1
|
Mahbub M, Goethert I, Danciu I, Knight K, Srinivasan S, Tamang S, Rozenberg-Ben-Dror K, Solares H, Martins S, Trafton J, Begoli E, Peterson GD. Question-answering system extracts information on injection drug use from clinical notes. Commun Med (Lond) 2024; 4:61. [PMID: 38570620 PMCID: PMC10991373 DOI: 10.1038/s43856-024-00470-6] [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] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2023] [Accepted: 02/29/2024] [Indexed: 04/05/2024] Open
Abstract
BACKGROUND Injection drug use (IDU) can increase mortality and morbidity. Therefore, identifying IDU early and initiating harm reduction interventions can benefit individuals at risk. However, extracting IDU behaviors from patients' electronic health records (EHR) is difficult because there is no other structured data available, such as International Classification of Disease (ICD) codes, and IDU is most often documented in unstructured free-text clinical notes. Although natural language processing can efficiently extract this information from unstructured data, there are no validated tools. METHODS To address this gap in clinical information, we design a question-answering (QA) framework to extract information on IDU from clinical notes for use in clinical operations. Our framework involves two main steps: (1) generating a gold-standard QA dataset and (2) developing and testing the QA model. We use 2323 clinical notes of 1145 patients curated from the US Department of Veterans Affairs (VA) Corporate Data Warehouse to construct the gold-standard dataset for developing and evaluating the QA model. We also demonstrate the QA model's ability to extract IDU-related information from temporally out-of-distribution data. RESULTS Here, we show that for a strict match between gold-standard and predicted answers, the QA model achieves a 51.65% F1 score. For a relaxed match between the gold-standard and predicted answers, the QA model obtains a 78.03% F1 score, along with 85.38% Precision and 79.02% Recall scores. Moreover, the QA model demonstrates consistent performance when subjected to temporally out-of-distribution data. CONCLUSIONS Our study introduces a QA framework designed to extract IDU information from clinical notes, aiming to enhance the accurate and efficient detection of people who inject drugs, extract relevant information, and ultimately facilitate informed patient care.
Collapse
Affiliation(s)
- Maria Mahbub
- Cyber Resilience and Intelligence Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA.
| | - Ian Goethert
- Information Technology Services Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA
| | - Ioana Danciu
- Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA
- Department of Biomedical Informatics, Vanderbilt University, Nashville, TN, USA
| | - Kathryn Knight
- Information Technology Services Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA
| | - Sudarshan Srinivasan
- Cyber Resilience and Intelligence Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA
| | - Suzanne Tamang
- Program Evaluation and Resource Center, Office of Mental Health and Suicide Prevention, Department of Veterans Affairs, Menlo Park, CA, USA
- Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA
| | | | - Hugo Solares
- Program Evaluation and Resource Center, Office of Mental Health and Suicide Prevention, Department of Veterans Affairs, Menlo Park, CA, USA
| | - Susana Martins
- Program Evaluation and Resource Center, Office of Mental Health and Suicide Prevention, Department of Veterans Affairs, Menlo Park, CA, USA
| | - Jodie Trafton
- Program Evaluation and Resource Center, Office of Mental Health and Suicide Prevention, Department of Veterans Affairs, Menlo Park, CA, USA
| | - Edmon Begoli
- Cyber Resilience and Intelligence Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA
| | - Gregory D Peterson
- Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville, Knoxville, TN, USA
| |
Collapse
|
2
|
Justice AC, Tate JP, Howland F, Gaziano JM, Kelley MJ, McMahon B, Haiman C, Wadia R, Madduri R, Danciu I, Leppert JT, Leapman MS, Thurtle D, Gnanapragasam VJ. Adaption and National Validation of a Tool for Predicting Mortality from Other Causes Among Men with Nonmetastatic Prostate Cancer. Eur Urol Oncol 2024:S2588-9311(23)00289-4. [PMID: 38171965 DOI: 10.1016/j.euo.2023.11.023] [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: 06/26/2023] [Revised: 10/24/2023] [Accepted: 11/30/2023] [Indexed: 01/05/2024]
Abstract
BACKGROUND An electronic health record-based tool could improve accuracy and eliminate bias in provider estimation of the risk of death from other causes among men with nonmetastatic cancer. OBJECTIVE To recalibrate and validate the Veterans Aging Cohort Study Charlson Comorbidity Index (VACS-CCI) to predict non-prostate cancer mortality (non-PCM) and to compare it with a tool predicting prostate cancer mortality (PCM). DESIGN, SETTING, AND PARTICIPANTS An observational cohort of men with biopsy-confirmed nonmetastatic prostate cancer, enrolled from 2001 to 2018 in the national US Veterans Health Administration (VA), was divided by the year of diagnosis into the development (2001-2006 and 2008-2018) and validation (2007) sets. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS Mortality (all cause, non-PCM, and PCM) was evaluated. Accuracy was assessed using calibration curves and C statistic in the development, validation, and combined sets; overall; and by age (<65 and 65+ yr), race (White and Black), Hispanic ethnicity, and treatment groups. RESULTS AND LIMITATIONS Among 107 370 individuals, we observed 24 977 deaths (86% non-PCM). The median age was 65 yr, 4947 were Black, and 5010 were Hispanic. Compared with CCI and age alone (C statistic 0.67, 95% confidence interval [CI] 0.67-0.68), VACS-CCI demonstrated improved validated discrimination (C statistic 0.75, 95% CI 0.74-0.75 for non-PCM). The prostate cancer mortality tool also discriminated well in validation (C statistic 0.81, 95% CI 0.78-0.83). Both were well calibrated overall and within subgroups. Owing to missing data, 18 009/125 379 (14%) were excluded, and VACS-CCI should be validated outside the VA prior to outside application. CONCLUSIONS VACS-CCI is ready for implementation within the VA. Electronic health record-assisted calculation is feasible, improves accuracy over age and CCI alone, and could mitigate inaccuracy and bias in provider estimation. PATIENT SUMMARY Veterans Aging Cohort Study Charlson Comorbidity Index is ready for application within the Veterans Health Administration. Electronic health record-assisted calculation is feasible, improves accuracy over age and Charlson Comorbidity Index alone, and might help mitigate inaccuracy and bias in provider estimation of the risk of non-prostate cancer mortality.
Collapse
Affiliation(s)
- Amy C Justice
- VA Connecticut Healthcare, West Haven, CT, USA; Pain Research, Informatics, Multimorbidities, Education (PRIME) Center, VA Connecticut Healthcare System, West Haven, CT, USA; Department of Medicine, Yale School of Medicine, New Haven, CT, USA; School of Public Health, Yale University, New Haven, CT, USA.
| | - Janet P Tate
- VA Connecticut Healthcare, West Haven, CT, USA; Department of Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Frank Howland
- Wabash College Economics Department, Crawfordsville, IN, USA
| | | | - Michael J Kelley
- Durham VA Health Care System, Durham, NC, USA; Cancer Institute and Department of Medicine, Duke University, Durham, NC, USA
| | | | - Christopher Haiman
- Center for Genetic Epidemiology, USC Keck School of Medicine, University of Southern California, Los Angeles, CA, USA
| | - Roxanne Wadia
- Department of Anatomic Pathology and Lab Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Ravi Madduri
- Data Science Learning Division, Argonne Research Library, Lemont, IL, USA
| | - Ioana Danciu
- Oak Ridge National Laboratory, Oak Ridge, TN, USA; Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, USA
| | - John T Leppert
- Department of Urology, Stanford University, Stanford, CA, USA; VA Palo Alto Health Care System, Palo Alto, CA, USA
| | - Michael S Leapman
- VA Connecticut Healthcare, West Haven, CT, USA; Department of Urology, Yale School of Medicine, New Haven, CT, USA
| | | | | |
Collapse
|
3
|
Peluso A, Danciu I, Yoon HJ, Yusof JM, Bhattacharya T, Spannaus A, Schaefferkoetter N, Durbin EB, Wu XC, Stroup A, Doherty J, Schwartz S, Wiggins C, Coyle L, Penberthy L, Tourassi GD, Gao S. Deep learning uncertainty quantification for clinical text classification. J Biomed Inform 2024; 149:104576. [PMID: 38101690 DOI: 10.1016/j.jbi.2023.104576] [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] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2023] [Revised: 12/06/2023] [Accepted: 12/10/2023] [Indexed: 12/17/2023]
Abstract
INTRODUCTION Machine learning algorithms are expected to work side-by-side with humans in decision-making pipelines. Thus, the ability of classifiers to make reliable decisions is of paramount importance. Deep neural networks (DNNs) represent the state-of-the-art models to address real-world classification. Although the strength of activation in DNNs is often correlated with the network's confidence, in-depth analyses are needed to establish whether they are well calibrated. METHOD In this paper, we demonstrate the use of DNN-based classification tools to benefit cancer registries by automating information extraction of disease at diagnosis and at surgery from electronic text pathology reports from the US National Cancer Institute (NCI) Surveillance, Epidemiology, and End Results (SEER) population-based cancer registries. In particular, we introduce multiple methods for selective classification to achieve a target level of accuracy on multiple classification tasks while minimizing the rejection amount-that is, the number of electronic pathology reports for which the model's predictions are unreliable. We evaluate the proposed methods by comparing our approach with the current in-house deep learning-based abstaining classifier. RESULTS Overall, all the proposed selective classification methods effectively allow for achieving the targeted level of accuracy or higher in a trade-off analysis aimed to minimize the rejection rate. On in-distribution validation and holdout test data, with all the proposed methods, we achieve on all tasks the required target level of accuracy with a lower rejection rate than the deep abstaining classifier (DAC). Interpreting the results for the out-of-distribution test data is more complex; nevertheless, in this case as well, the rejection rate from the best among the proposed methods achieving 97% accuracy or higher is lower than the rejection rate based on the DAC. CONCLUSIONS We show that although both approaches can flag those samples that should be manually reviewed and labeled by human annotators, the newly proposed methods retain a larger fraction and do so without retraining-thus offering a reduced computational cost compared with the in-house deep learning-based abstaining classifier.
Collapse
Affiliation(s)
- Alina Peluso
- Oak Ridge National Laboratory, Oak Ridge, TN 37830, United States.
| | - Ioana Danciu
- Oak Ridge National Laboratory, Oak Ridge, TN 37830, United States
| | - Hong-Jun Yoon
- Oak Ridge National Laboratory, Oak Ridge, TN 37830, United States
| | | | | | - Adam Spannaus
- Oak Ridge National Laboratory, Oak Ridge, TN 37830, United States
| | | | - Eric B Durbin
- University of Kentucky, Lexington, KY 40536, United States
| | - Xiao-Cheng Wu
- Louisiana State University, New Orleans, LA 70112, United States
| | - Antoinette Stroup
- Rutgers Cancer Institute of New Jersey, New Brunswick, NJ 08901, United States
| | | | - Stephen Schwartz
- Fred Hutchinson Cancer Research Center, Seattle, WA 98109, United States
| | - Charles Wiggins
- University of New Mexico, Albuquerque, NM 87131, United States
| | - Linda Coyle
- Information Management Services Inc., Calverton, MD 20705, United States
| | - Lynne Penberthy
- National Cancer Institute, Bethesda, MD 20814, United States
| | | | - Shang Gao
- Oak Ridge National Laboratory, Oak Ridge, TN 37830, United States
| |
Collapse
|
4
|
Haque MIU, Dubey AK, Danciu I, Justice AC, Ovchinnikova OS, Hinkle JD. Effect of image resolution on automated classification of chest X-rays. J Med Imaging (Bellingham) 2023; 10:044503. [PMID: 37547812 PMCID: PMC10403240 DOI: 10.1117/1.jmi.10.4.044503] [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] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2023] [Revised: 07/09/2023] [Accepted: 07/21/2023] [Indexed: 08/08/2023] Open
Abstract
Purpose Deep learning (DL) models have received much attention lately for their ability to achieve expert-level performance on the accurate automated analysis of chest X-rays (CXRs). Recently available public CXR datasets include high resolution images, but state-of-the-art models are trained on reduced size images due to limitations on graphics processing unit memory and training time. As computing hardware continues to advance, it has become feasible to train deep convolutional neural networks on high-resolution images without sacrificing detail by downscaling. This study examines the effect of increased resolution on CXR classification performance. Approach We used the publicly available MIMIC-CXR-JPG dataset, comprising 377,110 high resolution CXR images for this study. We applied image downscaling from native resolution to 2048 × 2048 pixels , 1024 × 1024 pixels , 512 × 512 pixels , and 256 × 256 pixels and then we used the DenseNet121 and EfficientNet-B4 DL models to evaluate clinical task performance using these four downscaled image resolutions. Results We find that while some clinical findings are more reliably labeled using high resolutions, many other findings are actually labeled better using downscaled inputs. We qualitatively verify that tasks requiring a large receptive field are better suited to downscaled low resolution input images, by inspecting effective receptive fields and class activation maps of trained models. Finally, we show that stacking an ensemble across resolutions outperforms each individual learner at all input resolutions while providing interpretable scale weights, indicating that diverse information is extracted across resolutions. Conclusions This study suggests that instead of focusing solely on the finest image resolutions, multi-scale features should be emphasized for information extraction from high-resolution CXRs.
Collapse
Affiliation(s)
- Md Inzamam Ul Haque
- University of Tennessee, The Bredesen Center, Knoxville, Tennessee, United States
| | - Abhishek K. Dubey
- Oak Ridge National Laboratory, Computational Sciences and Engineering Division, Oak Ridge, Tennessee, United States
| | - Ioana Danciu
- Oak Ridge National Laboratory, Computational Sciences and Engineering Division, Oak Ridge, Tennessee, United States
| | - Amy C. Justice
- VA Connecticut Healthcare, West Haven, Connecticut, United States
- VA Connecticut Healthcare System, Pain Research, Informatics, Multimorbidities, Education (PRIME) Center, West Haven, Connecticut, United States
- Yale School of Medicine, Department of Medicine, New Haven, Connecticut, United States
- Yale University, School of Public Health, New Haven, Connecticut, United States
| | - Olga S. Ovchinnikova
- University of Tennessee, The Bredesen Center, Knoxville, Tennessee, United States
- Oak Ridge National Laboratory, Computational Sciences and Engineering Division, Oak Ridge, Tennessee, United States
- University of Tennessee, Materials Science and Engineering, Knoxville, Tennessee, United States
| | - Jacob D. Hinkle
- Oak Ridge National Laboratory, Computational Sciences and Engineering Division, Oak Ridge, Tennessee, United States
| |
Collapse
|
5
|
Danciu I, Agasthya G, Tate JP, Chandra-Shekar M, Goethert I, Ovchinnikova OS, McMahon BH, Justice AC. In with the old, in with the new: machine learning for time to event biomedical research. J Am Med Inform Assoc 2022; 29:1737-1743. [PMID: 35920306 PMCID: PMC9471708 DOI: 10.1093/jamia/ocac106] [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: 12/28/2021] [Revised: 05/01/2022] [Accepted: 07/29/2022] [Indexed: 11/13/2022] Open
Abstract
The predictive modeling literature for biomedical applications is dominated by biostatistical methods for survival analysis, and more recently some out of the box machine learning approaches. In this article, we show a presentation of a machine learning method appropriate for time-to-event modeling in the area of prostate cancer long-term disease progression. Using XGBoost adapted to long-term disease progression, we developed a predictive model for 118 788 patients with localized prostate cancer at diagnosis from the Department of Veterans Affairs (VA). Our model accounted for patient censoring. Harrell's c-index for our model using only features available at the time of diagnosis was 0.757 95% confidence interval [0.756, 0.757]. Our results show that machine learning methods like XGBoost can be adapted to use accelerated failure time (AFT) with censoring to model long-term risk of disease progression. The long median survival justifies and requires censoring. Overall, we show that an existing machine learning approach can be used for AFT outcome modeling in prostate cancer, and more generally for other chronic diseases with long observation times.
Collapse
Affiliation(s)
- Ioana Danciu
- Corresponding Author: Ioana Danciu, Advanced Computing for Health Sciences Group, Oak Ridge National Laboratory, 1 Bethel Valley Road, Building 5700, Oak Ridge, TN 37830, USA;
| | - Greeshma Agasthya
- Advanced Computing for Health Sciences Group, Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA
| | - Janet P Tate
- Department of Veterans Affairs Connecticut Healthcare System, West Haven, Connecticut, USA
- Yale School of Medicine, New Haven, Connecticut, USA
| | - Mayanka Chandra-Shekar
- Advanced Computing for Health Sciences Group, Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA
| | - Ian Goethert
- Advanced Computing for Health Sciences Group, Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA
| | - Olga S Ovchinnikova
- Advanced Computing for Health Sciences Group, Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA
| | - Benjamin H McMahon
- Theoretical Biology Group, Los Alamos National Laboratory, Los Alamos, New Mexico, USA
| | - Amy C Justice
- Department of Veterans Affairs Connecticut Healthcare System, West Haven, Connecticut, USA
- Yale School of Medicine, New Haven, Connecticut, USA
- Yale School of Public Health, New Haven, Connecticut, USA
| |
Collapse
|
6
|
Kim M, Huffman JE, Justice A, Goethert I, Agasthya G, Danciu I. Identifying intragenic functional modules of genomic variations associated with cancer phenotypes by learning representation of association networks. BMC Med Genomics 2022; 15:151. [PMID: 35794577 PMCID: PMC9258200 DOI: 10.1186/s12920-022-01298-6] [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] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2022] [Accepted: 06/14/2022] [Indexed: 11/27/2022] Open
Abstract
BACKGROUND Genome-wide Association Studies (GWAS) aims to uncover the link between genomic variation and phenotype. They have been actively applied in cancer biology to investigate associations between variations and cancer phenotypes, such as susceptibility to certain types of cancer and predisposed responsiveness to specific treatments. Since GWAS primarily focuses on finding associations between individual genomic variations and cancer phenotypes, there are limitations in understanding the mechanisms by which cancer phenotypes are cooperatively affected by more than one genomic variation. RESULTS This paper proposes a network representation learning approach to learn associations among genomic variations using a prostate cancer cohort. The learned associations are encoded into representations that can be used to identify functional modules of genomic variations within genes associated with early- and late-onset prostate cancer. The proposed method was applied to a prostate cancer cohort provided by the Veterans Administration's Million Veteran Program to identify candidates for functional modules associated with early-onset prostate cancer. The cohort included 33,159 prostate cancer patients, 3181 early-onset patients, and 29,978 late-onset patients. The reproducibility of the proposed approach clearly showed that the proposed approach can improve the model performance in terms of robustness. CONCLUSIONS To our knowledge, this is the first attempt to use a network representation learning approach to learn associations among genomic variations within genes. Associations learned in this way can lead to an understanding of the underlying mechanisms of how genomic variations cooperatively affect each cancer phenotype. This method can reveal unknown knowledge in the field of cancer biology and can be utilized to design more advanced cancer-targeted therapies.
Collapse
Affiliation(s)
- Minsu Kim
- grid.135519.a0000 0004 0446 2659Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN USA
| | - Jennifer E. Huffman
- grid.410370.10000 0004 4657 1992Center for Population Genomics, MAVERIC, VA Boston Healthcare System, Jamaica Plain, MA USA
- grid.410370.10000 0004 4657 1992Massachusetts Veterans Epidemiology Research and Information Center, Veterans Affairs Boston Healthcare System, Boston, MA USA
| | - Amy Justice
- grid.281208.10000 0004 0419 3073Department of Veterans Affairs Connecticut Healthcare System, West Haven, CT USA
- grid.47100.320000000419368710Yale School of Medicine, New Haven, CT USA
| | - Ian Goethert
- grid.135519.a0000 0004 0446 2659Information Technology Services Division, Oak Ridge National Laboratory, Oak Ridge, TN USA
| | - Greeshma Agasthya
- grid.135519.a0000 0004 0446 2659Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN USA
| | | | - Ioana Danciu
- grid.135519.a0000 0004 0446 2659Advanced Computing for Health Sciences Group, Oak Ridge National Laboratory, Oak Ridge, TN USA
- grid.152326.10000 0001 2264 7217Department of Biomedical Informatics, Vanderbilt University, Nashville, TN USA
| |
Collapse
|
7
|
Gerlovin H, Posner DC, Ho YL, Rentsch CT, Tate JP, King JT, Kurgansky KE, Danciu I, Costa L, Linares FA, Goethert ID, Jacobson DA, Freiberg MS, Begoli E, Muralidhar S, Ramoni RB, Tourassi G, Gaziano JM, Justice AC, Gagnon DR, Cho K. Pharmacoepidemiology, Machine Learning, and COVID-19: An Intent-to-Treat Analysis of Hydroxychloroquine, With or Without Azithromycin, and COVID-19 Outcomes Among Hospitalized US Veterans. Am J Epidemiol 2021; 190:2405-2419. [PMID: 34165150 PMCID: PMC8384407 DOI: 10.1093/aje/kwab183] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2020] [Revised: 06/03/2021] [Accepted: 06/17/2021] [Indexed: 12/11/2022] Open
Abstract
Hydroxychloroquine (HCQ) was proposed as an early therapy for coronavirus disease
2019 (COVID-19) after in vitro studies indicated possible
benefit. Previous in vivo observational studies have presented
conflicting results, though recent randomized clinical trials have reported no
benefit from HCQ amongst hospitalized COVID-19 patients. We examined the effects
of HCQ alone, and in combination with azithromycin, in a hospitalized COVID-19
positive, United States (US) Veteran population using a propensity score
adjusted survival analysis with imputation of missing data. From March 1, 2020
through April 30, 2020, 64,055 US Veterans were tested for COVID-19 based on
Veteran Affairs Healthcare Administration electronic health record data. Of the
7,193 positive cases, 2,809 were hospitalized, and 657 individuals were
prescribed HCQ within the first 48-hours of hospitalization for the treatment of
COVID-19. There was no apparent benefit associated with HCQ receipt, alone or in
combination with azithromycin, and an increased risk of intubation when used in
combination with azithromycin [Hazard Ratio (95% Confidence Interval):
1.55 (1.07, 2.24)]. In conclusion, we assessed the effectiveness of HCQ with or
without azithromycin in treating patients hospitalized with COVID-19 using a
national sample of the US Veteran population. Using rigorous study design and
analytic methods to reduce confounding and bias, we found no evidence of a
survival benefit from the administration of HCQ.
Collapse
|
8
|
Knight KE, Honerlaw J, Danciu I, Linares F, Ho YL, Gagnon DR, Rush E, Gaziano JM, Begoli E, Cho K. Standardized Architecture for a Mega-Biobank Phenomic Library: The Million Veteran Program (MVP). AMIA Jt Summits Transl Sci Proc 2020; 2020:326-334. [PMID: 32477652 PMCID: PMC7233040] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
Electronic health records (EHRs) provide a wealth of data for phenotype development in population health studies, and researchers invest considerable time to curate data elements and validate disease definitions. The ability to reproduce well-defined phenotypes increases data quality, comparability of results and expedites research. In this paper, we present a standardized approach to organize and capture phenotype definitions, resulting in the creation of an open, online repository of phenotypes. This resource captures phenotype development, provenance and process from the Million Veteran Program, a national mega-biobank embedded in the Veterans Health Administration (VHA). To ensure that the repository is searchable, extendable, and sustainable, it is necessary to develop both a proper digital catalog architecture and underlying metadata infrastructure to enable effective management of the data fields required to define each phenotype. Our methods provide a resource for VHA investigators and a roadmap for researchers interested in standardizing their phenotype definitions to increase portability.
Collapse
Affiliation(s)
| | - Jacqueline Honerlaw
- Division of Population Health and Data Science, Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC), VA Boston Healthcare System, Boston, MA
| | | | | | - Yuk-Lam Ho
- Division of Population Health and Data Science, Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC), VA Boston Healthcare System, Boston, MA
| | - David R Gagnon
- Division of Population Health and Data Science, Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC), VA Boston Healthcare System, Boston, MA
- Department of Biostatistics, Boston University School of Public Health, Boston, MA
| | | | - J Michael Gaziano
- Division of Population Health and Data Science, Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC), VA Boston Healthcare System, Boston, MA
- Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA
| | | | - Kelly Cho
- Division of Population Health and Data Science, Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC), VA Boston Healthcare System, Boston, MA
- Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA
| |
Collapse
|
9
|
Rush EN, Danciu I, Ostrouchov G, Cho K, Mayer BW, Ho YL, Honerlaw J, Costa L, Linares F, Begoli E. JSONize: A Scalable Machine Learning Pipeline to Model Medical Notes as Semi-structured Documents. AMIA Jt Summits Transl Sci Proc 2020; 2020:533-541. [PMID: 32477675 PMCID: PMC7233081] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
The Department of Veteran's Affairs (VA) archives one of the largest corpora of clinical notes in their corporate data warehouse as unstructured text data. Unstructured text easily supports keyword searches and regular expressions. Often these simple searches do not adequately support the complex searches that need to be performed on notes. For example, a researcher may want all notes with a Duke Treadmill Score of less than five or people that smoke more than one pack per day. Range queries like this and more can be supported by modelling text as semi-structured documents. In this paper, we implement a scalable machine learning pipeline that models plain medical text as useful semi-structured documents. We improve on existing models and achieve an F1-score of 0.912 and scale our methods to the entire VA corpus.
Collapse
Affiliation(s)
| | | | | | - Kelly Cho
- Division of Population Health and Data Sciences, MAVERIC, VA Boston Healthcare System, Boston, MA, USA
- Department of Medicine, Harvard Medical School Division of Aging, Brigham and Womens Hospital, Boston, MA, USA
| | | | - Yuk-Lam Ho
- Division of Population Health and Data Sciences, MAVERIC, VA Boston Healthcare System, Boston, MA, USA
| | - Jacqueline Honerlaw
- Division of Population Health and Data Sciences, MAVERIC, VA Boston Healthcare System, Boston, MA, USA
| | | | | | | |
Collapse
|
10
|
McMahon B, Dhaubhadel S, Hengartner N, Danciu I, Janet T, Justice A. Model selection applied to 750 outpatient ICD-9 codes identifies hazards important for all-cause cancer mortality in 2 million veterans with 14 years of follow-up. J Clin Oncol 2020. [DOI: 10.1200/jco.2020.38.15_suppl.2053] [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] [Subscribe] [Scholar Register] [Indexed: 11/20/2022] Open
Abstract
2053 Background: Cost-benefit analysis before undergoing cancer treatments can involve a broad array of factors, yet existing statistical algorithms are limited to a few of the most commonly observed competing risks. Using 20 years of Veteran medical records from the Veteran’s Administration, we identify a broad array of outpatient descriptors providing contributions to computed mortality comparable in size to common cancers. Methods: 1,911,632 Veterans born between 1927 and 1968 with medical records extending from October 1, 2000 until either recorded death after October 1, 2005 (47%) or observation during CY 2019 were split equally into age-matched test and training sets. The 20 year-long record was split into three intervals: 5 years during which ICD codes were tallied, 14 years of waiting, and establishment of continuation in care during 2019. The 750 most common outpatient ICD9 codes were recorded as present/absent for each patient and used in a generalized linear model to predict subsequent mortality, subject to LASSO model selection and 10-fold cross validation. Gender was included as a covariate as well as age at time of prediction, up to the 4th power. Results: The C-statistic for predicting mortality in 14 years of follow-up was 0.835 on training data and 0.833 on test data when using the 498 codes selected by LASSO. Prevalent codes with the largest model coefficients were (ICD 9 code: model coefficient, # alive/# deceased in test set) congestive heart failure (428.0: 0.66, 9k/48k), chronic airway obstruction (496.: 0.60, 42k/105k), and tobacco use disorder (305.1: 0.54, 107k/123k), while the prevalent codes most protective in comparison to baseline were hyperlipidemia (272.4: -0.21, 211k/225k) and colon cancer screening (V76.51: -0.16, 49k/39k). In comparison, observed cancer ICD 9 coefficients were lung (162.9: 1.03, 1k/7k), colon (153.9: 0.18, 3.1k/7.0k), and prostate (185.: 0.06, 16k/32k). 74 predictors contribute with coefficients greater than colon cancers, such as ‘no household member able to render care’ (V60.4: 0.28, 1.1k/4.2k). Conclusions: A wide variety of structured data contribute at a similar level of importance in prediction of 14-year mortality. While various selection biases, co-linearity of predictors, differences in treatments, and missing data are significant impediments to utilization of predictive models in clinical practice, we have demonstrated an ability to identify and quantify predictors from a large data set with model selection techniques.
Collapse
Affiliation(s)
| | | | | | | | | | - Amy Justice
- Yale University School of Medicine, New Haven, CT
| |
Collapse
|
11
|
Janet T, Danciu I, Justice A, Leapman M, McMahon B, Wadia R. Predicting prostate cancer death among 98,994 veterans: Differences by race/ethnicity. J Clin Oncol 2020. [DOI: 10.1200/jco.2020.38.15_suppl.e17609] [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] [Subscribe] [Scholar Register] [Indexed: 11/20/2022] Open
Abstract
e17609 Background: Prostate cancer mortality is higher in Blacks than Whites, but existing prognostic indices fail to account for race/ethnicity. Using data from the national U.S. Veterans Affairs Healthcare System (VA), we compared prediction of prostate cancer death by race/ethnicity. Methods: Men with biopsy confirmed prostate cancer from 2002-2016 were included. We excluded those with lymph node or distant metastatic disease at diagnosis and those not classified as Non-Hispanic White (NHW), Non-Hispanic Black (NHB), or Hispanic (HSP). We set aside 20% for future validation. Cox models estimated hazard ratios (HR) for prostate cancer death, stratified by age and race/ethnicity. Each was adjusted for age, Gleason score, tumor (T) stage, PSA at diagnosis, and calendar year. Results: Among 98,994 veterans with localized disease, 64% were NHW, 30% were NHB, and 6% were HSP. At diagnosis, median age differed by race/ethnicity (NHW 66 [IQR 62-71] yrs.; NHB 63 [58-68] yrs.; HSP 66 [61-73] yrs.). During follow-up 23,316 men died, 3484 (15% overall, and by race/ethnicity) by prostate cancer. Among those < 65 yrs at diagnosis, HR for Gleason score were much stronger among NHW than NHB; associations for PSA level were stronger among NHB than NHW. HRs for HSP and NHW were similar. T stage HRs were similar by age and race/ethnicity. Conclusions: Risk associated with Gleason score and PSA varied by age and race/ethnicity. Prognostic models for prostate cancer disease progression must be evaluated in diverse populations and across age strata. [Table: see text]
Collapse
Affiliation(s)
| | | | - Amy Justice
- Yale University School of Medicine, New Haven, CT
| | - Michael Leapman
- Department of Urology, Yale School of Medicine, New Haven, CT
| | | | | |
Collapse
|
12
|
Danciu I, Erwin S, Agasthya G, Janet T, McMahon B, Tourassi G, Justice A. Using longitudinal PSA values and machine learning for predicting progression of early stage prostate cancer in veterans. J Clin Oncol 2020. [DOI: 10.1200/jco.2020.38.15_suppl.e17554] [Citation(s) in RCA: 3] [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] [Subscribe] [Scholar Register] [Indexed: 11/20/2022] Open
Abstract
e17554 Background: The ability to understand and predict at the time of diagnosis the trajectories of prostate cancer patients is critical for deciding the appropriate treatment plan. Evidence-based approaches for outcome prediction include predictive machine learning algorithms that harness health record data. Methods: All our analyses used the Veterans Affairs Clinical Data Warehouse (CDW). We included all individuals with a non-metastatic (early stage) prostate cancer diagnosis between 2002 and 2017 as documented in the CDW cancer registry (N = 111351). Our predictors were demographics (age at diagnosis, race), disease staging parameters abstracted at diagnosis ( Stage grouping AJCC, Gleason score, SEER summary stage) and prostate specific antigen (PSA) laboratory values in the last 5 years prior to diagnosis (last value, the value before last, average, minimum, maximum, rate of the change of the last 2 PSAs and density). The predicted outcome was disease progression at 2 years (N = 3469) and 5 years (N = 6325) defined as metastasis - taking either Abiraterone, Sipuleucel-T, Enzalutamide or Radium 223, registry cancer related death or PSA > 50. We used 4 different machine learning classifiers to train prediction models: random forest, k-nearest neighbor, decision trees, and xgboost all with hyper parameter optimization. For testing, we used two approaches: (1) 20% sample held out at the beginning of the study, and (2) stratified test/train split on the remaining data. Results: The table below shows the performance of the best classifier, xgboost. The top five predictors of disease progression were the last PSA, Gleason Score, maximum PSA, age at diagnosis, and SEER summary stage. The last PSA had a significantly higher contribution than the other predictors. More than one PSA value is important for prediction, emphasizing the need for investigating the PSA trajectory in the period before diagnosis. The models are overall very robust going from outcome at 2 years compared to 5 years. Conclusions: A machine learning based xgboost classifier can be integrated in clinical decision support at diagnosis, to robustly predict disease progression at 2 and 5 years. [Table: see text]
Collapse
Affiliation(s)
| | | | | | | | | | | | - Amy Justice
- Yale University School of Medicine, New Haven, CT
| |
Collapse
|
13
|
Savova GK, Danciu I, Alamudun F, Miller T, Lin C, Bitterman DS, Tourassi G, Warner JL. Use of Natural Language Processing to Extract Clinical Cancer Phenotypes from Electronic Medical Records. Cancer Res 2019; 79:5463-5470. [PMID: 31395609 PMCID: PMC7227798 DOI: 10.1158/0008-5472.can-19-0579] [Citation(s) in RCA: 72] [Impact Index Per Article: 14.4] [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: 02/15/2019] [Revised: 06/17/2019] [Accepted: 07/29/2019] [Indexed: 12/12/2022]
Abstract
Current models for correlating electronic medical records with -omics data largely ignore clinical text, which is an important source of phenotype information for patients with cancer. This data convergence has the potential to reveal new insights about cancer initiation, progression, metastasis, and response to treatment. Insights from this real-world data will catalyze clinical care, research, and regulatory activities. Natural language processing (NLP) methods are needed to extract these rich cancer phenotypes from clinical text. Here, we review the advances of NLP and information extraction methods relevant to oncology based on publications from PubMed as well as NLP and machine learning conference proceedings in the last 3 years. Given the interdisciplinary nature of the fields of oncology and information extraction, this analysis serves as a critical trail marker on the path to higher fidelity oncology phenotypes from real-world data.
Collapse
Affiliation(s)
- Guergana K Savova
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts.
- Harvard Medical School, Boston, Massachusetts
| | | | | | - Timothy Miller
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts
- Harvard Medical School, Boston, Massachusetts
| | - Chen Lin
- Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts
| | - Danielle S Bitterman
- Harvard Medical School, Boston, Massachusetts
- Dana Farber Cancer Institute, Boston, Massachusetts
| | | | | |
Collapse
|
14
|
Steitz BD, Weinberg ST, Danciu I, Unertl KM. Managing and Communicating Operational Workflow: Designing and Implementing an Electronic Outpatient Whiteboard. Appl Clin Inform 2016; 7:59-68. [PMID: 27081407 DOI: 10.4338/aci-2015-07-cr-0082] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.8] [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: 07/09/2015] [Accepted: 12/06/2015] [Indexed: 11/23/2022] Open
Abstract
BACKGROUND Healthcare team members in emergency department contexts have used electronic whiteboard solutions to help manage operational workflow for many years. Ambulatory clinic settings have highly complex operational workflow, but are still limited in electronic assistance to communicate and coordinate work activities. OBJECTIVE To describe and discuss the design, implementation, use, and ongoing evolution of a coordination and collaboration tool supporting ambulatory clinic operational workflow at Vanderbilt University Medical Center (VUMC). METHODS The outpatient whiteboard tool was initially designed to support healthcare work related to an electronic chemotherapy order-entry application. After a highly successful initial implementation in an oncology context, a high demand emerged across the organization for the outpatient whiteboard implementation. Over the past 10 years, developers have followed an iterative user-centered design process to evolve the tool. RESULTS The electronic outpatient whiteboard system supports 194 separate whiteboards and is accessed by over 2800 distinct users on a typical day. Clinics can configure their whiteboards to support unique workflow elements. Since initial release, features such as immunization clinical decision support have been integrated into the system, based on requests from end users. CONCLUSIONS The success of the electronic outpatient whiteboard demonstrates the usefulness of an operational workflow tool within the ambulatory clinic setting. Operational workflow tools can play a significant role in supporting coordination, collaboration, and teamwork in ambulatory healthcare settings.
Collapse
Affiliation(s)
- Bryan D Steitz
- Department of Biomedical Informatics, Vanderbilt University School of Medicine
| | - Stuart T Weinberg
- Department of Biomedical Informatics, Vanderbilt University School of Medicine; Department of Pediatrics, Vanderbilt University School of Medicine
| | - Ioana Danciu
- Department of Biomedical Informatics, Vanderbilt University School of Medicine; Department of Quality Safety and Risk Prevention, Vanderbilt University Medical Center
| | - Kim M Unertl
- Department of Biomedical Informatics, Vanderbilt University School of Medicine
| |
Collapse
|
15
|
Schildcrout JS, Shi Y, Danciu I, Bowton E, Field JR, Pulley JM, Basford MA, Gregg W, Cowan JD, Harrell FE, Roden DM, Peterson JF, Denny JC. A prognostic model based on readily available clinical data enriched a pre-emptive pharmacogenetic testing program. J Clin Epidemiol 2016; 72:107-15. [PMID: 26628336 PMCID: PMC4779720 DOI: 10.1016/j.jclinepi.2015.08.028] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.8] [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: 10/06/2014] [Revised: 07/06/2015] [Accepted: 08/31/2015] [Indexed: 12/27/2022]
Abstract
OBJECTIVES We describe the development, implementation, and evaluation of a model to pre-emptively select patients for genotyping based on medication exposure risk. STUDY DESIGN AND SETTING Using deidentified electronic health records, we derived a prognostic model for the prescription of statins, warfarin, or clopidogrel. The model was implemented into a clinical decision support (CDS) tool to recommend pre-emptive genotyping for patients exceeding a prescription risk threshold. We evaluated the rule on an independent validation cohort and on an implementation cohort, representing the population in which the CDS tool was deployed. RESULTS The model exhibited moderate discrimination with area under the receiver operator characteristic curves ranging from 0.68 to 0.75 at 1 and 2 years after index dates. Risk estimates tended to underestimate true risk. The cumulative incidences of medication prescriptions at 1 and 2 years were 0.35 and 0.48, respectively, among 1,673 patients flagged by the model. The cumulative incidences in the same number of randomly sampled subjects were 0.12 and 0.19, and in patients over 50 years with the highest body mass indices, they were 0.22 and 0.34. CONCLUSION We demonstrate that prognostic algorithms can guide pre-emptive pharmacogenetic testing toward those likely to benefit from it.
Collapse
Affiliation(s)
- Jonathan S Schildcrout
- Department of Biostatistics, Vanderbilt University School of Medicine, 2525 West End Ave, Suite 1100, Nashville, TN 37203, USA; Department of Anesthesiology, Vanderbilt University School of Medicine, 1211 21st Avenue South, Nashville, TN 37212, USA.
| | - Yaping Shi
- Department of Biostatistics, Vanderbilt University School of Medicine, 2525 West End Ave, Suite 1100, Nashville, TN 37203, USA
| | - Ioana Danciu
- Institute for Clinical and Translational Research, Vanderbilt University School of Medicine, 2525 West End Ave, Nashville, TN, 37203, USA
| | - Erica Bowton
- Institute for Clinical and Translational Research, Vanderbilt University School of Medicine, 2525 West End Ave, Nashville, TN, 37203, USA
| | - Julie R Field
- Institute for Clinical and Translational Research, Vanderbilt University School of Medicine, 2525 West End Ave, Nashville, TN, 37203, USA
| | - Jill M Pulley
- Institute for Clinical and Translational Research, Vanderbilt University School of Medicine, 2525 West End Ave, Nashville, TN, 37203, USA
| | - Melissa A Basford
- Institute for Clinical and Translational Research, Vanderbilt University School of Medicine, 2525 West End Ave, Nashville, TN, 37203, USA
| | - William Gregg
- Department of Biomedical Informatics, Vanderbilt University School of Medicine, 2525 West End Avenue, Suite 1475, Nashville, TN 37203, USA; Department of Medicine, Vanderbilt University School of Medicine, 1161 21st Avenue South, Nashville, TN 37232, USA
| | - James D Cowan
- Institute for Clinical and Translational Research, Vanderbilt University School of Medicine, 2525 West End Ave, Nashville, TN, 37203, USA
| | - Frank E Harrell
- Department of Biostatistics, Vanderbilt University School of Medicine, 2525 West End Ave, Suite 1100, Nashville, TN 37203, USA
| | - Dan M Roden
- Department of Medicine, Vanderbilt University School of Medicine, 1161 21st Avenue South, Nashville, TN 37232, USA; Department of Pharmacology, Vanderbilt University School of Medicine, 1285 Medical Research Building IV, Nashville, TN 37232-0575, USA
| | - Josh F Peterson
- Department of Biomedical Informatics, Vanderbilt University School of Medicine, 2525 West End Avenue, Suite 1475, Nashville, TN 37203, USA; Department of Medicine, Vanderbilt University School of Medicine, 1161 21st Avenue South, Nashville, TN 37232, USA
| | - Joshua C Denny
- Department of Biomedical Informatics, Vanderbilt University School of Medicine, 2525 West End Avenue, Suite 1475, Nashville, TN 37203, USA; Department of Medicine, Vanderbilt University School of Medicine, 1161 21st Avenue South, Nashville, TN 37232, USA
| |
Collapse
|
16
|
McGregor TL, Jones DP, Wang L, Danciu I, Bridges BC, Fleming GM, Shirey-Rice J, Chen L, Byrne DW, Van Driest SL. Acute Kidney Injury Incidence in Noncritically Ill Hospitalized Children, Adolescents, and Young Adults: A Retrospective Observational Study. Am J Kidney Dis 2016; 67:384-90. [PMID: 26319754 PMCID: PMC4769119 DOI: 10.1053/j.ajkd.2015.07.019] [Citation(s) in RCA: 91] [Impact Index Per Article: 11.4] [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: 03/03/2015] [Accepted: 07/06/2015] [Indexed: 01/01/2023]
Abstract
BACKGROUND Acute kidney injury (AKI) has been characterized in high-risk pediatric hospital inpatients, in whom AKI is frequent and associated with increased mortality, morbidity, and length of stay. The incidence of AKI among patients not requiring intensive care is unknown. STUDY DESIGN Retrospective cohort study. SETTING & PARTICIPANTS 13,914 noncritical admissions during 2011 and 2012 at our tertiary referral pediatric hospital were evaluated. Patients younger than 28 days or older than 21 years of age or with chronic kidney disease (CKD) were excluded. Admissions with 2 or more serum creatinine measurements were evaluated. FACTORS Demographic features, laboratory measurements, medication exposures, and length of stay. OUTCOME AKI defined as increased serum creatinine level in accordance with KDIGO (Kidney Disease: Improving Global Outcomes) criteria. Based on time of admission, time interval requirements were met in 97% of cases, but KDIGO time window criteria were not strictly enforced to allow implementation using clinically obtained data. RESULTS 2 or more creatinine measurements (one baseline before or during admission and a second during admission) in 2,374 of 13,914 (17%) patients allowed for AKI evaluation. A serum creatinine difference ≥0.3mg/dL or ≥1.5 times baseline was seen in 722 of 2,374 (30%) patients. A minimum of 5% of all noncritical inpatients without CKD in pediatric wards have an episode of AKI during routine hospital admission. LIMITATIONS Urine output, glomerular filtration rate, and time interval criteria for AKI were not applied secondary to study design and available data. The evaluated cohort was restricted to patients with 2 or more clinically obtained serum creatinine measurements, and baseline creatinine level may have been measured after the AKI episode. CONCLUSIONS AKI occurs in at least 5% of all noncritically ill hospitalized children, adolescents, and young adults without known CKD. Physicians should increase their awareness of AKI and improve surveillance strategies with serum creatinine measurements in this population so that exacerbating factors such as nephrotoxic medication exposures may be modified as indicated.
Collapse
Affiliation(s)
| | - Deborah P Jones
- Department of Pediatrics, Vanderbilt University, Nashville, TN
| | - Li Wang
- Department of Biostatistics, Vanderbilt University, Nashville, TN
| | - Ioana Danciu
- Institute for Clinical and Translational Research, Vanderbilt University, Nashville, TN
| | - Brian C Bridges
- Department of Pediatrics, Vanderbilt University, Nashville, TN
| | | | - Jana Shirey-Rice
- Institute for Clinical and Translational Research, Vanderbilt University, Nashville, TN
| | - Lixin Chen
- Institute for Clinical and Translational Research, Vanderbilt University, Nashville, TN
| | - Daniel W Byrne
- Department of Biostatistics, Vanderbilt University, Nashville, TN
| | - Sara L Van Driest
- Department of Pediatrics, Vanderbilt University, Nashville, TN; Department of Medicine, Vanderbilt University, Nashville, TN.
| |
Collapse
|
17
|
Peterson JF, Field JR, Unertl KM, Schildcrout JS, Johnson DC, Shi Y, Danciu I, Cleator JH, Pulley JM, McPherson JA, Denny JC, Laposata M, Roden DM, Johnson KB. Physician response to implementation of genotype-tailored antiplatelet therapy. Clin Pharmacol Ther 2016; 100:67-74. [PMID: 26693963 DOI: 10.1002/cpt.331] [Citation(s) in RCA: 41] [Impact Index Per Article: 5.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2015] [Revised: 11/20/2015] [Accepted: 12/17/2015] [Indexed: 01/07/2023]
Abstract
Physician responses to genomic information are vital to the success of precision medicine initiatives. We prospectively studied a pharmacogenomics implementation program for the propensity of clinicians to select antiplatelet therapy based on CYP2C19 loss-of-function variants in stented patients. Among 2,676 patients, 514 (19.2%) were found to have a CYP2C19 variant affecting clopidogrel metabolism. For the majority (93.6%) of the cohort, cardiologists received active and direct notification of CYP2C19 status. Over 12 months, 57.6% of poor metabolizers and 33.2% of intermediate metabolizers received alternatives to clopidogrel. CYP2C19 variant status was the most influential factor impacting the prescribing decision (hazard ratio [HR] in poor metabolizers 8.1, 95% confidence interval [CI] [5.4, 12.2] and HR 5.0, 95% CI [4.0, 6.3] in intermediate metabolizers), followed by patient age and type of stent implanted. We conclude that cardiologists tailored antiplatelet therapy for a minority of patients with a CYP2C19 variant and considered both genomic and nongenomic risks in their clinical decision-making.
Collapse
Affiliation(s)
- J F Peterson
- Department of Biomedical Informatics, Vanderbilt University School of Medicine, Nashville, Tennessee, USA.,Department of Medicine, Vanderbilt University School of Medicine, Nashville, Tennessee, USA
| | - J R Field
- Institute of Clinical and Translational Research, Vanderbilt University School of Medicine, Nashville, Tennessee, USA
| | - K M Unertl
- Department of Biomedical Informatics, Vanderbilt University School of Medicine, Nashville, Tennessee, USA
| | - J S Schildcrout
- Department of Biostatistics, Vanderbilt University School of Medicine, Nashville, Tennessee, USA.,Department of Anesthesiology, Vanderbilt University School of Medicine, Nashville, Tennessee, USA
| | - D C Johnson
- Department of Pharmacy, Vanderbilt University Medical Center, Nashville, Tennessee, USA
| | - Y Shi
- Department of Biostatistics, Vanderbilt University School of Medicine, Nashville, Tennessee, USA
| | - I Danciu
- Department of Biomedical Informatics, Vanderbilt University School of Medicine, Nashville, Tennessee, USA.,Institute of Clinical and Translational Research, Vanderbilt University School of Medicine, Nashville, Tennessee, USA
| | - J H Cleator
- Department of Medicine, Vanderbilt University School of Medicine, Nashville, Tennessee, USA.,Department of Pharmacology, Vanderbilt University School of Medicine, Nashville, Tennessee, USA
| | - J M Pulley
- Institute of Clinical and Translational Research, Vanderbilt University School of Medicine, Nashville, Tennessee, USA
| | - J A McPherson
- Department of Medicine, Vanderbilt University School of Medicine, Nashville, Tennessee, USA
| | - J C Denny
- Department of Biomedical Informatics, Vanderbilt University School of Medicine, Nashville, Tennessee, USA.,Department of Medicine, Vanderbilt University School of Medicine, Nashville, Tennessee, USA
| | - M Laposata
- Department of Pathology, Microbiology, and Immunology, Vanderbilt University School of Medicine, Nashville, Tennessee, USA
| | - D M Roden
- Department of Medicine, Vanderbilt University School of Medicine, Nashville, Tennessee, USA.,Department of Pharmacology, Vanderbilt University School of Medicine, Nashville, Tennessee, USA
| | - K B Johnson
- Department of Biomedical Informatics, Vanderbilt University School of Medicine, Nashville, Tennessee, USA.,Department of Pediatrics, Vanderbilt University School of Medicine, Nashville, Tennessee, USA
| |
Collapse
|
18
|
Peterson JF, Kripalani S, Danciu I, Harrell D, Marvanova M, Mixon AS, Rodriguez C, Powers JS. Electronic surveillance and pharmacist intervention for vulnerable older inpatients on high-risk medication regimens. J Am Geriatr Soc 2014; 62:2148-52. [PMID: 25366414 DOI: 10.1111/jgs.13057] [Citation(s) in RCA: 24] [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] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
Abstract
OBJECTIVES To develop and evaluate an electronic tool to assist clinical pharmacists with reviewing potentially inappropriate medications (PIMs) in hospitalized elderly adults. DESIGN Pilot intervention. SETTING Academic tertiary care hospital. PARTICIPANTS Hospitalized adults aged 65 and older admitted to the general medicine, orthopedics, and urology services during a 3-week period in 2011 who were administered at least one medication from a list of 240 PIMs. INTERVENTION A computerized PIMS dashboard flagged individuals with at least one administered PIM or a high calculated anticholinergic score. The dashboard also displayed 48-hour cumulative narcotic and benzodiazepine administration. Participants were ranked to reflect the estimated risk of an adverse event using logical combinations of data (e.g., use of multiple sedatives in a nonmonitored location). In a pilot implementation, a clinical pharmacist reviewed the flagged records and delivered an immediate point-of-care intervention for the treating physician. MEASUREMENTS Clinician response to pharmacist intervention. RESULTS The PIMS dashboard flagged 179 of 797 individuals (22%) admitted over a 3-week period and 485 participant-medication pairs for review by the clinical pharmacist. Seventy-one participant records with 139 participant-medication pairs required additional manual review of the electronic medical record. Twenty-two participants receiving 40 inappropriate medication orders were judged to warrant an intervention, which was delivered by personal communication over the telephone or text message. Clinicians enacted 31 of 40 (78%) pharmacist recommendations. CONCLUSION An electronic PIM dashboard provided an efficient mechanism for clinical pharmacists to rapidly screen the medication regimens of hospitalized elderly adults and deliver a timely point-of-care intervention when indicated.
Collapse
Affiliation(s)
- Josh F Peterson
- Department of Biomedical Informatics, School of Medicine, Vanderbilt University, Nashville, Tennessee; Department of Medicine, School of Medicine, Vanderbilt University, Nashville, Tennessee
| | | | | | | | | | | | | | | |
Collapse
|
19
|
Cox ZL, McCoy AB, Matheny ME, Bhave G, Peterson NB, Siew ED, Lewis J, Danciu I, Bian A, Shintani A, Ikizler TA, Neal EB, Peterson JF. Adverse drug events during AKI and its recovery. Clin J Am Soc Nephrol 2013; 8:1070-8. [PMID: 23539228 DOI: 10.2215/cjn.11921112] [Citation(s) in RCA: 54] [Impact Index Per Article: 4.9] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
Abstract
BACKGROUND AND OBJECTIVES The impact of AKI on adverse drug events and therapeutic failures and the medication errors leading to these events have not been well described. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS A single-center observational study of 396 hospitalized patients with a minimum 0.5 mg/dl change in serum creatinine who were prescribed a nephrotoxic or renally eliminated medication was conducted. The population was stratified into two groups by the direction of their initial serum creatinine change: AKI and AKI recovery. Adverse drug events, potential adverse drug events, therapeutic failures, and potential therapeutic failures for 148 drugs and 46 outcomes were retrospectively measured. Events were classified for preventability and severity by expert adjudication. Multivariable analysis identified medication classes predisposing AKI patients to adverse drug events. RESULTS Forty-three percent of patients experienced a potential adverse drug event, adverse drug event, therapeutic failure, or potential therapeutic failure; 66% of study events were preventable. Failure to adjust for kidney function (63%) and use of nephrotoxic medications during AKI (28%) were the most common potential adverse drug events. Worsening AKI and hypotension were the most common preventable adverse drug events. Most adverse drug events were considered serious (63%) or life-threatening (31%), with one fatal adverse drug event. Among AKI patients, administration of angiotensin-converting enzyme inhibitors/angiotensin receptor blockers, antibiotics, and antithrombotics was most strongly associated with the development of an adverse drug event or potential adverse drug event. CONCLUSIONS Adverse drug events and potential therapeutic failures are common and frequently severe in patients with AKI exposed to nephrotoxic or renally eliminated medications.
Collapse
Affiliation(s)
- Zachary L Cox
- Department of Pharmacy, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
| | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
20
|
Shuldiner AR, Relling MV, Peterson JF, Hicks JK, Freimuth RR, Sadee W, Pereira NL, Roden DM, Johnson JA, Klein TE, Shuldiner AR, Vesely M, Robinson SW, Ambulos N, Stass SA, Kelemen MD, Brown LA, Pollin TI, Beitelshees AL, Zhao RY, Pakyz RE, Palmer K, Alestock T, O'Neill C, Maloney K, Branham A, Sewell D, Relling MV, Crews K, Hoffman J, Cross S, Haidar C, Baker D, Hicks JK, Bell G, Greeson F, Gaur A, Reiss U, Huettel A, Cheng C, Gajjar A, Pappo A, Howard S, Hudson M, Pui CH, Jeha S, Evans WE, Broeckel U, Altman RB, Gong L, Whirl-Carrillo M, Klein TE, Sadee W, Manickam K, Sweet KM, Embi PJ, Roden D, Peterson J, Denny J, Schildcrout J, Bowton E, Pulley J, Beller M, Mitchell J, Danciu I, Price L, Pereira NL, Weinshilboum R, Wang L, Johnson JA, Nelson D, Clare-Salzler M, Elsey A, Burkley B, Langaee T, Liu F, Nessl D, Dong HJ, Lesko L, Freimuth RR, Chute CG. The Pharmacogenomics Research Network Translational Pharmacogenetics Program: overcoming challenges of real-world implementation. Clin Pharmacol Ther 2013; 94:207-10. [PMID: 23588301 DOI: 10.1038/clpt.2013.59] [Citation(s) in RCA: 138] [Impact Index Per Article: 12.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/02/2013] [Accepted: 03/14/2013] [Indexed: 11/09/2022]
Affiliation(s)
- A R Shuldiner
- Program in Personalized and Genomic Medicine and Department of Medicine, University of Maryland School of Medicine, Baltimore, Maryland, USA.
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
21
|
McCoy AB, Cox ZL, Neal EB, Waitman LR, Peterson NB, Bhave G, Siew ED, Danciu I, Lewis JB, Peterson JF. Real-time pharmacy surveillance and clinical decision support to reduce adverse drug events in acute kidney injury: a randomized, controlled trial. Appl Clin Inform 2012; 3:221-238. [PMID: 22719796 DOI: 10.4338/aci-2012-03-ra-0009] [Citation(s) in RCA: 29] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/21/2022] Open
Abstract
OBJECTIVES: Clinical decision support (CDS), such as computerized alerts, improves prescribing in the setting of acute kidney injury (AKI), but considerable opportunity remains to improve patient safety. The authors sought to determine whether pharmacy surveillance of AKI patients could detect and prevent medication errors that are not corrected by automated interventions. METHODS: The authors conducted a randomized clinical trial among 396 patients admitted to an academic, tertiary care hospital between June 1, 2010 and August 31, 2010 with an acute 0.5 mg/dl change in serum creatinine over 48 hours and a nephrotoxic or renally cleared medication order. Patients randomly assigned to the intervention group received surveillance from a clinical pharmacist using a web-based surveillance tool to monitor drug prescribing and kidney function trends. CDS alerting and standard pharmacy services were active in both study arms. Outcome measures included blinded adjudication of potential adverse drug events (pADEs), adverse drug events (ADEs) and time to provider modification or discontinuation of targeted nephrotoxic or renally cleared medications. RESULTS: Potential ADEs or ADEs occurred for 104 (8.0%) of control and 99 (7.1%) of intervention patient-medication pairs (p=0.4). Additionally, the time to provider modification or discontinuation of targeted nephrotoxic or renally cleared medications did not differ between control and intervention patients (33.4 hrs vs. 30.3 hrs, p=0.3). CONCLUSIONS: Pharmacy surveillance had no incremental benefit over previously implemented CDS alerts.
Collapse
Affiliation(s)
- Allison B McCoy
- Department of Biomedical Informatics, Vanderbilt University School of Medicine, Nashville, TN
| | | | | | | | | | | | | | | | | | | |
Collapse
|
22
|
Siew ED, Ikizler TA, Matheny ME, Shi Y, Schildcrout JS, Danciu I, Dwyer JP, Srichai M, Hung AM, Smith JP, Peterson JF. Estimating baseline kidney function in hospitalized patients with impaired kidney function. Clin J Am Soc Nephrol 2012; 7:712-9. [PMID: 22422536 DOI: 10.2215/cjn.10821011] [Citation(s) in RCA: 205] [Impact Index Per Article: 17.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
Abstract
BACKGROUND AND OBJECTIVES Inaccurate determination of baseline kidney function can misclassify acute kidney injury (AKI) and affect the study of AKI-related outcomes. No consensus exists on how to optimally determine baseline kidney function when multiple preadmission creatinine measurements are available. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS The accuracy of commonly used methods for estimating baseline serum creatinine was compared with that of a reference standard adjudicated by a panel of board-certified nephrologists in 379 patients with AKI or CKD admitted to a tertiary referral center. RESULTS Agreement between estimating methods and the reference standard was highest when using creatinine values measured 7-365 days before admission. During this interval, the intraclass correlation coefficient (ICC) for the mean outpatient serum creatinine level (0.91 [95% confidence interval (CI), 0.88-0.92]) was higher than the most recent outpatient (ICC, 0.84 [95% CI, 0.80-0.88]; P<0.001) and the nadir outpatient (ICC, 0.83 [95% CI, 0.76-0.87; P<0.001) serum creatinine. Using the final creatinine value from a prior inpatient admission increased the ICC of the most recent outpatient creatinine method (0.88 [95% CI, 0.85-0.91]). Performance of all methods declined or was unchanged when the time interval was broadened to 2 years or included serum creatinine measured within a week of admission. CONCLUSIONS The mean outpatient serum creatinine measured within a year of hospitalization most closely approximates nephrologist-adjudicated serum creatinine values.
Collapse
Affiliation(s)
- Edward D Siew
- Department of Medicine, Division of Nephrology, Vanderbilt University Medical Center, Nashville, Tennessee 37232, USA.
| | | | | | | | | | | | | | | | | | | | | |
Collapse
|
23
|
Waitman LR, Phillips IE, McCoy AB, Danciu I, Halpenny RM, Nelsen CL, Johnson DC, Starmer JM, Peterson JF. Adopting real-time surveillance dashboards as a component of an enterprisewide medication safety strategy. Jt Comm J Qual Patient Saf 2011; 37:326-32. [PMID: 21819031 DOI: 10.1016/s1553-7250(11)37041-9] [Citation(s) in RCA: 30] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
Abstract
BACKGROUND High-alert medications are frequently responsible for adverse drug events and present significant hazards to inpatients, despite technical improvements in the way they are ordered, dispensed, and administered. METHODS A real-time surveillance application was designed and implemented to enable pharmacy review of high-alert medication orders to complement existing computerized provider order entry and integrated clinical decision support systems in a tertiary care hospital. The surveillance tool integrated real-time data from multiple clinical systems and applied logical criteria to highlight potentially high-risk scenarios. Use of the surveillance system for adult inpatients was analyzed for warfarin, heparin and enoxaparin, and aminoglycoside antibiotics. RESULTS Among 28,929 hospitalizations during the study period, patients eligible to appear on a dashboard included 2224 exposed to warfarin, 8383 to heparin or enoxaparin, and 893 to aminoglycosides. Clinical pharmacists reviewed the warfarin and aminoglycoside dashboards during 100% of the days in the study period-and the heparinlenoxaparin dashboard during 71% of the days. Displayed alert conditions ranged from common events, such as 55% of patients receiving aminoglycosides were missing a baseline creatinine, to rare events, such as 0.1% of patients exposed to heparin were given a bolus greater than 10,000 units. On the basis of interpharmacist communication and electronic medical record notes recorded within the dashboards, interventions to prevent further patient harm were frequent. CONCLUSIONS Even in an environment with sophisticated computerized provider order entry and clinical decision support systems, real-time pharmacy surveillance of high-alert medications provides an important platform for intercepting medication errors and optimizing therapy.
Collapse
Affiliation(s)
- Lemuel R Waitman
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
| | | | | | | | | | | | | | | | | |
Collapse
|
24
|
McCoy AB, Waitman LR, Gadd CS, Danciu I, Smith JP, Lewis JB, Schildcrout JS, Peterson JF. A computerized provider order entry intervention for medication safety during acute kidney injury: a quality improvement report. Am J Kidney Dis 2010; 56:832-41. [PMID: 20709437 DOI: 10.1053/j.ajkd.2010.05.024] [Citation(s) in RCA: 90] [Impact Index Per Article: 6.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2009] [Accepted: 05/24/2010] [Indexed: 11/11/2022]
Abstract
BACKGROUND Frequently, prescribers fail to account for changing kidney function when prescribing medications. We evaluated the use of a computerized provider order entry intervention to improve medication management during acute kidney injury. STUDY DESIGN Quality improvement report with time series analyses. SETTING & PARTICIPANTS 1,598 adult inpatients with a minimum 0.5-mg/dL increase in serum creatinine level over 48 hours after an order for at least one of 122 nephrotoxic or renally cleared medications. QUALITY IMPROVEMENT PLAN Passive noninteractive warnings about increasing serum creatinine level appeared within the computerized provider order entry interface and on printed rounding reports. For contraindicated or high-toxicity medications that should be avoided or adjusted, an interruptive alert within the system asked providers to modify or discontinue the targeted orders, mark the current dosing as correct and to remain unchanged, or defer the alert to reappear in the next session. OUTCOMES & MEASUREMENTS Intervention effect on drug modification or discontinuation, time to modification or discontinuation, and provider interactions with alerts. RESULTS The modification or discontinuation rate per 100 events for medications included in the interruptive alert within 24 hours of increasing creatinine level improved from 35.2 preintervention to 52.6 postintervention (P < 0.001); orders were modified or discontinued more quickly (P < 0.001). During the postintervention period, providers initially deferred 78.1% of interruptive alerts, although 54% of these eventually were modified or discontinued before patient death, discharge, or transfer. The response to passive alerts about medications requiring review did not significantly change compared with baseline. LIMITATIONS Single tertiary-care academic medical center; provider actions were not independently adjudicated for appropriateness. CONCLUSIONS A computerized provider order entry-based alerting system to support medication management after acute kidney injury significantly increased the rate and timeliness of modification or discontinuation of targeted medications.
Collapse
Affiliation(s)
- Allison B McCoy
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, USA.
| | | | | | | | | | | | | | | |
Collapse
|
25
|
McCoy AB, Peterson JF, Gadd CS, Danciu I, Waitman LR. A system to improve medication safety in the setting of acute kidney injury: initial provider response. AMIA Annu Symp Proc 2008:1051. [PMID: 18999252] [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] [Subscribe] [Scholar Register] [Received: 03/14/2008] [Revised: 07/16/2008] [Indexed: 05/27/2023]
Abstract
Clinical decision support systems can decrease common errors related to inappropriate or excessive dosing for nephrotoxic or renally cleared drugs. We developed a comprehensive medication safety intervention with varying levels of workflow intrusiveness within computerized provider order entry to continuously monitor for and alert providers about early-onset acute kidney injury. Initial provider response to the interventions shows potential success in improving medication safety and suggests future enhancements to increase effectiveness.
Collapse
Affiliation(s)
- Allison B McCoy
- Department of Biomedical Informatics, Vanderbilt University, Nashville, TN, USA
| | | | | | | | | |
Collapse
|
26
|
Paraschivescu I, Danciu I, Mardare J, Constantinescu E, Neguţ M. [An episode of hospital infection due to Klebsiella pneumoniae in a neonatal department]. Rev Ig Bacteriol Virusol Parazitol Epidemiol Pneumoftiziol Bacteriol Virusol Parazitol Epidemiol 1989; 34:313-24. [PMID: 2701342] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Subscribe] [Scholar Register] [Indexed: 01/02/2023]
Abstract
Enterotoxin-producing Klebsiella pneumoniae was implicated in the induction of intrahospital infections in new-born babies. A total of 46 children and 4 adults (hospital personnel) were involved. Most of the subjects (82.6%) had median and light forms of gastroenterocolitis, and recovered following biological re-equilibration. In 17.39% of the cases the evolution was more severe due to advanced dehydration and secondary dissemination of the infection. Two children (approximately 4%) died. Factors that favored the dissemination of the infection were hygiene deficiencies and ignorance of functioning rules of materno-infantile units, and these included: admission to the hospital of working personnel with acute phenomena of enterocolitis; administration of sweetened solutions that were prepared without control and stored at room temperature; the "critical" point represented by the special room for "the accommodation" of the newborns, a "key-point" where infection was disseminated to other wards following dispersion of "adapted babies".
Collapse
|
27
|
Dumitrescu N, Tipărescu E, Hartia V, Danciu I, Boiu S. [Difficulties in diagnosis of bullous disease of the lung]. Med Interna (Bucur) 1970; 22:1263-71. [PMID: 5491395] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [MESH Headings] [Subscribe] [Scholar Register] [Indexed: 01/15/2023]
|
28
|
Goldiş G, Danciu I, Popescu T, Fotiade B, Oţoiu M. [Oximetry in pediatrics]. Pediatria (Bucur) 1969; 18:465-75. [PMID: 5378252] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [MESH Headings] [Subscribe] [Scholar Register] [Indexed: 01/14/2023]
|