Development and Validation of Machine Learning Models to Predict Admission From Emergency Department to Inpatient and Intensive Care Units.

Autor: Fenn A; Duke University School of Medicine, Durham, NC; Duke Institute of Health Innovation, Durham, NC. Electronic address: alexanderfenn@gmail.com., Davis C; Duke Institute of Health Innovation, Durham, NC., Buckland DM; Division of Emergency Medicine, Department of Surgery, Duke University School of Medicine, Durham, NC., Kapadia N; Division of Emergency Medicine, Department of Surgery, Duke University School of Medicine, Durham, NC., Nichols M; Duke Institute of Health Innovation, Durham, NC., Gao M; Duke Institute of Health Innovation, Durham, NC., Knechtle W; Duke Institute of Health Innovation, Durham, NC., Balu S; Duke Institute of Health Innovation, Durham, NC., Sendak M; Duke Institute of Health Innovation, Durham, NC., Theiling BJ; Division of Emergency Medicine, Department of Surgery, Duke University School of Medicine, Durham, NC.
Jazyk: angličtina
Zdroj: Annals of emergency medicine [Ann Emerg Med] 2021 Aug; Vol. 78 (2), pp. 290-302. Date of Electronic Publication: 2021 May 08.
DOI: 10.1016/j.annemergmed.2021.02.029
Abstrakt: Study Objective: This study aimed to develop and validate 2 machine learning models that use historical and current-visit patient data from electronic health records to predict the probability of patient admission to either an inpatient unit or ICU at each hour (up to 24 hours) of an emergency department (ED) encounter. The secondary goal was to provide a framework for the operational implementation of these machine learning models.
Methods: Data were curated from 468,167 adult patient encounters in 3 EDs (1 academic and 2 community-based EDs) of a large academic health system from August 1, 2015, to October 31, 2018. The models were validated using encounter data from January 1, 2019, to December 31, 2019. An operational user dashboard was developed, and the models were run on real-time encounter data.
Results: For the intermediate admission model, the area under the receiver operating characteristic curve was 0.873 and the area under the precision-recall curve was 0.636. For the ICU admission model, the area under the receiver operating characteristic curve was 0.951 and the area under the precision-recall curve was 0.461. The models had similar performance in both the academic- and community-based settings as well as across the 2019 and real-time encounter data.
Conclusion: Machine learning models were developed to accurately make predictions regarding the probability of inpatient or ICU admission throughout the entire duration of a patient's encounter in ED and not just at the time of triage. These models remained accurate for a patient cohort beyond the time period of the initial training data and were integrated to run on live electronic health record data, with similar performance.
(Copyright © 2021 American College of Emergency Physicians. Published by Elsevier Inc. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: