Explainable machine learning for predicting 30-day readmission in acute heart failure patients
Yang Zhang,
Tianyu Xiang,
Yanqing Wang,
Tingting Shu,
Chengliang Yin,
Huan Li,
Minjie Duan,
Mengyan Sun,
Binyi Zhao,
Kaisaierjiang Kadier,
Qian Xu,
Tao Ling,
Fanqi Kong,
Xiaozhu Liu
Affiliations
Yang Zhang
College of Medical Informatics, Chongqing Medical University, Chongqing, China; Medical Data Science Academy, Chongqing Medical University, Chongqing, China
Tianyu Xiang
Information Center, The University-Town Hospital of Chongqing Medical University, Chongqing, China
Yanqing Wang
The First Clinical College,Chongqing Medical University, Chongqing 400016, China
Tingting Shu
Army Medical University (Third Military Medical University), Chongqing, China
Chengliang Yin
Faculty of Medicine, Macau University of Science and Technology, Macau 999078, China
Huan Li
Chongqing College of Electronic Engineering, Chongqing, China
Minjie Duan
College of Medical Informatics, Chongqing Medical University, Chongqing, China; Medical Data Science Academy, Chongqing Medical University, Chongqing, China
Mengyan Sun
Harris Manchester College, Oxford, UK
Binyi Zhao
First Department of Medicine Medical Faculty Mannheim University Medical Centre Mannheim (UMM)University of Heidelberg, Mannheim, Germany
Kaisaierjiang Kadier
Department of Cardiology, First Affiliated Hospital of Xinjiang Medical University, Ürümqi, China
Qian Xu
Collection Development Department of Library, Chongqing Medical University, Chongqing, China
Tao Ling
Department of Pharmacy, Suqian First Hospital, Suqian, China; Corresponding author
Fanqi Kong
Department of Cardiology, The Third Affiliated Hospital of Wenzhou Medical University, Wenzhou, China; Corresponding author
Xiaozhu Liu
Medical Data Science Academy, Chongqing Medical University, Chongqing, China; Department of Critical Care Medicine, Beijing Shijitan Hospital, Capital Medical University, Beijing 100038, China; Corresponding author
Summary: We aimed to develop a machine-learning based predictive model to identify 30-day readmission risk in Acute heart failure (AHF) patients. In this study 2232 patients hospitalized with AHF were included. The variance inflation factor value and 5-fold cross-validation were used to select vital clinical variables. Five machine learning algorithms with good performance were applied to develop models, and the discrimination ability was comprehensively evaluated by sensitivity, specificity, and area under the ROC curve (AUC). Prediction results were illustrated by SHapley Additive exPlanations (SHAP) values. Finally, the XGBoost model performs optimally: the greatest AUC of 0.763 (0.703–0.824), highest sensitivity of 0.660, and high accuracy of 0.709. This study developed an optimal XGBoost model to predict the risk of 30-day unplanned readmission for AHF patients, which showed more significant performance compared with traditional logistic regression (LR) model.
