How Good Is Machine Learning in Predicting All-Cause 30-Day Hospital Readmission? Evidence From Administrative Data
How Good Is Machine Learning in Predicting All-Cause 30-Day Hospital Readmission? Evidence From Administrative Data
复制标题
DOI：
10.1016/j.jval.2020.06.009
复制
发表时间：
2020-10-01
期刊：
影响因子：
4.5
通讯作者：
Echevin, Damien
中科院分区：
文献类型：
--
作者：
Li, Qing;Yao, Xueqin;Echevin, Damien
目标：医院再入院是医疗保健系统的主要成本驱动因素，但现有的工作往往有穷人或中等的预测结果。尽管不同研究中可获得的信息不同，但改善预测与寻找重要的解释变量是不同的。这项研究具有大样本量和丰富的信息，探索了最先进的机器学习算法并展示了它们在预测中的性能。方法：使用1995年至2012年间来自魁北克的1，631，611名住院患者的管理数据，我们预测了30天入院和出院时再次入院的可能性。我们比较了传统逻辑回归、惩罚逻辑回归和最近的机器学习算法（如随机森林、深度学习和极端梯度提升）之间的性能。结果：在对训练集（80%的数据）进行10倍交叉验证后，机器学习在单独的保持测试集（20%的数据）上产生了非常好的结果。解释变量的重要性对于不同的算法是不一样的。受试者工作特征曲线下面积（AUC）入院时达到0.79以上，出院时达到0.88以上。包括许多不同类别的诊断代码是最具预测性的变量之一。带有惩罚的逻辑回归也产生了良好的结果，但标准逻辑回归在没有惩罚的情况下失败了。校准曲线证实了良好的结果。结论：虽然识别再入院风险最高的患者只是预防再入院的第一步，但机器学习可以高度预测30天内的再入院。
Objectives: Hospital readmission is a main cost driver for healthcare systems, but existing works often had poor or moderate predictive results. Although the available information differs in different studies, improving prediction is different from the search for important explanatory variables. With large sample size and abundant information, this study explores state-ofthe-art machine-learning algorithms and shows their performance in prediction.Methods: Using administrative data on 1 631 611 hospital stays from Quebec between 1995 and 2012, we predict the probability of 30-day readmission at hospital admission and discharge. We compare the performance between traditional logistic regression, logistic regression with penalization, and more recent machine-learning algorithms such as random forest, deep learning, and extreme gradient boosting.Results: After a 10-fold cross-validation on the training set (80% of the data), machine learning produced very good results on a separate hold-out test set (20% of the data). The importance of explanatory variables is not the same for different algorithms. The area under receiver operating characteristic curve (AUC) reached above 0.79 at hospital admission and above 0.88 at hospital discharge. Diagnostic codes, which include many different categories, are among the most predictive variables. Logistic regression with penalization also produced good results, but a standard logistic regression failed without penalization. The good results are confirmed by calibration curves.Conclusion: Although the identification of those at highest risk of readmission is just 1 step to preventing hospital readmissions, 30-day readmission is highly predictable with machine learning.