1
|
Jacobs JP, Kumar SR, Overman DM, Dearani JA, Romano JC. The Evolving Role of Machine Learning in the Analysis of Outcomes After Pediatric and Congenital Cardiac Surgery. Ann Thorac Surg 2024; 118:207-208. [PMID: 38081496 DOI: 10.1016/j.athoracsur.2023.11.030] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/16/2023] [Accepted: 11/18/2023] [Indexed: 06/25/2024]
Affiliation(s)
- Jeffrey Phillip Jacobs
- Congenital Heart Center Division of Cardiothoracic Surgery Departments of Surgery and Pediatrics University of Florida, 1600 SW Archer Rd, Gainesville, FL 32608.
| | - S Ram Kumar
- Division of Cardiothoracic Surgery Children's Nebraska University of Nebraska Medical Center Omaha, Nebraska
| | - David M Overman
- Division of Cardiovascular Surgery, Mayo Clinic-Children's Minnesota Cardiovascular Collaborative, Minneapolis, Minnesota
| | - Joseph A Dearani
- Division of Cardiovascular Surgery, Mayo Clinic-Children's Minnesota Cardiovascular Collaborative, Minneapolis, Minnesota
| | - Jennifer C Romano
- Department of Cardiac Surgery, University of Michigan, Ann Arbor, Michigan
| |
Collapse
|
2
|
Sarris GE, Zhuo D, Mingardi L, Dunn J, Levine J, Tobota Z, Maruszewski B, Fragata J, Bertsimas D. Congenital Heart Surgery Machine Learning-Derived In-Depth Benchmarking Tool. Ann Thorac Surg 2024; 118:199-206. [PMID: 38065331 DOI: 10.1016/j.athoracsur.2023.10.034] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/20/2023] [Revised: 09/15/2023] [Accepted: 10/09/2023] [Indexed: 01/06/2024]
Abstract
BACKGROUND We previously showed that machine learning-based methodologies of optimal classification trees (OCTs) can accurately predict risk after congenital heart surgery and assess case-mix-adjusted performance after benchmark procedures. We extend this methodology to provide interpretable, easily accessible, and actionable hospital performance analysis across all procedures. METHODS The European Congenital Heart Surgeons Association Congenital Cardiac Database data subset of 172,888 congenital cardiac surgical procedures performed in European centers between 1989 and 2022 was analyzed. OCT models (decision trees) were built predicting hospital mortality (area under the curve [AUC], 0.866), prolonged postoperative mechanical ventilatory support time (AUC, 0.851), or hospital length of stay (AUC, 0.818), thereby establishing case-adjusted benchmarking standards reflecting the overall performance of all participating hospitals, designated as the "virtual hospital." OCT analysis of virtual hospital aggregate data yielded predicted expected outcomes (both aggregate and for risk-matched patient cohorts) for the individual hospital's own specific case-mix, readily available on-line. RESULTS Raw average rates were hospital mortality, 4.9%; mechanical ventilatory support time, 14.5%; and length of stay, 15.0%. Of 146 participating centers, compared with each hospital's overall case-adjusted predicted hospital mortality benchmark, 20.5% statistically (<90% CI) overperformed and 20.5% underperformed. An interactive tool based on the OCT analysis automatically reveals 14 hospital-specific patient cohorts, simultaneously assessing overperformance or underperformance, and enabling further analysis of cohort strata in any chosen time frame. CONCLUSIONS Machine learning-based OCT benchmarking analysis provides automatic assessment of hospital-specific case-adjusted performance after congenital heart surgery, not only overall but importantly, also by similar risk patient cohorts. This is a tool for hospital self-assessment, particularly facilitated by the user-accessible online-platform.
Collapse
Affiliation(s)
| | - Daisy Zhuo
- Alexandria Health, Cambridge, Massachusetts
| | | | - Jack Dunn
- Alexandria Health, Cambridge, Massachusetts
| | | | | | | | - Jose Fragata
- Department of Cardiothoracic Surgery, Hospital de Santa Marta and NOVA University, Lisbon, Portugal
| | - Dimitris Bertsimas
- Operations Research Center and Sloan School of Management, Massachusetts Institute of Technology, Cambridge, Massachusetts
| |
Collapse
|
3
|
Verma A, Williamson CG, Bakhtiyar SS, Hadaya J, Hekking T, Kronen E, Si MS, Benharash P. Center-Level Variation in Failure to Rescue After Pediatric Cardiac Surgery. Ann Thorac Surg 2024; 117:552-559. [PMID: 37182822 DOI: 10.1016/j.athoracsur.2023.05.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/08/2022] [Revised: 04/17/2023] [Accepted: 05/01/2023] [Indexed: 05/16/2023]
Abstract
BACKGROUND Although failure to rescue (FTR) is increasingly recognized as a quality metric, studies in congenital cardiac surgery remain sparse. Within a national cohort of children undergoing cardiac operations, we characterized the presence of center-level variation in FTR and hypothesized a strong association with mortality but not complications. METHODS All children undergoing congenital cardiac operations were identified in the 2013 to 2019 Nationwide Readmissions Database. FTR was defined as in-hospital death after cardiac arrest, ventricular tachycardia/fibrillation, prolonged mechanical ventilation, pneumonia, stroke, venous thromboembolism, or sepsis, among other complications. Hierarchical models were used to generate hospital-specific, risk-adjusted rates of mortality, complications, and FTR. Centers in the highest decile of FTR were identified and compared with others. RESULTS Of an estimated 74,070 patients, 1.9% died before discharge, at least 1 perioperative complication developed in 43.0%, and 4.1% experienced FTR. After multilevel modeling, decreasing age, nonelective admission, and increasing operative complexity were associated with greater odds of FTR. Variations in overall mortality and FTR exhibited a strong, positive relationship (r = 0.97), whereas mortality and complications had a negligible association (r = -0.02). Compared with others, patients at centers with high rates of FTR had similar distributions of age, sex, chronic conditions, and operative complexity. CONCLUSIONS In the present study, center-level variations in mortality were more strongly explained by differences in FTR than complications. Our findings suggest the utility of FTR as a quality metric for congenital heart surgery, although further study is needed to develop a widely accepted definition and appropriate risk-adjustment models.
Collapse
Affiliation(s)
- Arjun Verma
- Cardiovascular Outcomes Research Laboratories (CORELAB), David Geffen School of Medicine at UCLA, University of California, Los Angeles, Los Angeles, California
| | - Catherine G Williamson
- Cardiovascular Outcomes Research Laboratories (CORELAB), David Geffen School of Medicine at UCLA, University of California, Los Angeles, Los Angeles, California
| | - Syed Shahyan Bakhtiyar
- Cardiovascular Outcomes Research Laboratories (CORELAB), David Geffen School of Medicine at UCLA, University of California, Los Angeles, Los Angeles, California; Department of Surgery, David Geffen School of Medicine at UCLA, University of California, Los Angeles, Los Angeles, California; Department of Surgery, University of Colorado Anschutz Medical Center, Aurora, Colorado
| | - Joseph Hadaya
- Cardiovascular Outcomes Research Laboratories (CORELAB), David Geffen School of Medicine at UCLA, University of California, Los Angeles, Los Angeles, California; Department of Surgery, David Geffen School of Medicine at UCLA, University of California, Los Angeles, Los Angeles, California
| | - Tyson Hekking
- Department of Pediatrics, David Geffen School of Medicine at UCLA, University of California, Los Angeles, Los Angeles, California
| | - Elsa Kronen
- Cardiovascular Outcomes Research Laboratories (CORELAB), David Geffen School of Medicine at UCLA, University of California, Los Angeles, Los Angeles, California
| | - Ming-Sing Si
- Division of Cardiac Surgery, Department of Surgery, David Geffen School of Medicine at UCLA, University of California, Los Angeles, Los Angeles, California
| | - Peyman Benharash
- Cardiovascular Outcomes Research Laboratories (CORELAB), David Geffen School of Medicine at UCLA, University of California, Los Angeles, Los Angeles, California; Division of Cardiac Surgery, Department of Surgery, David Geffen School of Medicine at UCLA, University of California, Los Angeles, Los Angeles, California.
| |
Collapse
|
4
|
Chang Junior J, Caneo LF, Turquetto ALR, Amato LP, Arita ECTC, Fernandes AMDS, Trindade EM, Jatene FB, Dossou PE, Jatene MB. Predictors of in-ICU length of stay among congenital heart defect patients using artificial intelligence model: A pilot study. Heliyon 2024; 10:e25406. [PMID: 38370176 PMCID: PMC10869777 DOI: 10.1016/j.heliyon.2024.e25406] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/08/2023] [Revised: 01/23/2024] [Accepted: 01/25/2024] [Indexed: 02/20/2024] Open
Abstract
Objective This study aims to develop a predictive model using artificial intelligence to estimate the ICU length of stay (LOS) for Congenital Heart Defects (CHD) patients after surgery, improving care planning and resource management. Design We analyze clinical data from 2240 CHD surgery patients to create and validate the predictive model. Twenty AI models are developed and evaluated for accuracy and reliability. Setting The study is conducted in a Brazilian hospital's Cardiovascular Surgery Department, focusing on transplants and cardiopulmonary surgeries. Participants Retrospective analysis is conducted on data from 2240 consecutive CHD patients undergoing surgery. Interventions Ninety-three pre and intraoperative variables are used as ICU LOS predictors. Measurements and main results Utilizing regression and clustering methodologies for ICU LOS (ICU Length of Stay) estimation, the Light Gradient Boosting Machine, using regression, achieved a Mean Squared Error (MSE) of 15.4, 11.8, and 15.2 days for training, testing, and unseen data. Key predictors included metrics such as "Mechanical Ventilation Duration", "Weight on Surgery Date", and "Vasoactive-Inotropic Score". Meanwhile, the clustering model, Cat Boost Classifier, attained an accuracy of 0.6917 and AUC of 0.8559 with similar key predictors. Conclusions Patients with higher ventilation times, vasoactive-inotropic scores, anoxia time, cardiopulmonary bypass time, and lower weight, height, BMI, age, hematocrit, and presurgical oxygen saturation have longer ICU stays, aligning with existing literature.
Collapse
Affiliation(s)
- João Chang Junior
- Hospital Das Clínicas HCFMUSP, Universidade de São Paulo, Instituto Do Coração - InCor, Av. Dr. Enéas Carvalho de Aguiar, 44, CEP 05403-000, São Paulo, Brazil
- Escola Superior de Engenharia e Gestão - ESEG, Rua Apeninos, 960, São Paulo, Brazil
- Centro Universitário Armando Alvares Penteado - FAAP, Rua Alagoas, 903, São Paulo, Brazil
| | - Luiz Fernando Caneo
- Hospital Das Clínicas HCFMUSP, Universidade de São Paulo, Instituto Do Coração - InCor, Av. Dr. Enéas Carvalho de Aguiar, 44, CEP 05403-000, São Paulo, Brazil
| | - Aida Luiza Ribeiro Turquetto
- Hospital Das Clínicas HCFMUSP, Universidade de São Paulo, Instituto Do Coração - InCor, Av. Dr. Enéas Carvalho de Aguiar, 44, CEP 05403-000, São Paulo, Brazil
- Núcleo de Avaliação de Tecnologias da Saúde - NATS-HCFMUSP, Brazil
| | - Luciana Patrick Amato
- Hospital Das Clínicas HCFMUSP, Universidade de São Paulo, Instituto Do Coração - InCor, Av. Dr. Enéas Carvalho de Aguiar, 44, CEP 05403-000, São Paulo, Brazil
- Núcleo de Avaliação de Tecnologias da Saúde - NATS-HCFMUSP, Brazil
| | - Elisandra Cristina Trevisan Calvo Arita
- Hospital Das Clínicas HCFMUSP, Universidade de São Paulo, Instituto Do Coração - InCor, Av. Dr. Enéas Carvalho de Aguiar, 44, CEP 05403-000, São Paulo, Brazil
| | - Alfredo Manoel da Silva Fernandes
- Hospital Das Clínicas HCFMUSP, Universidade de São Paulo, Instituto Do Coração - InCor, Av. Dr. Enéas Carvalho de Aguiar, 44, CEP 05403-000, São Paulo, Brazil
| | - Evelinda Marramon Trindade
- Núcleo de Avaliação de Tecnologias da Saúde - NATS-HCFMUSP, Brazil
- Laboratório de Ensino, Pesquisa e Inovação Em Saúde - LEPIC-HCFMUSP, Superintendência / Hospital Das Clínicas da FMUSP, Rua Dr. Ovidio Pires de Campos, 225, 5°. Andar – Superintendência, Sao Paulo, Brazil
- Sao Paulo State Health Secretariat–SES-SP, Sao Paulo, Brazil
| | - Fábio Biscegli Jatene
- Hospital Das Clínicas HCFMUSP, Universidade de São Paulo, Instituto Do Coração - InCor, Av. Dr. Enéas Carvalho de Aguiar, 44, CEP 05403-000, São Paulo, Brazil
| | - Paul-Eric Dossou
- Institut Catholique des Arts et Metiers–Icam, Paris-Senart, France
| | - Marcelo Biscegli Jatene
- Hospital Das Clínicas HCFMUSP, Universidade de São Paulo, Instituto Do Coração - InCor, Av. Dr. Enéas Carvalho de Aguiar, 44, CEP 05403-000, São Paulo, Brazil
| |
Collapse
|
5
|
Grunert M, Dorn C, Dopazo A, Sánchez-Cabo F, Vázquez J, Rickert-Sperling S, Lara-Pezzi E. Technologies to Study Genetics and Molecular Pathways. ADVANCES IN EXPERIMENTAL MEDICINE AND BIOLOGY 2024; 1441:435-458. [PMID: 38884724 DOI: 10.1007/978-3-031-44087-8_22] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/18/2024]
Abstract
Over the last few decades, the study of congenital heart disease (CHD) has benefited from various model systems and the development of molecular biological techniques enabling the analysis of single gene as well as global effects. In this chapter, we first describe different models including CHD patients and their families, animal models ranging from invertebrates to mammals, and various cell culture systems. Moreover, techniques to experimentally manipulate these models are discussed. Second, we introduce cardiac phenotyping technologies comprising the analysis of mouse and cell culture models, live imaging of cardiogenesis, and histological methods for fixed hearts. Finally, the most important and latest molecular biotechniques are described. These include genotyping technologies, different applications of next-generation sequencing, and the analysis of transcriptome, epigenome, proteome, and metabolome. In summary, the models and technologies presented in this chapter are essential to study the function and development of the heart and to understand the molecular pathways underlying CHD.
Collapse
Affiliation(s)
- Marcel Grunert
- Cardiovascular Genetics, Charité - Universitätsmedizin Berlin, Berlin, Germany
- DiNAQOR AG, Schlieren, Switzerland
| | - Cornelia Dorn
- Cardiovascular Genetics, Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - Ana Dopazo
- Genomics Unit, Centro Nacional de Investigaciones Cardiovasculares, Madrid, Spain
| | - Fátima Sánchez-Cabo
- Bioinformatics Unit, Centro Nacional de Investigaciones Cardiovasculares, Madrid, Spain
| | - Jésus Vázquez
- Proteomics Unit, Centro Nacional de Investigaciones Cardiovasculares, Madrid, Spain
| | | | - Enrique Lara-Pezzi
- Myocardial Homeostasis and Cardiac Injury Programme, Centro Nacional de Investigaciones Cardiovasculares, Madrid, Spain.
| |
Collapse
|
6
|
Chhatwal K, Smith JJ, Bola H, Zahid A, Venkatakrishnan A, Brand T. Uncovering the Genetic Basis of Congenital Heart Disease: Recent Advancements and Implications for Clinical Management. CJC PEDIATRIC AND CONGENITAL HEART DISEASE 2023; 2:464-480. [PMID: 38205435 PMCID: PMC10777202 DOI: 10.1016/j.cjcpc.2023.10.008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 05/31/2023] [Accepted: 10/13/2023] [Indexed: 01/12/2024]
Abstract
Congenital heart disease (CHD) is the most prevalent hereditary disorder, affecting approximately 1% of all live births. A reduction in morbidity and mortality has been achieved with advancements in surgical intervention, yet challenges in managing complications, extracardiac abnormalities, and comorbidities still exist. To address these, a more comprehensive understanding of the genetic basis underlying CHD is required to establish how certain variants are associated with the clinical outcomes. This will enable clinicians to provide personalized treatments by predicting the risk and prognosis, which might improve the therapeutic results and the patient's quality of life. We review how advancements in genome sequencing are changing our understanding of the genetic basis of CHD, discuss experimental approaches to determine the significance of novel variants, and identify barriers to use this knowledge in the clinics. Next-generation sequencing technologies are unravelling the role of oligogenic inheritance, epigenetic modification, genetic mosaicism, and noncoding variants in controlling the expression of candidate CHD-associated genes. However, clinical risk prediction based on these factors remains challenging. Therefore, studies involving human-induced pluripotent stem cells and single-cell sequencing help create preclinical frameworks for determining the significance of novel genetic variants. Clinicians should be aware of the benefits and implications of the responsible use of genomics. To facilitate and accelerate the clinical integration of these novel technologies, clinicians should actively engage in the latest scientific and technical developments to provide better, more personalized management plans for patients.
Collapse
Affiliation(s)
- Karanjot Chhatwal
- Imperial College School of Medicine, Imperial College London, London, United Kingdom
- National Heart and Lung Institute, Imperial College London, Imperial Center of Clinical and Translational Medicine, London, United Kingdom
| | - Jacob J. Smith
- Imperial College School of Medicine, Imperial College London, London, United Kingdom
- National Heart and Lung Institute, Imperial College London, Imperial Center of Clinical and Translational Medicine, London, United Kingdom
| | - Harroop Bola
- Imperial College School of Medicine, Imperial College London, London, United Kingdom
- National Heart and Lung Institute, Imperial College London, Imperial Center of Clinical and Translational Medicine, London, United Kingdom
| | - Abeer Zahid
- Imperial College School of Medicine, Imperial College London, London, United Kingdom
- National Heart and Lung Institute, Imperial College London, Imperial Center of Clinical and Translational Medicine, London, United Kingdom
| | - Ashwin Venkatakrishnan
- Imperial College School of Medicine, Imperial College London, London, United Kingdom
- National Heart and Lung Institute, Imperial College London, Imperial Center of Clinical and Translational Medicine, London, United Kingdom
| | - Thomas Brand
- National Heart and Lung Institute, Imperial College London, Imperial Center of Clinical and Translational Medicine, London, United Kingdom
| |
Collapse
|
7
|
Jacobs ML, Backer CL. World Journal for Pediatric and Congenital Heart Surgery-The Official Journal of the Congenital Heart Surgeons' Society. World J Pediatr Congenit Heart Surg 2023; 14:572-574. [PMID: 37737600 DOI: 10.1177/21501351231174815] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/23/2023]
Abstract
The World Journal for Pediatric and Congenital Heart Surgery (WJPCHS) was established in 2009, as a means of advancing the educational and scholarship goals of the World Society for Pediatric and Congenital Heart Surgery. WJPCHS has grown steadily since the first issue was published in April 2010. In 2017, the Congenital Heart Surgeons' Society and the European Congenital Heart Surgeons Association both designated WJPCHS as the official journal of their respective organizations. The CHSS and ECHSA represent the face and the voice of congenital heart surgery in North America (United States and Canada) and in Europe, respectively. Each organization has advanced the science of surgical management of congenital heart disease through multicenter outcomes analyses, which have strongly and positively influenced the care of patients around the world.
Collapse
Affiliation(s)
- Marshall L Jacobs
- Department of Surgery, Johns Hopkins School of Medicine, Baltimore, MD, USA
| | - Carl L Backer
- Section of Pediatric Cardiothoracic Surgery, UK HealthCare Kentucky Children's Hospital, Lexington, KY, USA
- Cardiothoracic Surgery, Heart Institute, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA
| |
Collapse
|
8
|
Jacobs JP, Krasemann T, Herbst C, Tobota Z, Maruszewski B, Fragata J, Ebels T, Vida VL, Mattila I, Kansy A, Asfour B, Hörer J, Lotto AA, Çiçek MS, Liuba P, Dittrich S, Chessa M, Bökenkamp R, Sharland G, Hanséus K, Blom NA, Sarris GE. Combining Congenital Heart Surgical and Interventional Cardiology Outcome Data in a Single Database: The Development of a Patient-Centered Collaboration of the European Congenital Heart Surgeons Association (ECHSA) and the Association for European Paediatric and Congenital Cardiology (AEPC). World J Pediatr Congenit Heart Surg 2023; 14:464-473. [PMID: 37410599 PMCID: PMC10411030 DOI: 10.1177/21501351231168829] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2023] [Accepted: 03/11/2023] [Indexed: 07/08/2023]
Abstract
The European Congenital Heart Surgeons Association (ECHSA) Congenital Database (CD) is the second largest clinical pediatric and congenital cardiac surgical database in the world and the largest in Europe, where various smaller national or regional databases exist. Despite the dramatic increase in interventional cardiology procedures over recent years, only scattered national or regional databases of such procedures exist in Europe. Most importantly, no congenital cardiac database exists in the world that seamlessly combines both surgical and interventional cardiology data on an international level; therefore, the outcomes of surgical and interventional procedures performed on the same or similar patients cannot easily be tracked, assessed, and analyzed. In order to fill this important gap in our capability to gather and analyze information on our common patients, ECHSA and The Association for European Paediatric and Congenital Cardiology (AEPC) have embarked on a collaborative effort to expand the ECHSA-CD with a new module designed to capture data about interventional cardiology procedures. The purpose of this manuscript is to describe the concept, the structure, and the function of the new AEPC Interventional Cardiology Part of the ECHSA-CD, as well as the potentially valuable synergies provided by the shared interventional and surgical analyses of outcomes of patients. The new AEPC Interventional Cardiology Part of the ECHSA-CD will allow centers to have access to robust surgical and transcatheter outcome data from their own center, as well as robust national and international aggregate outcome data for benchmarking. Each contributing center or department will have access to their own data, as well as aggregate data from the AEPC Interventional Cardiology Part of the ECHSA-CD. The new AEPC Interventional Cardiology Part of the ECHSA-CD will allow cardiology centers to have access to aggregate cardiology data, just as surgical centers already have access to aggregate surgical data. Comparison of surgical and catheter interventional outcomes could potentially strengthen decision processes. A study of the wealth of information collected in the database could potentially also contribute toward improved early and late survival, as well as enhanced quality of life of patients with pediatric and/or congenital heart disease treated with surgery and interventional cardiac catheterization across Europe and the world.
Collapse
Affiliation(s)
- Jeffrey P Jacobs
- Congenital Heart Center, Division of Cardiovascular Surgery, Departments of Surgery and Pediatrics, University of Florida, Gainesville, FL, United States of America
| | - Thomas Krasemann
- Department of Paediatric Cardiology, Sophia Children's Hospital, Rotterdam, The Netherlands
| | | | - Zdzislaw Tobota
- Pediatric Cardiothoracic Surgery, Children's Memorial Health Institute, Warsaw, Poland
| | - Bohdan Maruszewski
- Pediatric Cardiothoracic Surgery, Children's Memorial Health Institute, Warsaw, Poland
| | - Jose Fragata
- Hospital de Santa Marta, NOVA Medical School, Lisbon, Portugal
| | - Tjark Ebels
- Department of Cardiothoracic Surgery, University Medical Center Groningen, Groningen, The Netherlands
| | - Vladimiro L Vida
- Pediatric and Congenital Cardiac Surgery Unit, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padua, Padua, Italy
| | - Ilkka Mattila
- Department of Pediatric Cardiac Surgery, Hospital for Children and Adolescents, University of Helsinki, Helsinki, Finland
| | - Andrzej Kansy
- Pediatric Cardiothoracic Surgery, Children's Memorial Health Institute, Warsaw, Poland
| | - Boulos Asfour
- Department of Pediatric Cardiac Surgery, Pediatric Heart Center, University Hospital Bonn (UKB), Bonn, Germany
| | - Jürgen Hörer
- Department of Congenital and Pediatric Heart Surgery, German Heart Center Munich, Munich, Germany
- Division of Congenital and Pediatric Heart Surgery, University Hospital of Munich, Ludwig-Maximilians-Universität, Munich, Germany
| | - Attilio A Lotto
- Pediatric Cardiac Surgery, Alder Hey Children's Hospital, Liverpool, UK
| | - M Sertaç Çiçek
- Istanbul University Faculty of Medicine, Department of Cardiovascular Surgery, Istanbul, Turkey
| | - Petru Liuba
- Department of Cardiology, Pediatric Heart Center, Skåne University Hospital, Lund, Skåne, Sweden
- Lund University, Lund, Skåne, Sweden
| | - Sven Dittrich
- Department of Pediatric Cardiology, Friedrich-Alexander-Universitat Erlangen-Nurnberg, Erlangen, Germany
| | - Massimo Chessa
- ACHD Unit, Department of Pediatric and Adult Congenital Disease, IRCCS Policlinico San Donato, San Donato Milanese, Italy
- Vita Salute San Raffaele University, Milan, Italy
| | - Regina Bökenkamp
- Department of Pediatric Cardiology, Leiden University Medical Center, Leiden, The Netherlands
| | - Gurleen Sharland
- Department of Congenital Heart Disease, Evelina London Children's Hospital, Guy's and St Thomas’ NHS Foundation Trust, London, United Kingdom
| | - Katarina Hanséus
- Department of Paediatric Cardiology, Skåne University Hospital, Lund, Sweden
- Department of Clinical Sciences, Lund University, Lund, Sweden
| | - Nico A Blom
- Department of Pediatric Cardiology, Leiden University Medical Center, Leiden, The Netherlands
- Paediatric Cardiology, Amsterdam University Medical Center, Amsterdam, The Netherlands
| | | |
Collapse
|
9
|
Changing epidemiology of congenital heart disease: effect on outcomes and quality of care in adults. Nat Rev Cardiol 2023; 20:126-137. [PMID: 36045220 DOI: 10.1038/s41569-022-00749-y] [Citation(s) in RCA: 24] [Impact Index Per Article: 24.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 06/29/2022] [Indexed: 01/21/2023]
Abstract
The epidemiology of congenital heart disease (CHD) has changed in the past 50 years as a result of an increase in the prevalence and survival rate of CHD. In particular, mortality in patients with CHD has changed dramatically since the latter half of the twentieth century as a result of more timely diagnosis and the development of interventions for CHD that have prolonged life. As patients with CHD age, the disease burden shifts away from the heart and towards acquired cardiovascular and systemic complications. The societal costs of CHD are high, not just in terms of health-care utilization but also with regards to quality of life. Lifespan disease trajectories for populations with a high disease burden that is measured over prolonged time periods are becoming increasingly important to define long-term outcomes that can be improved. Quality improvement initiatives, including advanced physician training for adult CHD in the past 10 years, have begun to improve disease outcomes. As we seek to transform lifespan into healthspan, research efforts need to incorporate big data to allow high-value, patient-centred and artificial intelligence-enabled delivery of care. Such efforts will facilitate improved access to health care in remote areas and inform the horizontal integration of services needed to manage CHD for the prolonged duration of survival among adult patients.
Collapse
|
10
|
Use of machine learning in pediatric surgical clinical prediction tools: A systematic review. J Pediatr Surg 2023; 58:908-916. [PMID: 36804103 DOI: 10.1016/j.jpedsurg.2023.01.020] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/24/2022] [Accepted: 01/03/2023] [Indexed: 01/20/2023]
Abstract
PURPOSE Clinical prediction tools (CPTs) are decision-making instruments utilizing patient data to predict specific clinical outcomes, risk-stratify patients, or suggest personalized diagnostic or therapeutic options. Recent advancements in artificial intelligence have resulted in a proliferation of CPTs created using machine learning (ML)-yet the clinical applicability of ML-based CPTs and their validation in clinical settings remain unclear. This systematic review aims to compare the validity and clinical efficacy of ML-based to traditional CPTs in pediatric surgery. METHODS Nine databases were searched from 2000 until July 9, 2021 to retrieve articles reporting on CPTs and ML for pediatric surgical conditions. PRISMA standards were followed, and screening was performed by two independent reviewers in Rayyan, with a third reviewer resolving conflicts. Risk of bias was assessed using the PROBAST. RESULTS Out of 8300 studies, 48 met the inclusion criteria. The most represented surgical specialties were pediatric general (14), neurosurgery (13) and cardiac surgery (12). Prognostic (26) CPTs were the most represented type of surgical pediatric CPTs followed by diagnostic (10), interventional (9), and risk stratifying (2). One study included a CPT for diagnostic, interventional and prognostic purposes. 81% of studies compared their CPT to ML-based CPTs, statistical CPTs, or the unaided clinician, but lacked external validation and/or evidence of clinical implementation. CONCLUSIONS While most studies claim significant potential improvements by incorporating ML-based CPTs in pediatric surgical decision-making, both external validation and clinical application remains limited. Further studies must focus on validating existing instruments or developing validated tools, and incorporating them in the clinical workflow. TYPE OF STUDY Systematic Review LEVEL OF EVIDENCE: Level III.
Collapse
|
11
|
Jone PN, Gearhart A, Lei H, Xing F, Nahar J, Lopez-Jimenez F, Diller GP, Marelli A, Wilson L, Saidi A, Cho D, Chang AC. Artificial Intelligence in Congenital Heart Disease: Current State and Prospects. JACC. ADVANCES 2022; 1:100153. [PMID: 38939457 PMCID: PMC11198540 DOI: 10.1016/j.jacadv.2022.100153] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 06/13/2022] [Revised: 10/04/2022] [Accepted: 10/07/2022] [Indexed: 06/29/2024]
Abstract
The current era of big data offers a wealth of new opportunities for clinicians to leverage artificial intelligence to optimize care for pediatric and adult patients with a congenital heart disease. At present, there is a significant underutilization of artificial intelligence in the clinical setting for the diagnosis, prognosis, and management of congenital heart disease patients. This document is a call to action and will describe the current state of artificial intelligence in congenital heart disease, review challenges, discuss opportunities, and focus on the top priorities of artificial intelligence-based deployment in congenital heart disease.
Collapse
Affiliation(s)
- Pei-Ni Jone
- Section of Pediatric Cardiology, Department of Pediatrics, Lurie Children’s Hospital of Chicago, Northwestern University Feinberg School of Medicine, Chicago, Illinois, USA
| | - Addison Gearhart
- Department of Cardiology, Boston Children's Hospital and Harvard Medical School, Boston, Massachusetts, USA
| | - Howard Lei
- Division of Pediatric Cardiology, Children’s Hospital of Orange County, Orange, California, USA
| | - Fuyong Xing
- Department of Biostatistics and Informatics, University of Colorado Anschutz Medical Campus, Aurora, Colorado, USA
| | - Jai Nahar
- Department of Cardiology, Children's National Hospital, Washington, DC, USA
| | | | - Gerhard-Paul Diller
- Department of Cardiology III-Adult Congenital and Valvular Heart Disease, University Hospital Muenster, Muenster, Germany
- Adult Congenital Heart Centre and National Centre for Pulmonary Hypertension, Royal Brompton and Harefield National Health Service Foundation Trust, Imperial College London, London, UK
- National Register for Congenital Heart Defects, Berlin, Germany
| | - Ariane Marelli
- McGill Adult Unit for Congenital Heart Disease Excellence, Department of Medicine, McGill University, Montréal, Québec, Canada
| | - Laura Wilson
- Department of Pediatrics, University of Florida-Congenital Heart Center, Gainesville, Florida, USA
| | - Arwa Saidi
- Department of Pediatrics, University of Florida-Congenital Heart Center, Gainesville, Florida, USA
| | - David Cho
- Department of Cardiology, University of California at Los Angeles, Los Angeles, California, USA
| | - Anthony C. Chang
- Division of Pediatric Cardiology, Children’s Hospital of Orange County, Orange, California, USA
| |
Collapse
|
12
|
Sethi Y, Patel N, Kaka N, Desai A, Kaiwan O, Sheth M, Sharma R, Huang H, Chopra H, Khandaker MU, Lashin MMA, Hamd ZY, Emran TB. Artificial Intelligence in Pediatric Cardiology: A Scoping Review. J Clin Med 2022; 11:jcm11237072. [PMID: 36498651 PMCID: PMC9738645 DOI: 10.3390/jcm11237072] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/05/2022] [Revised: 11/22/2022] [Accepted: 11/26/2022] [Indexed: 12/05/2022] Open
Abstract
The evolution of AI and data science has aided in mechanizing several aspects of medical care requiring critical thinking: diagnosis, risk stratification, and management, thus mitigating the burden of physicians and reducing the likelihood of human error. AI modalities have expanded feet to the specialty of pediatric cardiology as well. We conducted a scoping review searching the Scopus, Embase, and PubMed databases covering the recent literature between 2002-2022. We found that the use of neural networks and machine learning has significantly improved the diagnostic value of cardiac magnetic resonance imaging, echocardiograms, computer tomography scans, and electrocardiographs, thus augmenting the clinicians' diagnostic accuracy of pediatric heart diseases. The use of AI-based prediction algorithms in pediatric cardiac surgeries improves postoperative outcomes and prognosis to a great extent. Risk stratification and the prediction of treatment outcomes are feasible using the key clinical findings of each CHD with appropriate computational algorithms. Notably, AI can revolutionize prenatal prediction as well as the diagnosis of CHD using the EMR (electronic medical records) data on maternal risk factors. The use of AI in the diagnostics, risk stratification, and management of CHD in the near future is a promising possibility with current advancements in machine learning and neural networks. However, the challenges posed by the dearth of appropriate algorithms and their nascent nature, limited physician training, fear of over-mechanization, and apprehension of missing the 'human touch' limit the acceptability. Still, AI proposes to aid the clinician tomorrow with precision cardiology, paving a way for extremely efficient human-error-free health care.
Collapse
Affiliation(s)
- Yashendra Sethi
- PearResearch, Dehradun 248001, India
- Department of Medicine, Government Doon Medical College, Dehradun 248001, India
| | - Neil Patel
- PearResearch, Dehradun 248001, India
- Department of Medicine, GMERS Medical College, Himmatnagar 383001, India
| | - Nirja Kaka
- PearResearch, Dehradun 248001, India
- Department of Medicine, GMERS Medical College, Himmatnagar 383001, India
| | - Ami Desai
- Department of Medicine, SMIMER Medical College, Surat 395010, India
| | - Oroshay Kaiwan
- PearResearch, Dehradun 248001, India
- Department of Medicine, Northeast Ohio Medical University, Rootstown, OH 44272, USA
- Correspondence: (O.K.); (Z.Y.H.); (T.B.E.)
| | - Mili Sheth
- Department of Medicine, GMERS Gandhinagar, Gandhinagar 382012, India
| | - Rupal Sharma
- Department of Medicine, Government Medical College, Nagpur 440003, India
| | - Helen Huang
- Faculty of Medicine and Health Science, Royal College of Surgeons in Ireland, D02 YN77 Dublin, Ireland
| | - Hitesh Chopra
- Chitkara College of Pharmacy, Chitkara University, Rajpura 140401, India
| | - Mayeen Uddin Khandaker
- Centre for Applied Physics and Radiation Technologies, School of Engineering and Technology, Sunway University, Bandar Sunway 47500, Malaysia
| | - Maha M. A. Lashin
- Department of Biomedical Engineering, College of Engineering, Princess Nourah bint Abdulrahman University, P.O. 84428, Riyadh 11671, Saudi Arabia
| | - Zuhal Y. Hamd
- Department of Radiological Sciences, College of Health and Rehabilitation Sciences, Princess Nourah bint Abdulrahman University, P.O. 84428, Riyadh 11671, Saudi Arabia
- Correspondence: (O.K.); (Z.Y.H.); (T.B.E.)
| | - Talha Bin Emran
- Department of Pharmacy, BGC Trust University Bangladesh, Chittagong 4381, Bangladesh
- Department of Pharmacy, Faculty of Allied Health Sciences, Daffodil International University, Dhaka 1207, Bangladesh
- Correspondence: (O.K.); (Z.Y.H.); (T.B.E.)
| |
Collapse
|
13
|
Garcia-Canadilla P, Isabel-Roquero A, Aurensanz-Clemente E, Valls-Esteve A, Miguel FA, Ormazabal D, Llanos F, Sanchez-de-Toledo J. Machine Learning-Based Systems for the Anticipation of Adverse Events After Pediatric Cardiac Surgery. Front Pediatr 2022; 10:930913. [PMID: 35832588 PMCID: PMC9271800 DOI: 10.3389/fped.2022.930913] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/28/2022] [Accepted: 06/06/2022] [Indexed: 11/18/2022] Open
Abstract
Pediatric congenital heart disease (CHD) patients are at higher risk of postoperative complications and clinical deterioration either due to their underlying pathology or due to the cardiac surgery, contributing significantly to mortality, morbidity, hospital and family costs, and poor quality of life. In current clinical practice, clinical deterioration is detected, in most of the cases, when it has already occurred. Several early warning scores (EWS) have been proposed to assess children at risk of clinical deterioration using vital signs and risk indicators, in order to intervene in a timely manner to reduce the impact of deterioration and risk of death among children. However, EWS are based on measurements performed at a single time point without incorporating trends nor providing information about patient's risk trajectory. Moreover, some of these measurements rely on subjective assessment making them susceptible to different interpretations. All these limitations could explain why the implementation of EWS in high-resource settings failed to show a significant decrease in hospital mortality. By means of machine learning (ML) based algorithms we could integrate heterogeneous and complex data to predict patient's risk of deterioration. In this perspective article, we provide a brief overview of the potential of ML technologies to improve the identification of pediatric CHD patients at high-risk for clinical deterioration after cardiac surgery, and present the CORTEX traffic light, a ML-based predictive system that Sant Joan de Déu Barcelona Children's Hospital is implementing, as an illustration of the application of an ML-based risk stratification system in a relevant hospital setting.
Collapse
Affiliation(s)
- Patricia Garcia-Canadilla
- BCNatal-Barcelona Center for Maternal-Fetal and Neonatal Medicine, Hospital Sant Joan de Déu and Hospital Clínic, University of Barcelona, Barcelona, Spain.,Cardiovascular Diseases and Child Development, Institut de Recerca Sant Joan de Déu, Esplugues de Llobregat, Spain
| | - Alba Isabel-Roquero
- Department of Pediatric Cardiology, Hospital Sant Joan de Déu Barcelona, Esplugues de Llobregat, Spain.,BCNMedTech, Universitat Pompeu Fabra, Barcelona, Spain
| | - Esther Aurensanz-Clemente
- Cardiovascular Diseases and Child Development, Institut de Recerca Sant Joan de Déu, Esplugues de Llobregat, Spain.,Department of Pediatric Cardiology, Hospital Sant Joan de Déu Barcelona, Esplugues de Llobregat, Spain
| | - Arnau Valls-Esteve
- Innovation in Health Technologies, Institut de Recerca Sant Joan de Déu, Esplugues de Llobregat, Spain
| | - Francesca Aina Miguel
- Department of Engineering, Hospital Sant Joan de Déu Barcelona, Esplugues de Llobregat, Spain
| | - Daniel Ormazabal
- Department of Informatics, Hospital Sant Joan de Déu Barcelona, Esplugues de Llobregat, Spain
| | - Floren Llanos
- Department of Informatics, Hospital Sant Joan de Déu Barcelona, Esplugues de Llobregat, Spain
| | - Joan Sanchez-de-Toledo
- Cardiovascular Diseases and Child Development, Institut de Recerca Sant Joan de Déu, Esplugues de Llobregat, Spain.,Department of Pediatric Cardiology, Hospital Sant Joan de Déu Barcelona, Esplugues de Llobregat, Spain.,Department of Critical Care Medicine, School of Medicine, University of Pittsburgh, Pittsburgh, PA, United States
| |
Collapse
|
14
|
Van den Eynde J, Kutty S, Danford DA, Manlhiot C. Artificial intelligence in pediatric cardiology: taking baby steps in the big world of data. Curr Opin Cardiol 2022; 37:130-136. [PMID: 34857721 DOI: 10.1097/hco.0000000000000927] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/25/2022]
Abstract
PURPOSE OF REVIEW Artificial intelligence (AI) has changed virtually every aspect of modern life, and medicine is no exception. Pediatric cardiology is both a perceptual and a cognitive subspecialty that involves complex decision-making, so AI is a particularly attractive tool for this medical discipline. This review summarizes the foundational work and incremental progress made as AI applications have emerged in pediatric cardiology since 2020. RECENT FINDINGS AI-based algorithms can be useful for pediatric cardiology in many areas, including: (1) clinical examination and diagnosis, (2) image processing, (3) planning and management of cardiac interventions, (4) prognosis and risk stratification, (5) omics and precision medicine, and (6) fetal cardiology. Most AI initiatives showcased in medical journals seem to work well in silico, but progress toward implementation in actual clinical practice has been more limited. Several barriers to implementation are identified, some encountered throughout medicine generally, and others specific to pediatric cardiology. SUMMARY Despite barriers to acceptance in clinical practice, AI is already establishing a durable role in pediatric cardiology. Its potential remains great, but to fully realize its benefits, substantial investment to develop and refine AI for pediatric cardiology applications will be necessary to overcome the challenges of implementation.
Collapse
Affiliation(s)
- Jef Van den Eynde
- The Blalock-Taussig-Thomas Pediatric and Congenital Heart Center, Department of Pediatrics, Johns Hopkins School of Medicine, Johns Hopkins University, Baltimore, Maryland, USA
- Department of Cardiovascular Sciences, KU Leuven & Congenital and Structural Cardiology, UZ Leuven, Leuven, Belgium
| | - Shelby Kutty
- The Blalock-Taussig-Thomas Pediatric and Congenital Heart Center, Department of Pediatrics, Johns Hopkins School of Medicine, Johns Hopkins University, Baltimore, Maryland, USA
| | - David A Danford
- The Blalock-Taussig-Thomas Pediatric and Congenital Heart Center, Department of Pediatrics, Johns Hopkins School of Medicine, Johns Hopkins University, Baltimore, Maryland, USA
| | - Cedric Manlhiot
- The Blalock-Taussig-Thomas Pediatric and Congenital Heart Center, Department of Pediatrics, Johns Hopkins School of Medicine, Johns Hopkins University, Baltimore, Maryland, USA
| |
Collapse
|
15
|
Van den Eynde J, Manlhiot C, Van De Bruaene A, Diller GP, Frangi AF, Budts W, Kutty S. Medicine-Based Evidence in Congenital Heart Disease: How Artificial Intelligence Can Guide Treatment Decisions for Individual Patients. Front Cardiovasc Med 2021; 8:798215. [PMID: 34926630 PMCID: PMC8674499 DOI: 10.3389/fcvm.2021.798215] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/19/2021] [Accepted: 11/09/2021] [Indexed: 01/06/2023] Open
Abstract
Built on the foundation of the randomized controlled trial (RCT), Evidence Based Medicine (EBM) is at its best when optimizing outcomes for homogeneous cohorts of patients like those participating in an RCT. Its weakness is a failure to resolve a clinical quandary: patients appear for care individually, each may differ in important ways from an RCT cohort, and the physician will wonder each time if following EBM will provide best guidance for this unique patient. In an effort to overcome this weakness, and promote higher quality care through a more personalized approach, a new framework has been proposed: Medicine-Based Evidence (MBE). In this approach, big data and deep learning techniques are embraced to interrogate treatment responses among patients in real-world clinical practice. Such statistical models are then integrated with mechanistic disease models to construct a “digital twin,” which serves as the real-time digital counterpart of a patient. MBE is thereby capable of dynamically modeling the effects of various treatment decisions in the context of an individual's specific characteristics. In this article, we discuss how MBE could benefit patients with congenital heart disease, a field where RCTs are difficult to conduct and often fail to provide definitive solutions because of a small number of subjects, their clinical complexity, and heterogeneity. We will also highlight the challenges that must be addressed before MBE can be embraced in clinical practice and its full potential can be realized.
Collapse
Affiliation(s)
- Jef Van den Eynde
- Department of Cardiovascular Sciences, KU Leuven and Congenital and Structural Cardiology, UZ Leuven, Leuven, Belgium.,Blalock-Taussig-Thomas Pediatric and Congenital Heart Center, The Johns Hopkins Hospital and School of Medicine, Johns Hopkins University, Baltimore, MD, United States
| | - Cedric Manlhiot
- Blalock-Taussig-Thomas Pediatric and Congenital Heart Center, The Johns Hopkins Hospital and School of Medicine, Johns Hopkins University, Baltimore, MD, United States
| | - Alexander Van De Bruaene
- Department of Cardiovascular Sciences, KU Leuven and Congenital and Structural Cardiology, UZ Leuven, Leuven, Belgium
| | - Gerhard-Paul Diller
- Department of Cardiology III-Adult Congenital and Valvular Heart Disease, University Hospital Muenster, Muenster, Germany
| | - Alejandro F Frangi
- Department of Cardiovascular Sciences, KU Leuven and Congenital and Structural Cardiology, UZ Leuven, Leuven, Belgium.,Centre for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), School of Computing and Medicine, University of Leeds, Leeds, United Kingdom.,Leeds Institute for Cardiovascular and Metabolic Medicine, Schools of Medicine, University of Leeds, Leeds, United Kingdom
| | - Werner Budts
- Department of Cardiovascular Sciences, KU Leuven and Congenital and Structural Cardiology, UZ Leuven, Leuven, Belgium
| | - Shelby Kutty
- Blalock-Taussig-Thomas Pediatric and Congenital Heart Center, The Johns Hopkins Hospital and School of Medicine, Johns Hopkins University, Baltimore, MD, United States
| |
Collapse
|
16
|
Ram Kumar S. Congenital Heart Surgery Report Cards…. World J Pediatr Congenit Heart Surg 2021; 13:36-37. [PMID: 34919484 DOI: 10.1177/21501351211064144] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Affiliation(s)
- S Ram Kumar
- 12223Keck School of Medicine of University of Southern California; Heart Institute, Children's Hospital, Los Angeles, CA, USA
| |
Collapse
|
17
|
Gimovsky AC, Zhuo D, Levine J, Dunn J, Amarm M, Peaceman A. Benchmarking Cesarean Delivery Rates using Machine Learning-Derived Optimal Classification Trees. Health Serv Res 2021; 57:796-805. [PMID: 34862801 PMCID: PMC9264474 DOI: 10.1111/1475-6773.13921] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2021] [Revised: 11/22/2021] [Accepted: 11/23/2021] [Indexed: 11/30/2022] Open
Abstract
OBJECTIVE To establish a case-adjusted hospital-specific performance evaluation tool using machine learning methodology for cesarean delivery. DATA SOURCES Secondary data were collected from patients between 1/1/2015-2/28/2018 using a hospital's "Electronic Data Warehouse" database from Illinois, USA. STUDY DESIGN The machine learning methodology of Optimal Classification Trees (OCT's) was used to predict cesarean delivery rate by physician group, thereby establishing the case-adjusted benchmarking standards in comparison to the overall hospital cesarean delivery rate. Outcomes of specific patient populations of each participating practice were predicted, as if each were treated in the overall hospital environment. The resulting OCTs estimate physician group expected cesarean delivery outcomes, both aggregate and in specific clinical situations. DATA COLLECTION/EXTRACTION METHODS 12,841 singleton, vertex, term deliveries, cared for by practices with ≥50 births. PRINCIPAL FINDINGS The overall rate of cesarean delivery was 18.6% (n = 2384), with a range of 13.3%-33.7% amongst 22 physician practices. An optimal decision tree was used to create a prediction model for the overall hospital which defined 23 patient cohorts, divided by 46 nodes. The model's performance for prediction of cesarean delivery is as follows: area under the curve- 0.73, sensitivity- 98.4%, specificity- 16.1%, positive predictive value 83.7%, negative predictive value 70.6%. Comparisons with the overall hospital's specific-case adjusted benchmark groups revealed that several groups outperformed the overall hospital and some practice groups underperformed in comparison to the overall hospital. CONCLUSIONS OCT benchmarking can assess physician practice specific case-adjusted performance, both overall and clinical situation specific, and can serve as a valuable tool for hospital self-assessment and quality improvement. This article is protected by copyright. All rights reserved.
Collapse
Affiliation(s)
- Alexis C Gimovsky
- Division of Maternal Fetal Medicine, Department of Obstetrics and Gynecology, Alpert Medical School of Brown University, Providence, Rhode Island, United States
| | - Daisy Zhuo
- Interpretable AI, One Broadway, Cambridge, Massachusetts, United States
| | - Jordan Levine
- Alexandria Health, Providence, Rhode Island, United States
| | - Jack Dunn
- Interpretable AI, One Broadway, Cambridge, Massachusetts, United States
| | - Maxime Amarm
- Interpretable AI, One Broadway, Cambridge, Massachusetts, United States
| | - Alan Peaceman
- Division of Maternal Fetal Medicine, Department of Obstetrics and Gynecology, Northwestern University Feinberg School of Medicine, Chicago, Illinois, United States
| |
Collapse
|
18
|
Bertsimas D, Zhuo D, Levine J, Dunn J, Tobota Z, Maruszewski B, Fragata J, Sarris GE. Benchmarking in Congenital Heart Surgery Using Machine Learning-Derived Optimal Classification Trees. World J Pediatr Congenit Heart Surg 2021; 13:23-35. [PMID: 34783609 DOI: 10.1177/21501351211051227] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Background: We have previously shown that the machine learning methodology of optimal classification trees (OCTs) can accurately predict risk after congenital heart surgery (CHS). We have now applied this methodology to define benchmarking standards after CHS, permitting case-adjusted hospital-specific performance evaluation. Methods: The European Congenital Heart Surgeons Association Congenital Database data subset (31 792 patients) who had undergone any of the 10 "benchmark procedure group" primary procedures were analyzed. OCT models were built predicting hospital mortality (HM), and prolonged postoperative mechanical ventilatory support time (MVST) or length of hospital stay (LOS), thereby establishing case-adjusted benchmarking standards reflecting the overall performance of all participating hospitals, designated as the "virtual hospital." These models were then used to predict individual hospitals' expected outcomes (both aggregate and, importantly, for risk-matched patient cohorts) for their own specific cases and case-mix, based on OCT analysis of aggregate data from the "virtual hospital." Results: The raw average rates were HM = 4.4%, MVST = 15.3%, and LOS = 15.5%. Of 64 participating centers, in comparison with each hospital's specific case-adjusted benchmark, 17.0% statistically (under 90% confidence intervals) overperformed and 26.4% underperformed with respect to the predicted outcomes for their own specific cases and case-mix. For MVST and LOS, overperformers were 34.0% and 26.4%, and underperformers were 28.3% and 43.4%, respectively. OCT analyses reveal hospital-specific patient cohorts of either overperformance or underperformance. Conclusions: OCT benchmarking analysis can assess hospital-specific case-adjusted performance after CHS, both overall and patient cohort-specific, serving as a tool for hospital self-assessment and quality improvement.
Collapse
Affiliation(s)
- Dimitris Bertsimas
- Operations Research Center and Sloan School of Management, 2167Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Daisy Zhuo
- Alexandria Health, Cambridge, MA, USA.,Alexandria Health, Providence, RI, USA
| | - Jordan Levine
- Alexandria Health, Cambridge, MA, USA.,Alexandria Health, Providence, RI, USA
| | - Jack Dunn
- Alexandria Health, Cambridge, MA, USA.,Alexandria Health, Providence, RI, USA
| | | | | | - Jose Fragata
- Hospital de Santa Marta and NOVA University, Lisbon, Portugal
| | | |
Collapse
|
19
|
Kumar SR. Does It Measure Up? World J Pediatr Congenit Heart Surg 2021; 12:461-462. [PMID: 34278858 DOI: 10.1177/21501351211020709] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
Measuring outcomes in pediatric cardiac care has been one of the more widespread, and at the same time controversial and often polarizing, quality improvement initiatives undertaken in the medical field. Risk models, such as the Society of Thoracic Surgeons Congenital Heart Surgery Risk Model, have been developed to account for comorbidities while predicting the expected mortality for a given surgical encounter. In this issue of the journal, Bertsimas and colleagues report on machine learning approaches to predict adverse outcomes in congenital heart surgery using the European Congenital Heart Surgeons Association's congenital database. A head-to-head comparison of machine learning models and the currently available risk models utilizing the same data set are required to better understand the strengths and weaknesses of each of these approaches. Such a focused analysis will shed light on future approaches for risk modeling, which will undoubtedly continue to benefit from the guidance provided by expert clinical intuition.
Collapse
Affiliation(s)
- S Ram Kumar
- Division of Cardiac Surgery, Department of Surgery, 12223Keck School of Medicine of University of Southern California, Los Angeles, CA, USA.,Department of Pediatrics, 12223Keck School of Medicine of University of Southern California, Los Angeles, CA, USA.,Heart Institute, Children's Hospital, Los Angeles, CA, USA
| |
Collapse
|