Ebinger Joseph, Wells Matthew, Ouyang David, Davis Tod, Kaufman Noy, Cheng Susan, Chugh Sumeet
Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
Enterprise Data Intelligence, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
Intell Based Med. 2021;5:100035. doi: 10.1016/j.ibmed.2021.100035. Epub 2021 May 27.
The COVID-19 pandemic has placed unprecedented strain on the healthcare system, particularly hospital bed capacity in the setting of large variations in patient length of stay (LOS). Using electronic health record data from 966 COVID-19 patients at a large academic medical center, we developed three machine learning algorithms to predict the likelihood of prolonged LOS, defined as >8 days. The models included 353 variables and were trained on 80% of the cohort, with 20% used for model validation. The three models were created on hospital days 1, 2 and 3, each including information available at or before that point in time. The models' predictive capabilities improved sequentially over time, reaching an accuracy of 0.765, with an AUC of 0.819 by day 3. These models, developed using readily available data, may help hospital systems prepare for bed capacity needs, and help clinicians counsel patients on their likelihood of prolonged hospitalization.
新冠疫情给医疗系统带来了前所未有的压力，尤其是在患者住院时长差异很大的情况下，医院床位容量面临巨大挑战。我们利用一家大型学术医疗中心966名新冠患者的电子健康记录数据，开发了三种机器学习算法，以预测住院时长延长（定义为超过8天）的可能性。这些模型包含353个变量，并在该队列80%的数据上进行训练，20%的数据用于模型验证。这三个模型分别在住院第1天、第2天和第3天创建，每个模型都包含在该时间点或之前可用的信息。随着时间的推移，这些模型的预测能力逐步提高，到第3天准确率达到0.765，曲线下面积（AUC）为0.819。这些使用现成数据开发的模型，可能有助于医院系统为床位容量需求做好准备，并帮助临床医生就患者延长住院的可能性向患者提供咨询。
