期刊
NPJ DIGITAL MEDICINE
卷 5, 期 1, 页码 -出版社
NATURE PORTFOLIO
DOI: 10.1038/s41746-022-00649-y
关键词
-
资金
- Wellcome Institutional Strategic Support Fund (ISSF) UCL and Partner Hospitals [BRC717/HI/RW/101440]
- NIHR UCLH Biomedical Research Centre HIGODS Theme [BRC824/HG/ZK/110420]
- National Institute for Health Research [AI_AWARD01786]
- NHSX
- Wellcome Trust [204841/Z/16/Z]
- National Institutes of Health Research (NIHR) [AI_AWARD01786] Funding Source: National Institutes of Health Research (NIHR)
Machine learning for hospital operations is not well studied. In this study, a prediction pipeline using live electronic health records from a UK teaching hospital's emergency department was developed to generate short-term probabilistic forecasts of emergency admissions. The models achieved good predictive performance depending on the elapsed visit time at the point of prediction.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据