Hospital systems, payers, and regulators have focused on reducing length of stay (LOS) and early readmission, with uncertain benefit. Interpretable machine learning (ML) may assist in transparently identifying the risk of important outcomes. We conducted a retrospective cohort study of hospitalizations at a tertiary academic medical center and its branches from January 2011 to May 2018. A consecutive sample of all hospitalizations in the study period were included. Algorithms were trained on medical, sociodemographic, and institutional variables to predict readmission, length of stay (LOS), and death within 48–72 h. Prediction performance was measured by area under the receiver operator characteristic curve (AUC), Brier score loss (BSL), which measures how well predicted probability matches observed probability, and other metrics. Interpretations were generated using multiple feature extraction algorithms. The study cohort included 1,485,880 hospitalizations for 708,089 unique patients (median age of 59 years, first and third quartiles (QI) [39, 73]; 55.6% female; 71% white). There were 211,022 30-day readmissions for an overall readmission rate of 14% (for patients ≥65 years: 16%). Median LOS, including observation and labor and delivery patients, was 2.94 days (QI [1.67, 5.34]), or, if these patients are excluded, 3.71 days (QI [2.15, 6.51]). Predictive performance was as follows: 30-day readmission (AUC 0.76/BSL 0.11); LOS > 5 days (AUC 0.84/BSL 0.15); death within 48–72 h (AUC 0.91/BSL 0.001). Explanatory diagrams showed factors that impacted each prediction.

医院系统、付款人和监管机构一直致力于减少住院时间 (LOS) 和提前再入院，但效果不确定。可解释的机器学习 (ML) 可能有助于透明地识别重要结果的风险。我们对 2011 年 1 月至 2018 年 5 月期间某三级学术医疗中心及其分支机构的住院情况进行了回顾性队列研究。纳入了研究期间所有住院情况的连续样本。对算法进行医学、社会人口统计学和机构变量的训练，以预测 48-72 小时内的再入院、住院时间 (LOS) 和死亡。预测性能通过接受者操作特征曲线 (AUC) 下的面积、Brier 得分损失 (BSL)（衡量预测概率与观测概率的匹配程度）以及其他指标来衡量。使用多种特征提取算法生成解释。该研究队列包括 708,089 名独特患者（中位年龄 59 岁，第一和第三四分位数 (QI) [39, 73]；55.6% 女性；71% 白人），共 1,485,880 名住院患者。30 天再入院人数为 211,022 人，总体再入院率为 14%（≥65 岁患者：16%）。包括观察和待产患者在内的中位 LOS 为 2.94 天 (QI [1.67, 5.34])，或者，如果排除这些患者，则为 3.71 天 (QI [2.15, 6.51])。预测表现如下：30 天再入院（AUC 0.76/BSL 0.11）；LOS > 5 天（AUC 0.84/BSL 0.15）；48-72 小时内死亡（AUC 0.91/BSL 0.001）。解释图显示了影响每个预测的因素。