Duke University School of Medicine, Durham, NC; Duke Institute of Health Innovation, Durham, NC.
Duke Institute of Health Innovation, Durham, NC.
Ann Emerg Med. 2021 Aug;78(2):290-302. doi: 10.1016/j.annemergmed.2021.02.029. Epub 2021 May 8.
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.
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.
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.
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.
本研究旨在开发和验证两个机器学习模型，这些模型使用电子病历中的历史和当前就诊患者数据，预测患者在急诊科就诊期间每小时（最多 24 小时）入住住院部或 ICU 的概率。次要目标是为这些机器学习模型的实际应用提供框架。
从 2015 年 8 月 1 日至 2018 年 10 月 31 日期间，从一家大型学术医疗系统的 3 个急诊科（1 个学术性和 2 个社区性急诊科）的 468167 名成年患者就诊中整理数据。使用 2019 年 1 月 1 日至 2019 年 12 月 31 日期间的就诊数据验证模型。开发了一个操作型用户仪表板，并在实时就诊数据上运行模型。
对于中级入院模型，接受者操作特征曲线下的面积为 0.873，精度-召回曲线下的面积为 0.636。对于 ICU 入院模型，接受者操作特征曲线下的面积为 0.951，精度-召回曲线下的面积为 0.461。这些模型在学术性和社区性环境中以及在 2019 年和实时就诊数据中都具有相似的性能。
开发了机器学习模型，以便在患者在急诊科就诊的整个过程中准确预测住院或 ICU 入院的概率，而不仅仅是在分诊时。这些模型对于超出初始训练数据时间段的患者队列仍然准确，并且集成到实时电子病历数据上运行，具有相似的性能。
