Home »
Academic Articles »
C »
Machine learning for real-time aggregated prediction of hospital admission for emergency patients
Machine learning for real-time aggregated prediction of hospital admission for emergency patients
Zella King
(Clinical Operational Research Unit, University College London)
Joseph Farrington
(Institute of Health Informatics, University College London)
Martin Utley
(Clinical Operational Research Unit, University College London)
Enoch Kung
(Clinical Operational Research Unit, University College London)
Samer Elkhodair
(University College London Hospitals NHS Foundation Trust)
Steve Harris
(University College London Hospitals NHS Foundation Trust)
Richard Sekula
(University College London Hospitals NHS Foundation Trust)
Jonathan Gillham
(University College London Hospitals NHS Foundation Trust)
Kezhi Li
(Institute of Health Informatics, University College London)
Sonya Crowe
(Clinical Operational Research Unit, University College London)
Journal: npj Digital Medicine
•
• Nature Portfolio
• ISSN: 2398-6352
Abstract
Abstract Machine learning for hospital operations is under-studied. We present a prediction pipeline that uses live electronic health-records for patients in a UK teaching hospital’s emergency department (ED) to generate short-term, probabilistic forecasts of emergency admissions. A set of XGBoost classifiers applied to 109,465 ED visits yielded AUROCs from 0.82 to 0.90 depending on elapsed visit-time at the point of prediction. Patient-level probabilities of admission were aggregated to forecast the number of admissions among current ED patients and, incorporating patients yet to arrive, total emergency admissions within specified time-windows. The pipeline gave a mean absolute error (MAE) of 4.0 admissions (mean percentage error of 17%) versus 6.5 (32%) for a benchmark metric. Models developed with 104,504 later visits during the Covid-19 pandemic gave AUROCs of 0.68–0.90 and MAE of 4.2 (30%) versus a 4.9 (33%) benchmark. We discuss how we surmounted challenges of designing and implementing models for real-time use, including temporal framing, data preparation, and changing operational conditions.
Zella King, Joseph Farrington, Martin Utley, et al. (2022). "Machine learning for real-time aggregated prediction of hospital admission for emergency patients". npj Digital Medicine. https://doi.org/10.1038/s41746-022-00649-y