预测急诊科患者收入普通病房或重症监护病房的机器学习模型的开发与验证
本研究使用2015年8月1日至2018年10月31日期间3家急诊科(1家学术型、2家社区型)的468,167例成人就诊数据,开发了2个机器学习模型,分别预测患者收入普通病房或ICU的概率,并利用2019年1月1日至12月31日的就诊数据进行验证。模型在急诊就诊全程每小时(至24小时)进行预测,而非仅在分诊时。收入普通病房模型的受试者工作特征曲线下面积为0.873,精确率-召回率曲线下面积为0.636;收入ICU模型的受试者工作特征曲线下面积为0.951,精确率-召回率曲线下面积为0.461。模型在学术型与社区型急诊科、2019年验证数据及实时电子健康记录数据中表现相似。研究还开发了操作仪表盘,使模型可在实时数据上运行。
要点
- 收入普通病房模型:受试者工作特征曲线下面积0.873,精确率-召回率曲线下面积0.636。
- 收入ICU模型:受试者工作特征曲线下面积0.951,精确率-召回率曲线下面积0.461。
- 模型在急诊就诊全程每小时(至24小时)预测收入普通病房或ICU的概率,而非仅在分诊时。
- 模型在学术型与社区型急诊科、2019年验证数据及实时电子健康记录数据中表现相似。
- 研究基于3家急诊科468,167例成人就诊数据开发,并开发了操作仪表盘在实时数据上运行。
适用人群与场景
- 3家急诊科(1家学术型、2家社区型)的成人患者就诊,数据来自大型学术健康系统。
研究设计与关键结果
- 研究类型:模型开发与验证研究;样本量:468,167例成人就诊;中心数:3家急诊科(1家学术型、2家社区型)。
- 数据来源:2015年8月1日至2018年10月31日电子健康记录数据用于开发;2019年1月1日至12月31日数据用于验证。
- 收入普通病房模型:受试者工作特征曲线下面积0.873,精确率-召回率曲线下面积0.636。
- 收入ICU模型:受试者工作特征曲线下面积0.951,精确率-召回率曲线下面积0.461。
- 模型在学术型与社区型急诊科、2019年验证数据及实时数据中表现相似。
- 开发了操作仪表盘,模型可在实时电子健康记录数据上运行。
证据类型、等级与局限
- 证据类型:模型开发与验证研究;局限:原文未报告局限性。
对床旁实践的改变
- 原文未据此给出推荐。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
STUDY OBJECTIVE: 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.
METHODS: 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.
RESULTS: 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.
CONCLUSION: 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.
参考来源
- Fenn A, Davis C, Buckland DM, et al. Development and Validation of Machine Learning Models to Predict Admission From Emergency Department to Inpatient and Intensive Care Units. Ann Emerg Med. 2021. PMID: 33972128. doi:10.1016/j.annemergmed.2021.02.029
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。