Xinmeng Zhang1, Chao Yan1, Bradley A Malin1,2,3, Mayur B Patel4,5, You Chen1,2. 1. Department of Computer Science, Vanderbilt University, Nashville, Tennessee, USA. 2. Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA. 3. Department of Biostatistics, Vanderbilt University Medical Center, Nashville, Tennessee, USA. 4. Section of Surgical Sciences, Departments of Surgery & Neurosurgery, Division of Trauma, Surgical Critical Care, and Emergency General Surgery, Nashville, Tennessee, USA. 5. Geriatric Research and Education Clinical Center, Surgical Services, Veteran Affairs Tennessee Valley Healthcare System, Nashville, Tennessee, USA.
Abstract
OBJECTIVE: 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. MATERIALS AND METHODS: This study focused on the EHR data for all adults admitted to Vanderbilt University Medical Center in 2019. We learned multiple advanced models to assess the value that EHR audit log data adds to the daily prediction of discharge likelihood within 24 h and to compare different representation strategies. We applied Shapley additive explanations to identify the most influential types of user-EHR interactions for discharge prediction. RESULTS: The data include 26 283 inpatient stays, 133 398 patient-day observations, and 819 types of user-EHR interactions. The model using the count of each type of interaction in the recent 24 h and other commonly used features, including demographics and admission diagnoses, achieved the highest area under the receiver operating characteristics (AUROC) curve of 0.921 (95% CI: 0.919-0.923). By contrast, the model lacking user-EHR interactions achieved a worse AUROC of 0.862 (0.860-0.865). In addition, 10 of the 20 (50%) most influential factors were user-EHR interaction features. CONCLUSION: EHR audit log data contain rich information such that it can improve hospital-wide discharge predictions.
OBJECTIVE: 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. MATERIALS AND METHODS: This study focused on the EHR data for all adults admitted to Vanderbilt University Medical Center in 2019. We learned multiple advanced models to assess the value that EHR audit log data adds to the daily prediction of discharge likelihood within 24 h and to compare different representation strategies. We applied Shapley additive explanations to identify the most influential types of user-EHR interactions for discharge prediction. RESULTS: The data include 26 283 inpatient stays, 133 398 patient-day observations, and 819 types of user-EHR interactions. The model using the count of each type of interaction in the recent 24 h and other commonly used features, including demographics and admission diagnoses, achieved the highest area under the receiver operating characteristics (AUROC) curve of 0.921 (95% CI: 0.919-0.923). By contrast, the model lacking user-EHR interactions achieved a worse AUROC of 0.862 (0.860-0.865). In addition, 10 of the 20 (50%) most influential factors were user-EHR interaction features. CONCLUSION: EHR audit log data contain rich information such that it can improve hospital-wide discharge predictions.
Authors: Brian G Arndt; John W Beasley; Michelle D Watkinson; Jonathan L Temte; Wen-Jan Tuan; Christine A Sinsky; Valerie J Gilchrist Journal: Ann Fam Med Date: 2017-09 Impact factor: 5.166
Authors: Scott R Levin; Eric T Harley; James C Fackler; Christoph U Lehmann; Jason W Custer; Daniel France; Scott L Zeger Journal: Crit Care Med Date: 2012-11 Impact factor: 7.598
Authors: Michelle R Hribar; Sarah Read-Brown; Isaac H Goldstein; Leah G Reznick; Lorinna Lombardi; Mansi Parikh; Winston Chamberlain; Michael F Chiang Journal: J Am Med Inform Assoc Date: 2018-01-01 Impact factor: 4.497