Affordable Access

deepdyve-link
Publisher Website

Real-time electronic health record mortality prediction during the COVID-19 pandemic: a prospective cohort study

Authors
  • Sottile, Peter D1
  • Albers, David2
  • DeWitt, Peter E2
  • Russell, Seth3
  • Stroh, J N4
  • Kao, David P5
  • Adrian, Bonnie6
  • Levine, Matthew E7
  • Mooney, Ryan8
  • Larchick, Lenny8
  • Kutner, Jean S9
  • Wynia, Matthew K10, 11
  • Glasheen, Jeffrey J12
  • Bennett, Tellen D2, 13
  • 1 Division of Pulmonary Sciences and Critical Care Medicine, Department of Medicine, University of Colorado School of Medicine, USA , (United States)
  • 2 Section of Informatics and Data Science, Department of Pediatrics, University of Colorado School of Medicine, USA , (United States)
  • 3 Data Science to Patient Value Initiative, University of Colorado School of Medicine, USA , (United States)
  • 4 Department of Bioengineering, University of Colorado-Denver College of Engineering, Design, and Computing, USA , (United States)
  • 5 Divisions of Cardiology and Bioinformatics/Personalized Medicine, Department of Medicine, University of Colorado School of Medicine, USA , (United States)
  • 6 UCHealth Clinical Informatics and University of Colorado College of Nursing, USA , (United States)
  • 7 Department of Computational and Mathematical Sciences, California Institute of Technology, USA , (United States)
  • 8 UCHealth Hospital System, USA , (United States)
  • 9 Division of General Internal Medicine, Department of Medicine, University of Colorado School of Medicine, University of Colorado Hospital/UCHealth, USA , (United States)
  • 10 Department of Medicine, University of Colorado School of Medicine,, USA , (United States)
  • 11 Center for Bioethics and Humanities, University of Colorado, USA , (United States)
  • 12 Division of Hospital Medicine, Department of Medicine, University of Colorado School of Medicine, UCHealth, USA , (United States)
  • 13 Department of Pediatrics, Section of Critical Care Medicine, University of Colorado School of Medicine, USA , (United States)
Type
Published Article
Journal
Journal of the American Medical Informatics Association
Publisher
Oxford University Press
Publication Date
Sep 02, 2021
Volume
28
Issue
11
Pages
2354–2365
Identifiers
DOI: 10.1093/jamia/ocab100
PMID: 33973011
PMCID: PMC8136054
Source
PubMed Central
Keywords
Disciplines
  • AcademicSubjects/MED00580
  • AcademicSubjects/SCI01060
  • AcademicSubjects/SCI01530
License
Unknown

Abstract

Objective To rapidly develop, validate, and implement a novel real-time mortality score for the COVID-19 pandemic that improves upon sequential organ failure assessment (SOFA) for decision support for a Crisis Standards of Care team. Materials and Methods We developed, verified, and deployed a stacked generalization model to predict mortality using data available in the electronic health record (EHR) by combining 5 previously validated scores and additional novel variables reported to be associated with COVID-19-specific mortality. We verified the model with prospectively collected data from 12 hospitals in Colorado between March 2020 and July 2020. We compared the area under the receiver operator curve (AUROC) for the new model to the SOFA score and the Charlson Comorbidity Index. Results The prospective cohort included 27 296 encounters, of which 1358 (5.0%) were positive for SARS-CoV-2, 4494 (16.5%) required intensive care unit care, 1480 (5.4%) required mechanical ventilation, and 717 (2.6%) ended in death. The Charlson Comorbidity Index and SOFA scores predicted mortality with an AUROC of 0.72 and 0.90, respectively. Our novel score predicted mortality with AUROC 0.94. In the subset of patients with COVID-19, the stacked model predicted mortality with AUROC 0.90, whereas SOFA had AUROC of 0.85. Discussion Stacked regression allows a flexible, updatable, live-implementable, ethically defensible predictive analytics tool for decision support that begins with validated models and includes only novel information that improves prediction. Conclusion We developed and validated an accurate in-hospital mortality prediction score in a live EHR for automatic and continuous calculation using a novel model that improved upon SOFA.

Report this publication

Statistics

Seen <100 times