Pediatric sepsis phenotypes for enhanced therapeutics: An application of clustering to electronic health records

Abstract Objective The heterogeneity of pediatric sepsis patients suggests the potential benefits of clustering analytics to derive phenotypes with distinct host response patterns that may help guide personalized therapeutics. We evaluate the relative performance of latent class analysis (LCA) and K...

Full description

Saved in:
Bibliographic Details
Main Authors: Ioannis Koutroulis, Tom Velez, Tony Wang, Seife Yohannes, Jessica E. Galarraga, Joseph A. Morales, Robert J. Freishtat, James M. Chamberlain
Format: Article
Language:English
Published: Elsevier 2022-02-01
Series:Journal of the American College of Emergency Physicians Open
Subjects:
Online Access:https://doi.org/10.1002/emp2.12660
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850184236401688576
author Ioannis Koutroulis
Tom Velez
Tony Wang
Seife Yohannes
Jessica E. Galarraga
Joseph A. Morales
Robert J. Freishtat
James M. Chamberlain
author_facet Ioannis Koutroulis
Tom Velez
Tony Wang
Seife Yohannes
Jessica E. Galarraga
Joseph A. Morales
Robert J. Freishtat
James M. Chamberlain
author_sort Ioannis Koutroulis
collection DOAJ
description Abstract Objective The heterogeneity of pediatric sepsis patients suggests the potential benefits of clustering analytics to derive phenotypes with distinct host response patterns that may help guide personalized therapeutics. We evaluate the relative performance of latent class analysis (LCA) and K‐means, 2 commonly used clustering methods toward the derivation of clinically useful pediatric sepsis phenotypes. Methods Data were extracted from anonymized medical records of 6446 pediatric patients that presented to 1 of 6 emergency departments (EDs) between 2013 and 2018 and were thereafter admitted. Using International Classification of Diseases (ICD)‐9 and ICD‐10 discharge codes, 151 patients were identified with a sepsis continuum diagnosis that included septicemia, sepsis, severe sepsis, and septic shock. Using feature sets used in related clustering studies, LCA and K‐means algorithms were used to derive 4 distinct phenotypic pediatric sepsis segmentations. Each segmentation was evaluated for phenotypic homogeneity, separation, and clinical use. Results Using the 2 feature sets, LCA clustering resulted in 2 similar segmentations of 4 clinically distinct phenotypes, while K‐means clustering resulted in segmentations of 3 and 4 phenotypes. All 4 segmentations identified at least 1 high severity phenotype, but LCA‐identified phenotypes reflected superior stratification, high entropy approaching 1 (eg, 0.994) indicating excellent separation between estimated phenotypes, and differential treatment/treatment response, and outcomes that were non‐randomly distributed across phenotypes (P < 0.001). Conclusion Compared to K‐means, which is commonly used in clustering studies, LCA appears to be a more robust, clinically useful statistical tool in analyzing a heterogeneous pediatric sepsis cohort toward informing targeted therapies. Additional prospective studies are needed to validate clinical utility of predictive models that target derived pediatric sepsis phenotypes in emergency department settings.
format Article
id doaj-art-b98a63f7ddbc44fcb91e0aafc49fedcc
institution OA Journals
issn 2688-1152
language English
publishDate 2022-02-01
publisher Elsevier
record_format Article
series Journal of the American College of Emergency Physicians Open
spelling doaj-art-b98a63f7ddbc44fcb91e0aafc49fedcc2025-08-20T02:17:05ZengElsevierJournal of the American College of Emergency Physicians Open2688-11522022-02-0131n/an/a10.1002/emp2.12660Pediatric sepsis phenotypes for enhanced therapeutics: An application of clustering to electronic health recordsIoannis Koutroulis0Tom Velez1Tony Wang2Seife Yohannes3Jessica E. Galarraga4Joseph A. Morales5Robert J. Freishtat6James M. Chamberlain7Emergency Medicine Children's National Hospital/George Washington University School of Medicine and Health Sciences Washington District of Columbia USAComputer Technology Associates Cardiff California USAImedacs Ann Arbor Michigan USAMedStar Health Research Institute Hyattsville Maryland USAMedStar Health Research Institute Hyattsville Maryland USAComputer Technology Associates Cardiff California USAEmergency Medicine Children's National Hospital/George Washington University School of Medicine and Health Sciences Washington District of Columbia USAEmergency Medicine Children's National Hospital/George Washington University School of Medicine and Health Sciences Washington District of Columbia USAAbstract Objective The heterogeneity of pediatric sepsis patients suggests the potential benefits of clustering analytics to derive phenotypes with distinct host response patterns that may help guide personalized therapeutics. We evaluate the relative performance of latent class analysis (LCA) and K‐means, 2 commonly used clustering methods toward the derivation of clinically useful pediatric sepsis phenotypes. Methods Data were extracted from anonymized medical records of 6446 pediatric patients that presented to 1 of 6 emergency departments (EDs) between 2013 and 2018 and were thereafter admitted. Using International Classification of Diseases (ICD)‐9 and ICD‐10 discharge codes, 151 patients were identified with a sepsis continuum diagnosis that included septicemia, sepsis, severe sepsis, and septic shock. Using feature sets used in related clustering studies, LCA and K‐means algorithms were used to derive 4 distinct phenotypic pediatric sepsis segmentations. Each segmentation was evaluated for phenotypic homogeneity, separation, and clinical use. Results Using the 2 feature sets, LCA clustering resulted in 2 similar segmentations of 4 clinically distinct phenotypes, while K‐means clustering resulted in segmentations of 3 and 4 phenotypes. All 4 segmentations identified at least 1 high severity phenotype, but LCA‐identified phenotypes reflected superior stratification, high entropy approaching 1 (eg, 0.994) indicating excellent separation between estimated phenotypes, and differential treatment/treatment response, and outcomes that were non‐randomly distributed across phenotypes (P < 0.001). Conclusion Compared to K‐means, which is commonly used in clustering studies, LCA appears to be a more robust, clinically useful statistical tool in analyzing a heterogeneous pediatric sepsis cohort toward informing targeted therapies. Additional prospective studies are needed to validate clinical utility of predictive models that target derived pediatric sepsis phenotypes in emergency department settings.https://doi.org/10.1002/emp2.12660K‐meansLCAphenotypessepsis
spellingShingle Ioannis Koutroulis
Tom Velez
Tony Wang
Seife Yohannes
Jessica E. Galarraga
Joseph A. Morales
Robert J. Freishtat
James M. Chamberlain
Pediatric sepsis phenotypes for enhanced therapeutics: An application of clustering to electronic health records
Journal of the American College of Emergency Physicians Open
K‐means
LCA
phenotypes
sepsis
title Pediatric sepsis phenotypes for enhanced therapeutics: An application of clustering to electronic health records
title_full Pediatric sepsis phenotypes for enhanced therapeutics: An application of clustering to electronic health records
title_fullStr Pediatric sepsis phenotypes for enhanced therapeutics: An application of clustering to electronic health records
title_full_unstemmed Pediatric sepsis phenotypes for enhanced therapeutics: An application of clustering to electronic health records
title_short Pediatric sepsis phenotypes for enhanced therapeutics: An application of clustering to electronic health records
title_sort pediatric sepsis phenotypes for enhanced therapeutics an application of clustering to electronic health records
topic K‐means
LCA
phenotypes
sepsis
url https://doi.org/10.1002/emp2.12660
work_keys_str_mv AT ioanniskoutroulis pediatricsepsisphenotypesforenhancedtherapeuticsanapplicationofclusteringtoelectronichealthrecords
AT tomvelez pediatricsepsisphenotypesforenhancedtherapeuticsanapplicationofclusteringtoelectronichealthrecords
AT tonywang pediatricsepsisphenotypesforenhancedtherapeuticsanapplicationofclusteringtoelectronichealthrecords
AT seifeyohannes pediatricsepsisphenotypesforenhancedtherapeuticsanapplicationofclusteringtoelectronichealthrecords
AT jessicaegalarraga pediatricsepsisphenotypesforenhancedtherapeuticsanapplicationofclusteringtoelectronichealthrecords
AT josephamorales pediatricsepsisphenotypesforenhancedtherapeuticsanapplicationofclusteringtoelectronichealthrecords
AT robertjfreishtat pediatricsepsisphenotypesforenhancedtherapeuticsanapplicationofclusteringtoelectronichealthrecords
AT jamesmchamberlain pediatricsepsisphenotypesforenhancedtherapeuticsanapplicationofclusteringtoelectronichealthrecords