital Necker-Enfants Malade, Assistance Publique Hôpitaux de Paris, University of Paris, Paris, France
| | - Kee Yuan Ngiam
- Department of Biomedical informatics, WiSDM, National University Health Systems Singapore, Singapore
| | - Gilbert S Omenn
- Department of Computational Medicine & Bioinformatics, Internal Medicine, Human Genetics, & School of Public Health, University of Michigan, Ann Arbor
| | - Lav P. Patel
- Department of Internal Medicine, Division of Medical Informatics, University of Kansas Medical Center, Kansas City
| | | | - Neil J. Sebire
- Digital Research, Informatics and Virtual Environments (DRIVE), Great Ormond Street Hospital for Children, London, United Kingdom
| | | | | | - Andrew M. South
- Department of Pediatrics-Section of Nephrology, Brenner Children's Hospital, Wake Forest School of Medicine, Winston Salem, North Carolina
| | - Anastasia Spiridou
- Digital Research, Informatics and Virtual Environments (DRIVE), Great Ormond Street Hospital for Children, London, United Kingdom
| | - Deanne M. Taylor
- Department of Biomedical Health Informatics and the Department of Pediatrics, The Children's Hospital of Philadelphia, Philadelphia, Pennsylvania
- Department of Pediatrics, Perelman Medical School at the University of Pennsylvania, Philadelphia
| | - Patric Tippmann
- Institute of Medical Biometry and Statistics, Faculty of Medicine and Medical Center, University of Freiburg, Germany
| | - Shyam Visweswaran
- Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, Pennsylvania
| | - Griffin M. Weber
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts
| | - Isaac S. Kohane
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts
| | - Tianxi Cai
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts
| | - Paul Avillach
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, Massachusetts
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts
| |
Collapse
|
25
|
Geva A, Abman SH, Manzi SF, Ivy DD, Mullen MP, Griffin J, Lin C, Savova GK, Mandl KD. Adverse drug event rates in pediatric pulmonary hypertension: a comparison of real-world data sources. J Am Med Inform Assoc 2021; 27:294-300. [PMID: 31769835 PMCID: PMC7025334 DOI: 10.1093/jamia/ocz194] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2019] [Revised: 10/08/2019] [Accepted: 10/21/2019] [Indexed: 11/14/2022] Open
Abstract
Objective Real-world data (RWD) are increasingly used for pharmacoepidemiology and regulatory innovation. Our objective was to compare adverse drug event (ADE) rates determined from two RWD sources, electronic health records and administrative claims data, among children treated with drugs for pulmonary hypertension. Materials and Methods Textual mentions of medications and signs/symptoms that may represent ADEs were identified in clinical notes using natural language processing. Diagnostic codes for the same signs/symptoms were identified in our electronic data warehouse for the patients with textual evidence of taking pulmonary hypertension-targeted drugs. We compared rates of ADEs identified in clinical notes to those identified from diagnostic code data. In addition, we compared putative ADE rates from clinical notes to those from a healthcare claims dataset from a large, national insurer. Results Analysis of clinical notes identified up to 7-fold higher ADE rates than those ascertained from diagnostic codes. However, certain ADEs (eg, hearing loss) were more often identified in diagnostic code data. Similar results were found when ADE rates ascertained from clinical notes and national claims data were compared. Discussion While administrative claims and clinical notes are both increasingly used for RWD-based pharmacovigilance, ADE rates substantially differ depending on data source. Conclusion Pharmacovigilance based on RWD may lead to discrepant results depending on the data source analyzed. Further work is needed to confirm the validity of identified ADEs, to distinguish them from disease effects, and to understand tradeoffs in sensitivity and specificity between data sources.
Collapse
Affiliation(s)
- Alon Geva
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA.,Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, Massachusetts, USA.,Department of Anaesthesia, Harvard Medical School, Boston, Massachusetts, USA
| | - Steven H Abman
- Division of Pediatric Pulmonary Medicine, Children's Hospital Colorado, Aurora, Colorado, USA.,Department of Pediatrics, University of Colorado School of Medicine, Aurora, Colorado, USA
| | - Shannon F Manzi
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA.,Division of Genetics & Genomics, Clinical Pharmacogenomics Service, Department of Pharmacy, Boston Children's Hospital, Boston, Massachusetts, USA.,Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA
| | - Dunbar D Ivy
- Department of Pediatrics, University of Colorado School of Medicine, Aurora, Colorado, USA.,Division of Cardiology, Heart Institute, Children's Hospital Colorado, Aurora, Colorado, USA
| | - Mary P Mullen
- Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA.,Department of Cardiology, Boston Children's Hospital, Boston, Massachusetts, USA
| | - John Griffin
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, Massachusetts, USA
| | - Chen Lin
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA
| | - Guergana K Savova
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA.,Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA
| | - Kenneth D Mandl
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA.,Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA.,Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|
26
|
Castiñeira D, Schlosser KR, Geva A, Rahmani AR, Fiore G, Walsh BK, Smallwood CD, Arnold JH, Santillana M. Adding Continuous Vital Sign Information to Static Clinical Data Improves the Prediction of Length of Stay After Intubation: A Data-Driven Machine Learning Approach. Respir Care 2021; 65:1367-1377. [PMID: 32879034 DOI: 10.4187/respcare.07561] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022]
Abstract
BACKGROUND Bedside monitors in the ICU routinely measure and collect patients' physiologic data in real time to continuously assess the health status of patients who are critically ill. With the advent of increased computational power and the ability to store and rapidly process big data sets in recent years, these physiologic data show promise in identifying specific outcomes and/or events during patients' ICU hospitalization. METHODS We introduced a methodology designed to automatically extract information from continuous-in-time vital sign data collected from bedside monitors to predict if a patient will experience a prolonged stay (length of stay) on mechanical ventilation, defined as >4 d, in a pediatric ICU. RESULTS Continuous-in-time vital signs information and clinical history data were retrospectively collected for 284 ICU subjects from their first 24 h on mechanical ventilation from a medical-surgical pediatric ICU at Boston Children's Hospital. Multiple machine learning models were trained on multiple subsets of these subjects to predict the likelihood that each of these subjects would experience a long stay. We evaluated the predictive power of our models strictly on unseen hold-out validation sets of subjects. Our methodology achieved model performance of >83% (area under the curve) by using only vital sign information as input, and performances of 90% (area under the curve) by combining vital sign information with subjects' static clinical data readily available in electronic health records. We implemented this approach on 300 independently trained experiments with different choices of training and hold-out validation sets to ensure the consistency and robustness of our results in our study sample. The predictive power of our approach outperformed recent efforts that used deep learning to predict a similar task. CONCLUSIONS Our proposed workflow may prove useful in the design of scalable approaches for real-time predictive systems in ICU environments, exploiting real-time vital sign information from bedside monitors. (ClinicalTrials.gov registration NCT02184208.).
Collapse
Affiliation(s)
- David Castiñeira
- Massachusetts Institute of Technology, Cambridge, Massachusetts. .,Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts
| | - Katherine R Schlosser
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, Massachusetts.,Department of Anaesthesia, Harvard Medical School, Boston, Massachusetts.,Department of Pediatrics, Division of Pediatric Critical Care, Columbia University Irving Medical Center, New York, New York
| | - Alon Geva
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts.,Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, Massachusetts.,Department of Anaesthesia, Harvard Medical School, Boston, Massachusetts
| | - Amir R Rahmani
- Data Science Institute, Columbia University at the time the research was conducted
| | - Gaston Fiore
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts
| | - Brian K Walsh
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, Massachusetts.,Department of Anaesthesia, Harvard Medical School, Boston, Massachusetts.,Department of Allied Health Professions, School of Health Sciences, Liberty University, Lynchburg, Virginia
| | - Craig D Smallwood
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, Massachusetts.,Department of Anaesthesia, Harvard Medical School, Boston, Massachusetts
| | - John H Arnold
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, Massachusetts.,Department of Anaesthesia, Harvard Medical School, Boston, Massachusetts
| | | |
Collapse
|
27
|
Geva A, Liu M, Panickan VA, Avillach P, Cai T, Mandl KD. A high-throughput phenotyping algorithm is portable from adult to pediatric populations. J Am Med Inform Assoc 2021; 28:1265-1269. [PMID: 33594412 DOI: 10.1093/jamia/ocaa343] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2020] [Revised: 11/27/2020] [Accepted: 12/28/2020] [Indexed: 11/14/2022] Open
Abstract
OBJECTIVE Multimodal automated phenotyping (MAP) is a scalable, high-throughput phenotyping method, developed using electronic health record (EHR) data from an adult population. We tested transportability of MAP to a pediatric population. MATERIALS AND METHODS Without additional feature engineering or supervised training, we applied MAP to a pediatric population enrolled in a biobank and evaluated performance against physician-reviewed medical records. We also compared performance of MAP at the pediatric institution and the original adult institution where MAP was developed, including for 6 phenotypes validated at both institutions against physician-reviewed medical records. RESULTS MAP performed equally well in the pediatric setting (average AUC 0.98) as it did at the general adult hospital system (average AUC 0.96). MAP's performance in the pediatric sample was similar across the 6 specific phenotypes also validated against gold-standard labels in the adult biobank. CONCLUSIONS MAP is highly transportable across diverse populations and has potential for wide-scale use.
Collapse
Affiliation(s)
- Alon Geva
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA.,Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, Massachusetts, USA.,Department of Anaesthesia, Harvard Medical School, Boston, Massachusetts, USA
| | - Molei Liu
- Department of Biostatistics, Harvard T. H. Chan School of Public Health, Boston, Massachusetts, USA
| | - Vidul A Panickan
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA
| | - Paul Avillach
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA.,Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA.,Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA
| | - Tianxi Cai
- Department of Biostatistics, Harvard T. H. Chan School of Public Health, Boston, Massachusetts, USA.,Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA
| | - Kenneth D Mandl
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA.,Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA.,Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|
28
|
Geva A, Stedman JP, Manzi SF, Lin C, Savova GK, Avillach P, Mandl KD. Adverse drug event presentation and tracking (ADEPT): semiautomated, high throughput pharmacovigilance using real-world data. JAMIA Open 2020; 3:413-421. [PMID: 33215076 PMCID: PMC7660953 DOI: 10.1093/jamiaopen/ooaa031] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2020] [Revised: 06/23/2020] [Accepted: 06/27/2020] [Indexed: 11/24/2022] Open
Abstract
Objective To advance use of real-world data (RWD) for pharmacovigilance, we sought to integrate a high-sensitivity natural language processing (NLP) pipeline for detecting potential adverse drug events (ADEs) with easily interpretable output for high-efficiency human review and adjudication of true ADEs. Materials and methods The adverse drug event presentation and tracking (ADEPT) system employs an open source NLP pipeline to identify in clinical notes mentions of medications and signs and symptoms potentially indicative of ADEs. ADEPT presents the output to human reviewers by highlighting these drug-event pairs within the context of the clinical note. To measure incidence of seizures associated with sildenafil, we applied ADEPT to 149 029 notes for 982 patients with pediatric pulmonary hypertension. Results Of 416 patients identified as taking sildenafil, NLP found 72 [17%, 95% confidence interval (CI) 14–21] with seizures as a potential ADE. Upon human review and adjudication, only 4 (0.96%, 95% CI 0.37–2.4) patients with seizures were determined to have true ADEs. Reviewers using ADEPT required a median of 89 s (interquartile range 57–142 s) per patient to review potential ADEs. Discussion ADEPT combines high throughput NLP to increase sensitivity of ADE detection and human review, to increase specificity by differentiating true ADEs from signs and symptoms related to comorbidities, effects of other medications, or other confounders. Conclusion ADEPT is a promising tool for creating gold standard, patient-level labels for advancing NLP-based pharmacovigilance. ADEPT is a potentially time savings platform for computer-assisted pharmacovigilance based on RWD.
Collapse
Affiliation(s)
- Alon Geva
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA.,Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, Massachusetts, USA.,Department of Anaesthesia, Harvard Medical School, Boston, Massachusetts, USA
| | - Jason P Stedman
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA
| | - Shannon F Manzi
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA.,Clinical Pharmacogenomics Service, Division of Genetics & Genomics and Department of Pharmacy, Boston Children's Hospital, Boston, Massachusetts, USA.,Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA
| | - Chen Lin
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA
| | - Guergana K Savova
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA.,Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA
| | - Paul Avillach
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA.,Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA
| | - Kenneth D Mandl
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA.,Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA.,Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|
29
|
Shani-Hershkovitz R, Avirame K, Alyagon U, Zangen A, Harel E, Levkovitz Y, Geva A, Peremen Z. P235 An EEG based tool to inform responsiveness to rTMS treatment for subjects with major depression. Clin Neurophysiol 2020. [DOI: 10.1016/j.clinph.2019.12.346] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/24/2022]
|
30
|
Schlosser KR, Fiore GA, Smallwood CD, Griffin JF, Geva A, Santillana M, Arnold JH. Noninvasive Ventilation Is Interrupted Frequently and Mostly Used at Night in the Pediatric Intensive Care Unit. Respir Care 2019; 65:341-346. [PMID: 31551282 DOI: 10.4187/respcare.06883] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022]
Abstract
BACKGROUND Noninvasive ventilation (NIV) is commonly used to support children with respiratory failure, but detailed patterns of real-world use are lacking. The aim of our study was to describe use patterns of NIV via electronic medical record (EMR) data. METHODS We performed a retrospective electronic chart review in a tertiary care pediatric ICU in the United States. Subjects admitted to the pediatric ICU from 2014 to 2017 who were mechanically ventilated were included in the study. RESULTS The median number of discrete device episodes, defined as a time on support without interruption, was 20 (interquartile range [IQR] 8-49) per subject. The median duration of bi-level positive airway pressure (BPAP) support prior to interruption was 6.3 h (IQR 2.4-10.4); the median duration of CPAP was 6 h (IQR 2.1-10.4). Interruptions to BPAP had a median duration of 6.3 h (IQR 2-15.5); interruptions to CPAP had a median duration of 8.6 h (IQR 2.2-16.8). Use of NIV followed a diurnal pattern, with 44% of BPAP and 42% of CPAP subjects initiating support between 7:00 pm and midnight, and 49% of BPAP and 46% of CPAP subjects stopping support between 5:00 am and 10:00 am. CONCLUSIONS NIV was frequently interrupted, and initiation and discontinuation of NIV follows a diurnal pattern. Use of EMR data collected for routine clinical care allowed the analysis of granular details of typical use patterns. Understanding NIV use patterns may be particularly important to understanding the burden of pediatric ICU bed utilization for nocturnal NIV. To our knowledge, this is the first study to examine in detail the use of pediatric NIV and to define diurnal use and frequent interruptions to support.
Collapse
Affiliation(s)
- Katherine R Schlosser
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, Massachusetts. .,Division of Pediatric Critical Care, Department of Pediatrics, Columbia University Irving Medical Center, New York
| | - Gaston A Fiore
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts
| | - Craig D Smallwood
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, Massachusetts
| | - John F Griffin
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, Massachusetts
| | - Alon Geva
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, Massachusetts.,Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts
| | - Mauricio Santillana
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts
| | - John H Arnold
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, Massachusetts
| |
Collapse
|
31
|
Ning W, Chan S, Beam A, Yu M, Geva A, Liao K, Mullen M, Mandl KD, Kohane I, Cai T, Yu S. Feature extraction for phenotyping from semantic and knowledge resources. J Biomed Inform 2019; 91:103122. [PMID: 30738949 PMCID: PMC6424621 DOI: 10.1016/j.jbi.2019.103122] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/10/2023]
Abstract
OBJECTIVE Phenotyping algorithms can efficiently and accurately identify patients with a specific disease phenotype and construct electronic health records (EHR)-based cohorts for subsequent clinical or genomic studies. Previous studies have introduced unsupervised EHR-based feature selection methods that yielded algorithms with high accuracy. However, those selection methods still require expert intervention to tweak the parameter settings according to the EHR data distribution for each phenotype. To further accelerate the development of phenotyping algorithms, we propose a fully automated and robust unsupervised feature selection method that leverages only publicly available medical knowledge sources, instead of EHR data. METHODS SEmantics-Driven Feature Extraction (SEDFE) collects medical concepts from online knowledge sources as candidate features and gives them vector-form distributional semantic representations derived with neural word embedding and the Unified Medical Language System Metathesaurus. A number of features that are semantically closest and that sufficiently characterize the target phenotype are determined by a linear decomposition criterion and are selected for the final classification algorithm. RESULTS SEDFE was compared with the EHR-based SAFE algorithm and domain experts on feature selection for the classification of five phenotypes including coronary artery disease, rheumatoid arthritis, Crohn's disease, ulcerative colitis, and pediatric pulmonary arterial hypertension using both supervised and unsupervised approaches. Algorithms yielded by SEDFE achieved comparable accuracy to those yielded by SAFE and expert-curated features. SEDFE is also robust to the input semantic vectors. CONCLUSION SEDFE attains satisfying performance in unsupervised feature selection for EHR phenotyping. Both fully automated and EHR-independent, this method promises efficiency and accuracy in developing algorithms for high-throughput phenotyping.
Collapse
Affiliation(s)
- Wenxin Ning
- Department of Industrial Engineering, Tsinghua University, Beijing, China
| | - Stephanie Chan
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA
| | - Andrew Beam
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
| | - Ming Yu
- Department of Industrial Engineering, Tsinghua University, Beijing, China
| | - Alon Geva
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, USA; Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, MA, USA; Department of Anesthesia, Harvard Medical School, Boston, MA, USA
| | - Katherine Liao
- Department of Medicine, Division of Rheumatology, Immunology and Allergy, Brigham and Women's Hospital, Boston, MA, USA; Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
| | - Mary Mullen
- Department of Cardiology, Boston Children's Hospital, Boston, MA, USA; Department of Pediatrics, Harvard Medical School, Boston, MA, USA
| | - Kenneth D Mandl
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, USA; Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
| | - Isaac Kohane
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
| | - Tianxi Cai
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA; Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
| | - Sheng Yu
- Center for Statistical Science, Tsinghua University, Beijing, China; Department of Industrial Engineering, Tsinghua University, Beijing, China; Institute for Data Science, Tsinghua University, Beijing, China.
| |
Collapse
|
32
|
Reches A, Or-ly H, Weiss M, Stern Y, Baumeister J, Foss K, Ellis J, Laish B, Laufer O, Sadeh B, Ettinger M, Arthur T, Shaham G, Myer G, Kehat O, Shani-Hershkovich R, Peremen Z, Geva A. P 136 Brain network analysis of EEG data in the service of clinical assessment – utilizing big data and prior theoretical knowledge to identify a biomarker for mTBI in adolscents. Clin Neurophysiol 2017. [DOI: 10.1016/j.clinph.2017.06.209] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
33
|
Geva A, Gronsbell JL, Cai T, Cai T, Murphy SN, Lyons JC, Heinz MM, Natter MD, Patibandla N, Bickel J, Mullen MP, Mandl KD. A Computable Phenotype Improves Cohort Ascertainment in a Pediatric Pulmonary Hypertension Registry. J Pediatr 2017; 188. [PMID: 28625502 PMCID: PMC5572538 DOI: 10.1016/j.jpeds.2017.05.037] [Citation(s) in RCA: 23] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/28/2023]
Abstract
OBJECTIVES To compare registry and electronic health record (EHR) data mining approaches for cohort ascertainment in patients with pediatric pulmonary hypertension (PH) in an effort to overcome some of the limitations of registry enrollment alone in identifying patients with particular disease phenotypes. STUDY DESIGN This study was a single-center retrospective analysis of EHR and registry data at Boston Children's Hospital. The local Informatics for Integrating Biology and the Bedside (i2b2) data warehouse was queried for billing codes, prescriptions, and narrative data related to pediatric PH. Computable phenotype algorithms were developed by fitting penalized logistic regression models to a physician-annotated training set. Algorithms were applied to a candidate patient cohort, and performance was evaluated using a separate set of 136 records and 179 registry patients. We compared clinical and demographic characteristics of patients identified by computable phenotype and the registry. RESULTS The computable phenotype had an area under the receiver operating characteristics curve of 90% (95% CI, 85%-95%), a positive predictive value of 85% (95% CI, 77%-93%), and identified 413 patients (an additional 231%) with pediatric PH who were not enrolled in the registry. Patients identified by the computable phenotype were clinically distinct from registry patients, with a greater prevalence of diagnoses related to perinatal distress and left heart disease. CONCLUSIONS Mining of EHRs using computable phenotypes identified a large cohort of patients not recruited using a classic registry. Fusion of EHR and registry data can improve cohort ascertainment for the study of rare diseases. TRIAL REGISTRATION ClinicalTrials.gov: NCT02249923.
Collapse
Affiliation(s)
- Alon Geva
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, MA,Division of Critical Care Medicine, Department of Anesthesiology, Perioperative, and Pain Medicine, Boston Children’s Hospital, Boston, MA,Department of Anaesthesia, Harvard Medical School, Boston, MA
| | - Jessica L. Gronsbell
- Department of Biostatistics, Harvard T. H. Chan School of Public Health, Boston, MA
| | - Tianxi Cai
- Department of Biostatistics, Harvard T. H. Chan School of Public Health, Boston, MA
| | - Tianrun Cai
- Division of Rheumatology, Immunology and Allergy, Brigham and Women’s Hospital, Boston, MA
| | - Shawn N. Murphy
- Department of Research Information Services and Computing, Partners Healthcare, Boston, MA,Department of Neurology, Massachusetts General Hospital, Boston, MA,Department of Biomedical Informatics, Harvard Medical School, Boston, MA
| | - Jessica C. Lyons
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA
| | - Michelle M. Heinz
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, MA
| | - Marc D. Natter
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, MA,Department of Pediatrics, Harvard Medical School, Boston, MA
| | - Nandan Patibandla
- Information Services Department, Boston Children’s Hospital, Boston, MA
| | - Jonathan Bickel
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, MA,Information Services Department, Boston Children’s Hospital, Boston, MA,Department of Pediatrics, Harvard Medical School, Boston, MA
| | - Mary P. Mullen
- Department of Cardiology, Boston Children’s Hospital, Boston, MA,Department of Pediatrics, Harvard Medical School, Boston, MA
| | - Kenneth D. Mandl
- Computational Health Informatics Program, Boston Children’s Hospital, Boston, MA,Department of Biomedical Informatics, Harvard Medical School, Boston, MA,Department of Pediatrics, Harvard Medical School, Boston, MA
| | | |
Collapse
|
34
|
Ong MS, Mullen MP, Austin ED, Szolovits P, Natter MD, Geva A, Cai T, Kong SW, Mandl KD. Learning a Comorbidity-Driven Taxonomy of Pediatric Pulmonary Hypertension. Circ Res 2017; 121:341-353. [PMID: 28611076 PMCID: PMC5559726 DOI: 10.1161/circresaha.117.310804] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/02/2017] [Revised: 06/07/2017] [Accepted: 06/12/2017] [Indexed: 11/16/2022]
Abstract
RATIONALE Pediatric pulmonary hypertension (PH) is a heterogeneous condition with varying natural history and therapeutic response. Precise classification of PH subtypes is, therefore, crucial for individualizing care. However, gaps remain in our understanding of the spectrum of PH in children. OBJECTIVE We seek to study the manifestations of PH in children and to assess the feasibility of applying a network-based approach to discern disease subtypes from comorbidity data recorded in longitudinal data sets. METHODS AND RESULTS A retrospective cohort study comprising 6 943 263 children (<18 years of age) enrolled in a commercial health insurance plan in the United States, between January 2010 and May 2013. A total of 1583 (0.02%) children met the criteria for PH. We identified comorbidities significantly associated with PH compared with the general population of children without PH. A Bayesian comorbidity network was constructed to model the interdependencies of these comorbidities, and network-clustering analysis was applied to derive disease subtypes comprising subgraphs of highly connected comorbid conditions. A total of 186 comorbidities were found to be significantly associated with PH. Network analysis of comorbidity patterns captured most of the major PH subtypes with known pathological basis defined by the World Health Organization and Panama classifications. The analysis further identified many subtypes documented in only a few case studies, including rare subtypes associated with several well-described genetic syndromes. CONCLUSIONS Application of network science to model comorbidity patterns recorded in longitudinal data sets can facilitate the discovery of disease subtypes. Our analysis relearned established subtypes, thus validating the approach, and identified rare subtypes that are difficult to discern through clinical observations, providing impetus for deeper investigation of the disease subtypes that will enrich current disease classifications.
Collapse
Affiliation(s)
- Mei-Sing Ong
- From the Computational Health Informatics Program (M.-S.O., M.D.N., A.G., S.W.K., K.D.M.), Department of Cardiology (M.P.M.), Division of Critical Care Medicine, Department of Anesthesiology, Perioperative, and Pain Medicine (A.G.), and Department of Anesthesia (A.G.), Harvard School of Medicine, Boston Children's Hospital, MA; Department of Pediatrics, Vanderbilt University Medical Center, Nashville, TN (E.D.A.); Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge (P.S.); Department of Pediatrics, Massachusetts General Hospital, Boston (M.D.N.); and Department of Biostatistics, Harvard School of Public Health, Boston, MA. (T.C.).
| | - Mary P Mullen
- From the Computational Health Informatics Program (M.-S.O., M.D.N., A.G., S.W.K., K.D.M.), Department of Cardiology (M.P.M.), Division of Critical Care Medicine, Department of Anesthesiology, Perioperative, and Pain Medicine (A.G.), and Department of Anesthesia (A.G.), Harvard School of Medicine, Boston Children's Hospital, MA; Department of Pediatrics, Vanderbilt University Medical Center, Nashville, TN (E.D.A.); Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge (P.S.); Department of Pediatrics, Massachusetts General Hospital, Boston (M.D.N.); and Department of Biostatistics, Harvard School of Public Health, Boston, MA. (T.C.)
| | - Eric D Austin
- From the Computational Health Informatics Program (M.-S.O., M.D.N., A.G., S.W.K., K.D.M.), Department of Cardiology (M.P.M.), Division of Critical Care Medicine, Department of Anesthesiology, Perioperative, and Pain Medicine (A.G.), and Department of Anesthesia (A.G.), Harvard School of Medicine, Boston Children's Hospital, MA; Department of Pediatrics, Vanderbilt University Medical Center, Nashville, TN (E.D.A.); Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge (P.S.); Department of Pediatrics, Massachusetts General Hospital, Boston (M.D.N.); and Department of Biostatistics, Harvard School of Public Health, Boston, MA. (T.C.)
| | - Peter Szolovits
- From the Computational Health Informatics Program (M.-S.O., M.D.N., A.G., S.W.K., K.D.M.), Department of Cardiology (M.P.M.), Division of Critical Care Medicine, Department of Anesthesiology, Perioperative, and Pain Medicine (A.G.), and Department of Anesthesia (A.G.), Harvard School of Medicine, Boston Children's Hospital, MA; Department of Pediatrics, Vanderbilt University Medical Center, Nashville, TN (E.D.A.); Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge (P.S.); Department of Pediatrics, Massachusetts General Hospital, Boston (M.D.N.); and Department of Biostatistics, Harvard School of Public Health, Boston, MA. (T.C.)
| | - Marc D Natter
- From the Computational Health Informatics Program (M.-S.O., M.D.N., A.G., S.W.K., K.D.M.), Department of Cardiology (M.P.M.), Division of Critical Care Medicine, Department of Anesthesiology, Perioperative, and Pain Medicine (A.G.), and Department of Anesthesia (A.G.), Harvard School of Medicine, Boston Children's Hospital, MA; Department of Pediatrics, Vanderbilt University Medical Center, Nashville, TN (E.D.A.); Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge (P.S.); Department of Pediatrics, Massachusetts General Hospital, Boston (M.D.N.); and Department of Biostatistics, Harvard School of Public Health, Boston, MA. (T.C.)
| | - Alon Geva
- From the Computational Health Informatics Program (M.-S.O., M.D.N., A.G., S.W.K., K.D.M.), Department of Cardiology (M.P.M.), Division of Critical Care Medicine, Department of Anesthesiology, Perioperative, and Pain Medicine (A.G.), and Department of Anesthesia (A.G.), Harvard School of Medicine, Boston Children's Hospital, MA; Department of Pediatrics, Vanderbilt University Medical Center, Nashville, TN (E.D.A.); Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge (P.S.); Department of Pediatrics, Massachusetts General Hospital, Boston (M.D.N.); and Department of Biostatistics, Harvard School of Public Health, Boston, MA. (T.C.)
| | - Tianxi Cai
- From the Computational Health Informatics Program (M.-S.O., M.D.N., A.G., S.W.K., K.D.M.), Department of Cardiology (M.P.M.), Division of Critical Care Medicine, Department of Anesthesiology, Perioperative, and Pain Medicine (A.G.), and Department of Anesthesia (A.G.), Harvard School of Medicine, Boston Children's Hospital, MA; Department of Pediatrics, Vanderbilt University Medical Center, Nashville, TN (E.D.A.); Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge (P.S.); Department of Pediatrics, Massachusetts General Hospital, Boston (M.D.N.); and Department of Biostatistics, Harvard School of Public Health, Boston, MA. (T.C.)
| | - Sek Won Kong
- From the Computational Health Informatics Program (M.-S.O., M.D.N., A.G., S.W.K., K.D.M.), Department of Cardiology (M.P.M.), Division of Critical Care Medicine, Department of Anesthesiology, Perioperative, and Pain Medicine (A.G.), and Department of Anesthesia (A.G.), Harvard School of Medicine, Boston Children's Hospital, MA; Department of Pediatrics, Vanderbilt University Medical Center, Nashville, TN (E.D.A.); Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge (P.S.); Department of Pediatrics, Massachusetts General Hospital, Boston (M.D.N.); and Department of Biostatistics, Harvard School of Public Health, Boston, MA. (T.C.)
| | - Kenneth D Mandl
- From the Computational Health Informatics Program (M.-S.O., M.D.N., A.G., S.W.K., K.D.M.), Department of Cardiology (M.P.M.), Division of Critical Care Medicine, Department of Anesthesiology, Perioperative, and Pain Medicine (A.G.), and Department of Anesthesia (A.G.), Harvard School of Medicine, Boston Children's Hospital, MA; Department of Pediatrics, Vanderbilt University Medical Center, Nashville, TN (E.D.A.); Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge (P.S.); Department of Pediatrics, Massachusetts General Hospital, Boston (M.D.N.); and Department of Biostatistics, Harvard School of Public Health, Boston, MA. (T.C.)
| |
Collapse
|
35
|
Geva A, Olson KL, Liu C, Mandl KD. Provider Connectedness to Other Providers Reduces Risk of Readmission After Hospitalization for Heart Failure. Med Care Res Rev 2017; 76:115-128. [PMID: 29148301 DOI: 10.1177/1077558717718626] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/14/2023]
Abstract
Provider interactions other than explicit care coordination, which is challenging to measure, may influence practice and outcomes. We performed a network analysis using claims data from a commercial payor. Networks were identified based on provider pairs billing outpatient care for the same patient. We compared network variables among patients who had and did not have a 30-day readmission after hospitalization for heart failure. After adjusting for comorbidities, high median provider connectedness-normalized degree, which for each provider is the number of connections to other providers normalized to the number of providers in the region-was the network variable associated with reduced odds of readmission after heart failure hospitalization (odds ratio = 0.55; 95% confidence interval [0.35, 0.86]). We conclude that heart failure patients with high provider connectedness are less likely to require readmission. The structure and importance of provider relationships using claims data merits further study.
Collapse
Affiliation(s)
- Alon Geva
- 1 Boston Children's Hospital, Boston, MA, USA.,2 Harvard Medical School, Boston, MA, USA
| | - Karen L Olson
- 1 Boston Children's Hospital, Boston, MA, USA.,2 Harvard Medical School, Boston, MA, USA
| | | | - Kenneth D Mandl
- 1 Boston Children's Hospital, Boston, MA, USA.,2 Harvard Medical School, Boston, MA, USA
| |
Collapse
|
36
|
Biederman J, Hammerness P, Sadeh B, Peremen Z, Amit A, Or-Ly H, Stern Y, Reches A, Geva A, Faraone SV. Diagnostic utility of brain activity flow patterns analysis in attention deficit hyperactivity disorder. Psychol Med 2017; 47:1259-1270. [PMID: 28065167 DOI: 10.1017/s0033291716003329] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/01/2023]
Abstract
BACKGROUND A previous small study suggested that Brain Network Activation (BNA), a novel ERP-based brain network analysis, may have diagnostic utility in attention deficit hyperactivity disorder (ADHD). In this study we examined the diagnostic capability of a new advanced version of the BNA methodology on a larger population of adults with and without ADHD. METHOD Subjects were unmedicated right-handed 18- to 55-year-old adults of both sexes with and without a DSM-IV diagnosis of ADHD. We collected EEG while the subjects were performing a response inhibition task (Go/NoGo) and then applied a spatio-temporal Brain Network Activation (BNA) analysis of the EEG data. This analysis produced a display of qualitative measures of brain states (BNA scores) providing information on cortical connectivity. This complex set of scores was then fed into a machine learning algorithm. RESULTS The BNA analysis of the EEG data recorded during the Go/NoGo task demonstrated a high discriminative capacity between ADHD patients and controls (AUC = 0.92, specificity = 0.95, sensitivity = 0.86 for the Go condition; AUC = 0.84, specificity = 0.91, sensitivity = 0.76 for the NoGo condition). CONCLUSIONS BNA methodology can help differentiate between ADHD and healthy controls based on functional brain connectivity. The data support the utility of the tool to augment clinical examinations by objective evaluation of electrophysiological changes associated with ADHD. Results also support a network-based approach to the study of ADHD.
Collapse
Affiliation(s)
- J Biederman
- Massachusettes General Hospital,Boston,MA,USA
| | | | | | | | - A Amit
- ElMindA Ltd,Herzliya,Israel
| | | | | | | | - A Geva
- ElMindA Ltd,Herzliya,Israel
| | - S V Faraone
- SUNY Upstate Medical University,Syracuse,NY,USA
| |
Collapse
|
37
|
Sand D, Peremen Z, Haor D, Arkadir D, Bergman H, Geva A. Optimization of deep brain stimulation in STN among patients with Parkinson's disease using a novel EEG-based tool. Brain Stimul 2017. [DOI: 10.1016/j.brs.2017.01.490] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022] Open
|
38
|
Reches A, Kutcher J, Elbin RJ, Or-Ly H, Sadeh B, Greer J, McAllister DJ, Geva A, Kontos AP. Preliminary investigation of Brain Network Activation (BNA) and its clinical utility in sport-related concussion. Brain Inj 2017; 31:237-246. [PMID: 28055228 PMCID: PMC5351793 DOI: 10.1080/02699052.2016.1231343] [Citation(s) in RCA: 17] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
Background: The clinical diagnosis and management of patients with sport-related concussion is largely dependent on subjectively reported symptoms, clinical examinations, cognitive, balance, vestibular and oculomotor testing. Consequently, there is an unmet need for objective assessment tools that can identify the injury from a physiological perspective and add an important layer of information to the clinician’s decision-making process. Objective: The goal of the study was to evaluate the clinical utility of the EEG-based tool named Brain Network Activation (BNA) as a longitudinal assessment method of brain function in the management of young athletes with concussion. Methods: Athletes with concussion (n = 86) and age-matched controls (n = 81) were evaluated at four time points with symptom questionnaires and BNA. BNA scores were calculated by comparing functional networks to a previously defined normative reference brain network model to the same cognitive task. Results: Subjects above 16 years of age exhibited a significant decrease in BNA scores immediately following injury, as well as notable changes in functional network activity, relative to the controls. Three representative case studies of the tested population are discussed in detail, to demonstrate the clinical utility of BNA. Conclusion: The data support the utility of BNA to augment clinical examinations, symptoms and additional tests by providing an effective method for evaluating objective electrophysiological changes associated with sport-related concussions.
Collapse
Affiliation(s)
- A Reches
- a ElMindA Ltd , Herzliya , Israel
| | - J Kutcher
- b The Sports Neurology Clinic , University of Michigan , Ann Arbor , MI , USA
| | - R J Elbin
- c Department of Health, Human Performance and Recreation , University of Arkansas , Fayetteville , AR , USA
| | - H Or-Ly
- a ElMindA Ltd , Herzliya , Israel
| | - B Sadeh
- a ElMindA Ltd , Herzliya , Israel
| | - J Greer
- b The Sports Neurology Clinic , University of Michigan , Ann Arbor , MI , USA
| | - D J McAllister
- d UPMC Sports Medicine Concussion Program, Department of Orthopaedic Surgery , University of Pittsburgh , Pittsburgh , PA , USA
| | - A Geva
- a ElMindA Ltd , Herzliya , Israel
| | - A P Kontos
- d UPMC Sports Medicine Concussion Program, Department of Orthopaedic Surgery , University of Pittsburgh , Pittsburgh , PA , USA
| |
Collapse
|
39
|
Pickard SS, Geva A, Gauvreau K, del Nido PJ, Geva T. Long-term outcomes and risk factors for aortic regurgitation after discrete subvalvular aortic stenosis resection in children. Heart 2015; 101:1547-53. [PMID: 26238147 DOI: 10.1136/heartjnl-2015-307460] [Citation(s) in RCA: 22] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/08/2015] [Accepted: 06/18/2015] [Indexed: 11/04/2022] Open
Abstract
OBJECTIVES To characterise long-term outcomes after discrete subaortic stenosis (DSS) resection and to identify risk factors for reoperation and aortic regurgitation (AR) requiring repair or replacement. METHODS All patients who underwent DSS resection between 1984 and 2009 at our institution with at least 36 months' follow-up were included. Demographic, surgical and echocardiographic data were reviewed. Outcomes were reoperation for recurrent DSS, surgery for AR, death and morbidities, including heart transplant, endocarditis and complete heart block. RESULTS Median length of postoperative follow-up was 10.9 years (3-27.2 years). Reoperation occurred in 32 patients (21%) and plateaued 10 years after initial resection. Survival at 10 years and 20 years was 98.6% and 86.3%, respectively. Aortic valve (AoV) repair or replacement for predominant AR occurred in 31 patients (20%) during or after DSS resection. By multivariable analysis, prior aortic stenosis (AS) intervention (HR 22.4, p<0.001) was strongly associated with AoV repair or replacement. Risk factors for reoperation by multivariable analysis included younger age at resection (HR 1.24, p=0.003), preoperative gradient ≥60 mm Hg (HR 2.23, p=0.04), peeling of membrane off AoV or mitral valve (HR 2.52, p=0.01), distance of membrane to AoV <7.0 mm (HR 4.03, p=0.03) and AS (HR 2.58, p=0.01). CONCLUSIONS In this cohort, the incidence of reoperations after initial DSS resection plateaued after 10 years. Despite a significant rate of reoperation, overall survival was good. Concomitant congenital AS and its associated interventions significantly increased the risk of AR requiring surgical intervention.
Collapse
Affiliation(s)
- Sarah S Pickard
- Departments of Cardiology, Boston Children's Hospital, Boston, Massachusetts, USA Departments of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA
| | - Alon Geva
- Critical Care Medicine, Boston Children's Hospital, Boston, Massachusetts, USA Department of Anesthesia, Harvard Medical School, Boston, Massachusetts, USA
| | - Kimberlee Gauvreau
- Departments of Cardiology, Boston Children's Hospital, Boston, Massachusetts, USA Departments of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA
| | - Pedro J del Nido
- Cardiovascular Surgery, Boston Children's Hospital, Boston, Massachusetts, USA Department of Surgery, Harvard Medical School, Boston, Massachusetts, USA
| | - Tal Geva
- Departments of Cardiology, Boston Children's Hospital, Boston, Massachusetts, USA Departments of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|
40
|
Geva A, Wright SB, Baldini LM, Smallcomb JA, Safran C, Gray JE. Spread of methicillin-resistant Staphylococcus aureus in a large tertiary NICU: network analysis. Pediatrics 2011; 128:e1173-80. [PMID: 22007011 PMCID: PMC3208963 DOI: 10.1542/peds.2010-2562] [Citation(s) in RCA: 36] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/24/2022] Open
Abstract
OBJECTIVE Methicillin-resistant Staphylococcus aureus (MRSA) colonization in NICUs increases the risk of nosocomial infection. Network analysis provides tools to examine the interactions among patients and staff members that put patients at risk of colonization. METHODS Data from MRSA surveillance cultures were combined with patient room locations, nursing assignments, and sibship information to create patient- and unit-based networks. Multivariate models were constructed to quantify the risk of incident MRSA colonization as a function of exposure to MRSA-colonized infants in these networks. RESULTS A MRSA-negative infant in the NICU simultaneously with a MRSA-positive infant had higher odds of becoming colonized when the colonized infant was a sibling, compared with an unrelated patient (odds ratio: 8.8 [95% confidence interval [CI]: 5.3-14.8]). Although knowing that a patient was MRSA-positive and was placed on contact precautions reduced the overall odds of another patient becoming colonized by 35% (95% CI: 20%-47%), having a nurse in common with that patient still increased the odds of colonization by 43% (95% CI: 14%-80%). Normalized group degree centrality, a unitwide network measure of connectedness between colonized and uncolonized patients, was a significant predictor of incident MRSA cases (odds ratio: 18.1 [95% CI: 3.6-90.0]). CONCLUSIONS Despite current infection-control strategies, patients remain at significant risk of MRSA colonization from MRSA-positive siblings and from other patients with whom they share nursing care. Strategies that minimize the frequency of staff members caring for both colonized and uncolonized infants may be beneficial in reducing the spread of MRSA colonization.
Collapse
Affiliation(s)
- Alon Geva
- Departments of Neonatology, ,Department of Medicine, Children's Hospital Boston, Boston, Massachusetts; and ,Departments of Pediatrics and
| | - Sharon B. Wright
- Health Care Quality, and ,Medicine and ,Medicine, Harvard Medical School, Harvard University, Boston, Massachusetts
| | | | - Jane A. Smallcomb
- Neonatal Intensive Care Unit, Beth Israel-Deaconess Medical Center, Boston, Massachusetts
| | - Charles Safran
- Medicine and ,Medicine, Harvard Medical School, Harvard University, Boston, Massachusetts
| | - James E. Gray
- Departments of Neonatology, ,Medicine and ,Departments of Pediatrics and ,Medicine, Harvard Medical School, Harvard University, Boston, Massachusetts
| |
Collapse
|
41
|
Abstract
OBJECTIVE In centers electing to offer therapeutic hypothermia for treating hypoxic-ischemic encephalopathy (HIE), determining the optimal number of cooling devices is not straightforward. The authors used computer-based modeling to determine the level of service as a function of local HIE caseload and number of cooling devices available. METHODS The authors used discrete event simulation to create a model that varied the number of HIE cases and number of cooling devices available. Outcomes of interest were percentage of HIE-affected infants not cooled, number of infants not cooled, and percentage of time that all cooling devices were in use. RESULTS With 1 cooling device, even the smallest perinatal center did not achieve a cooling rate of 99% of eligible infants. In contrast, 2 devices ensured 99% service in centers treating as many as 20 infants annually. In centers averaging no more than 1 HIE infant monthly, the addition of a third cooling device did not result in a substantial reduction in the number of infants who would not be cooled. CONCLUSION Centers electing to offer therapeutic hypothermia with only a single cooling device are at significant risk of being unable to provide treatment to eligible infants, whereas 2 devices appear to suffice for most institutions treating as many as 20 annual HIE cases. Three devices would rarely be needed given current caseloads seen at individual institutions. The quantitative nature of this analysis allows decision makers to determine the number of devices necessary to ensure adequate availability of therapeutic hypothermia given the HIE caseload of a particular institution.
Collapse
Affiliation(s)
- Alon Geva
- Department of Neonatology (AG, JG) Beth Israel-Deaconess Medical Center, Boston, MA,Division of Newborn Medicine, Harvard Medical School, Boston, MA (AG, JG)
| | - James Gray
- Division of Clinical Informatics (JG) Beth Israel-Deaconess Medical Center, Boston, MA,Division of Newborn Medicine, Harvard Medical School, Boston, MA (AG, JG)
| |
Collapse
|
42
|
Abstract
Objective. To use meta-analytic techniques to examine the effect of dexamethasone on the risk of postoperative bleeding following tonsillectomy. Data Sources. PubMed and Embase databases accessed on April 23, 2009, and April 28, 2009. Review Methods. Using principles of meta-analysis, inclusion and exclusion criteria were developed to identify all randomized controlled trials of patients undergoing tonsillectomy in which perioperative intravenous dexamethasone was administered in at least 1 treatment arm and bleeding complications were reported. Electronic databases were searched to identify candidate articles. Two authors independently abstracted data from each article. Discrepancies were resolved by consensus. A fixed-effects model was used to pool relative risks among studies using the Mantel-Haenszel method. Studies were assessed for publication bias using a funnel plot of studies’ effect size vs standard error of the effect size as well as Begg test and Egger test. A P value <.05 was considered significant. Results. The primary search identified 85 potential studies. Fourteen met inclusion criteria and were selected for meta-analysis. No significant heterogeneity was found among studies (I2< 0.1%; 95% confidence interval [CI], 0%-55%; P = .68). The pooled relative risk (RR) of postoperative bleeding did not differ significantly between patients receiving dexamethasone and controls (RR, 1.02; 95% CI, 0.65-1.61; P = .92). When studies were stratified by age, primary vs secondary hemorrhage, and follow-up duration, no further significant differences in bleeding rate were identified. No evidence of publication bias was found using Begg ( P = .70) or Egger ( P = .73) tests. Conclusion. The results of this meta-analysis indicate that perioperative dexamethasone does not confer an increased risk of postoperative bleeding in patients undergoing tonsillectomy.
Collapse
Affiliation(s)
- Alon Geva
- Department of Medicine, Children’s Hospital Boston, Boston, Massachusetts, USA
- Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA
| | - Matthew T. Brigger
- Department of Otolaryngology–Head and Neck Surgery, Naval Medical Center San Diego, San Diego, California, USA
| |
Collapse
|
43
|
Abstract
OBJECTIVE The goal was to examine nursing team structure and its relationship with family satisfaction. METHODS We used electronic health records to create patient-based, 1-mode networks of nursing handoffs. In these networks, nurses were represented as nodes and handoffs as edges. For each patient, we calculated network statistics including team size and diameter, network centrality index, proportion of newcomers to care teams according to day of hospitalization, and a novel measure of the average number of shifts between repeat caregivers, which was meant to quantify nursing continuity. We assessed parental satisfaction by using a standardized survey. RESULTS Team size increased with increasing length of stay. At 2 weeks of age, 50% of shifts were staffed by a newcomer nurse who had not previously cared for the index patient. The patterns of newcomers to teams did not differ according to birth weight. When the population was dichotomized according to median mean repeat caregiver interval value, increased reports of problems with nursing care were seen with less-consistent staffing by familiar nurses. This relationship persisted after controlling for factors including birth weight, length of stay, and team size. CONCLUSIONS Family perceptions of nursing care quality are more strongly associated with team structure and the sequence of nursing participation than with team size. Objective measures of health care team structure and function can be examined by applying network analytic techniques to information contained in electronic health records.
Collapse
Affiliation(s)
- James E Gray
- Division of Newborn Medicine, Harvard Medical School, Boston, MA. USA.
| | | | | | | | | | | |
Collapse
|
44
|
Gray J, Geva A, Zheng Z, Zupancic JAF. CoolSim: using industrial modeling techniques to examine the impact of selective head cooling in a model of perinatal regionalization. Pediatrics 2008; 121:28-36. [PMID: 18166554 DOI: 10.1542/peds.2007-0633] [Citation(s) in RCA: 12] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/24/2022] Open
Abstract
OBJECTIVE A selective head-cooling device for the treatment of moderate to severe hypoxic-ischemic encephalopathy has been approved by the Food and Drug Administration for use in the United States. To reflect the complexity of health care delivery at the systems level, we used the industrial modeling technique of discrete event simulation to analyze the impact of various deployment strategies for selective head cooling and its partner technology, amplitude-integrated electroencephalography. METHODS We modeled the course through the perinatal system of all births in Massachusetts over a 1-year period. Cohort and care characteristics were drawn from existing databases. Results of a recently published trial were used to estimate the effects of selective head cooling. One thousand cohort replications were conducted to assess uncertainty. Several policy alternatives were examined, including no use of selective head cooling and scenarios that altered the number and placement of selective head-cooling and amplitude-integrated electroencephalography units throughout the state. Patient-level outcome and cost data were assessed. RESULTS For all scenarios tested, the use of amplitude-integrated electroencephalography/selective head cooling resulted in better outcomes at lower cost. However, substantial differences in transfer rates, failure-to-cool rates, and total costs were seen across scenarios. Optimal decision-making regarding the number and placement of devices led to a 16% improvement in cost savings and a 10-fold decrease in failure-to-cool rates, compared with other deployment scenarios. These results were insensitive to significant changes in model inputs. CONCLUSIONS On the basis of currently available data, the package of amplitude-integrated electroencephalography and selective head cooling seems to be an economically desirable intervention. Quantifiable techniques to assess system-wide technology performance provide a powerful approach to informing decisions regarding the structure and function of health care systems.
Collapse
Affiliation(s)
- James Gray
- Department of Neonatology, Beth Israel Deaconess Medical Center, 330 Brookline Ave, Boston, MA 02215, USA
| | | | | | | |
Collapse
|
45
|
Geva A, McMahon CJ, Gauvreau K, Mohammed L, del Nido PJ, Geva T. Risk factors for reoperation after repair of discrete subaortic stenosis in children. J Am Coll Cardiol 2007; 50:1498-504. [PMID: 17919571 DOI: 10.1016/j.jacc.2007.07.013] [Citation(s) in RCA: 42] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/07/2007] [Revised: 05/30/2007] [Accepted: 07/01/2007] [Indexed: 10/22/2022]
Abstract
OBJECTIVES This study aimed to identify independent predictors of reoperation after successful resection of discrete subaortic stenosis (DSS). BACKGROUND Recurrence of DSS has been reported to range from 0% to 55% of patients. Factors associated with recurrence have not been adequately defined. METHODS Patients were included if they had a diagnosis of DSS, normal segmental cardiac anatomy, previous resection of DSS, and at least 36 months' follow-up. Demographic, surgical, and echocardiographic data were analyzed. Primary outcome was repeat resection of DSS in patients after successful primary resection. RESULTS Of 111 subjects who had successful surgical resection of DSS, 16 patients (14%) required reoperation. Median follow-up time was 8.2 years. Form of DSS and gender did not differ significantly between those with reoperation and those without. In multivariate analysis, independent predictors of reoperation that would be available before first surgery were <6 mm distance between the aortic valve (AoV) and the obstruction (hazard ratio [HR] 5.1; p = 0.013) and peak gradient by Doppler > or =60 mm Hg (HR 4.2; p = 0.016). If intraoperative variables are also considered, peeling of the membrane from the AoV or mitral valve at first surgery, <6 mm distance between the DSS and AoV, and peak gradient by Doppler > or =60 mm Hg were independent predictors of reoperation. CONCLUSIONS Proximity of the obstructive lesion to the AoV and severe obstruction determined by preoperative echocardiography, as well as involvement of valve leaflets requiring surgical peeling, predict recurrent DSS requiring reoperation.
Collapse
Affiliation(s)
- Alon Geva
- Department of Cardiology, Children's Hospital Boston, and Harvard Medical School, Boston, Massachusetts 02115, USA
| | | | | | | | | | | |
Collapse
|
46
|
Abstract
A baby girl presented with symptomatic sickle cell disease exacerbated by mild hypoxemia, despite a newborn-screening diagnosis of sickle cell trait. DNA sequencing of the beta globin gene revealed that her maternal beta globin allele was normal. Her paternal allele had not only the expected sickle-trait mutation, betaGlu6Val, but also a second, charge-neutral mutation, betaLeu68Phe. Analysis of the patient's hemoglobin revealed that the double-mutant protein, which we called "hemoglobin Jamaica Plain," had severely reduced oxygen affinity. Structural modeling suggested destabilization of the oxy conformation as a molecular mechanism for sickling in a heterozygote at an ambient partial pressure of oxygen.
Collapse
Affiliation(s)
- Alon Geva
- Division of Hematology-Oncology, Children's Hospital Boston, MA 02115, USA
| | | | | | | | | | | |
Collapse
|
47
|
Yao DC, Tolan DR, Murray MF, Harris DJ, Darras BT, Geva A, Neufeld EJ. Hemolytic anemia and severe rhabdomyolysis caused by compound heterozygous mutations of the gene for erythrocyte/muscle isozyme of aldolase, ALDOA(Arg303X/Cys338Tyr). Blood 2003; 103:2401-3. [PMID: 14615364 DOI: 10.1182/blood-2003-09-3160] [Citation(s) in RCA: 47] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/19/2023] Open
Abstract
Aldolase (E.C. 4.1.2.13), a homotetrameric protein encoded by the ALDOA gene, converts fructose-1,6-bisphosphate to dihydroxyacetone phosphate and glyceraldehyde-3-phosphate. Three isozymes are encoded by distinct genes. The sole aldolase present in red blood cells and skeletal muscle is the A isozyme. We report here the case of a girl of Sicilian descent with aldolase A deficiency. Clinical manifestations included transfusion-dependent anemia until splenectomy at age 3 and increasing muscle weakness, with death at age 4 associated with rhabdomyolysis and hyperkalemia. Sequence analysis of the ALDOA coding regions revealed 2 novel heterozygous ALDOA mutations in conserved regions of the protein. The paternal allele encoded a nonsense mutation, Arg303X, in the enzyme-active site. The maternal allele encoded a missense mutation, Cys338Tyr, predicted to cause enzyme instability. This is the most severely affected patient reported to date and only the second with both rhabdomyolysis and hemolysis.
Collapse
Affiliation(s)
- David C Yao
- Division of Genetics, Department of Neurology, Children's Hospital Boston, Dana Farber Cancer Institute and Harvard Medical School, MA 02115, USA
| | | | | | | | | | | | | |
Collapse
|
48
|
Steinkamp M, Geva A, Joffe S, Lapp CN, Neufeld EJ. Chronic disseminated intravascular coagulation and childhood-onset skin necrosis resulting from homozygosity for a protein C Gla domain mutation, Arg15Trp. J Pediatr Hematol Oncol 2002; 24:685-8. [PMID: 12439046 DOI: 10.1097/00043426-200211000-00018] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/19/2023]
Abstract
A toddler of Haitian descent presented with an 18-month history of chronic consumption coagulopathy, followed by catastrophic skin necrosis. Protein C deficiency (1% to 3% of control) was noted by functional assay; chromogenic assay and antigen levels were 30% of control. Plasma infusion abrogated the disseminated intravascular coagulation-like state. The authors identified a homozygous mutation, C1432T, resulting in a missense, Arg15Trp, in the gamma-carboxyglutamate domain of the protein. Chronic consumption coagulopathy without purpura fulminans or venous thrombosis is a rare presentation of defective protein C pathway. The result of this mutation is a mixed type I (low antigen) and type II (low function) phenotype.
Collapse
Affiliation(s)
- Mara Steinkamp
- Division of Hematology, Children's Hospital, 300 Longwood Avenue, Boston, MA 02115, USA
| | | | | | | | | |
Collapse
|
49
|
Kaplan B, Yogev Y, Sulkas J, Geva A, Nahum R, Fisher M. Attitude towards health and hormone replacement therapy among female obstetrician-gynecologists in Israel. Maturitas 2002; 43:113-6. [PMID: 12385859 DOI: 10.1016/s0378-5122(02)00187-1] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
Abstract
OBJECTIVE To assess Israeli women gynecologists toward their own health, their health related behaviors and to assess attitude towards and the use of hormone replacement therapy (HRT). METHODS Ninety five actively employed hospital and community women gynecologist completed a questionnaire on attitude towards self-health, way of life, smoking habits, and regular breast, blood, pap smear examinations and HRT. RESULTS Mean BMI was 25.3 Kg/m(2)+/-4.2, 61% considered themselves above average weight, and only 39% estimated their weight as appropriate. Fifty six percent were on active weight-loss diets, and 35% were current smokers. Blood tests, pap smears and breast evaluations were regularly done by 73.4, 91.5, and 64.1%, respectively. Overall, 74% of the gynecologists had a positive opinion about HRT; 70% of the menopausal subgroup had ever used HRT, and 93.3% of the perimenopausal subgroup intended to use it. The main reason for starting HRT was climacteric symptoms, and for stopping or avoiding HRT were equally bleeding, fear of cancer and adverse reactions towards HRT. By far the oral HRT mode was the most popular and 90% of users expressed satisfaction with treatment. CONCLUSIONS Israeli women gynecologists are aware and maintain carefully their health, excluding cigarette smoking. The high rate of use and awareness of HRT among this group is encouraging considering that gynecologist serves as role model for the public and maintains the main source of HRT in the community.
Collapse
Affiliation(s)
- B Kaplan
- The Israeli Society of Obstetrics and Gynecology in the Community, Tel-Aviv, Israel.
| | | | | | | | | | | |
Collapse
|
50
|
Abstract
The objective of the study was to examine mothers' knowledge about contraception, their attitudes to their daughters' use of contraception, and their communication with their daughters on the subject. A 20-item questionnaire was distributed in gynecological clinics throughout Israel for completion by women who had daughters over the age of 14 years. The questionnaire covered the mothers' demographic data, use of contraception, knowledge of contraception, attitude to their daughters' contraceptive use and sexual relationships, and communication with their daughters about contraception. Only 36% of the women received contraceptive information from physicians. Almost half felt their daughter should begin sexual relations when she felt she was ready; over two-thirds felt she should begin using contraception before or at the time of beginning sexual relations. Over three-quarters spoke with their daughters about contraception. Higher educational level of the mother was associated with high rate use of contraception by the mother, her support of earlier use of contraception by her daughter, a greater likelihood of her discussing contraception with her daughter, and a lesser likelihood to view contraceptives as dangerous to one's health. It is concluded that mothers of teenage daughters in Israel are involved in their daughters' decisions to begin sexual relations and the use of contraceptives. Their knowledge of contraception is adequate, although some gaps are still apparent. Clear correlation is found between higher educational level of the mothers and a more liberal attitude toward their daughters' sex life.
Collapse
Affiliation(s)
- R Bachar
- The Israeli Society of Obstetrics and Gynecology in the Community, Department of Obstetrics and Gynecology, Rabin Medical Center, Petah Tikva, Israel
| | | | | | | | | | | |
Collapse
|