Open AccessPredicting next-day discharge via electronic health record access logs
Author(s) -
Xinmeng Zhang,
Chao Yan,
Bradley Malin,
Mayur B. Patel,
You Chen
Publication year - 2021
Publication title -
journal of the american medical informatics association
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.614
H-Index - 150
eISSN - 1527-974X
pISSN - 1067-5027
DOI - 10.1093/jamia/ocab211
Subject(s) - audit , electronic health record , health records , medical diagnosis , medicine , medical record , demographics , receiver operating characteristic , resource (disambiguation) , computer science , medical emergency , machine learning , health care , computer network , demography , management , pathology , sociology , economics , radiology , economic growth
Hospital capacity management depends on accurate real-time estimates of hospital-wide discharges. Estimation by a clinician requires an excessively large amount of effort and, even when attempted, accuracy in forecasting next-day patient-level discharge is poor. This study aims to support next-day discharge predictions with machine learning by incorporating electronic health record (EHR) audit log data, a resource that captures EHR users' granular interactions with patients' records by communicating various semantics and has been neglected in outcome predictions.