Development of a prediction model for the risk of 30-day unplanned readmission in older patients with heart failure: A multicenter retrospective study

作者全名："Zhang, Yang; Wang, Haolin; Yin, Chengliang; Shu, Tingting; Yu, Jie; Jian, Jie; Jian, Chang; Duan, Minjie; Kadier, Kaisaierjiang; Xu, Qian; Wang, Xueer; Xiang, Tianyu; Liu, Xiaozhu"

作者地址："[Zhang, Yang; Wang, Haolin; Jian, Jie; Jian, Chang; Duan, Minjie; Liu, Xiaozhu] Chongqing Med Univ, Coll Med Informat, Chongqing, Peoples R China; [Zhang, Yang; Jian, Jie; Jian, Chang; Duan, Minjie; Liu, Xiaozhu] Chongqing Med Univ, Med Data Sci Acad, Chongqing, Peoples R China; [Yin, Chengliang] Macau Univ Sci & Technol, Fac Med, Taipa 999078, Macao, Peoples R China; [Shu, Tingting] Army Med Univ, Mil Med Univ 3, Chongqing, Peoples R China; [Yu, Jie] Qingdao Univ, Affiliated Taian City Cent Hosp, Dept Med Imaging, Tai An 271000, Peoples R China; [Kadier, Kaisaierjiang] Xinjiang Med Univ, Affiliated Hosp 1, Dept Cardiol, Urumqi, Peoples R China; [Xu, Qian] Chongqing Med Univ, Collect Dev Dept Lib, Chongqing, Peoples R China; [Wang, Xueer] Guangxi Med Univ, Coll Oncol, Nanning 530022, Peoples R China; [Xiang, Tianyu] Chongqing Med Univ, Univ Town Hosp, Informat Ctr, Chongqing, Peoples R China; [Liu, Xiaozhu] 288 Tiantian Ave, Chongqing, Peoples R China"

通信作者："Xiang, TY (通讯作者)，Chongqing Med Univ, Univ Town Hosp, Informat Ctr, Chongqing, Peoples R China.; Liu, XZ (通讯作者)，288 Tiantian Ave, Chongqing, Peoples R China."

来源：NUTRITION METABOLISM AND CARDIOVASCULAR DISEASES

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:001080061500001

JCR分区：Q2

影响因子：3.3

年份：2023

卷号：33

期号：10

开始页：1878

结束页：1887

文献类型：Article

关键词：Heart failure; Machine learning; Unplanned; Predictive model; readmission

摘要："Background and aim: Heart failure (HF) imposes significant global health costs due to its high incidence, readmission, and mortality rate. Accurate assessment of readmission risk and precise interventions have become important measures to improve health for patients with HF. Therefore, this study aimed to develop a machine learning (ML) model to predict 30-day unplanned readmissions in older patients with HF.Methods and results: This study collected data on hospitalized older patients with HF from the medical data platform of Chongqing Medical University from January 1, 2012, to December 31, 2021. A total of 5 candidate algorithms were selected from 15 ML algorithms with excellent performance, which was evaluated by area under the operating characteristic curve (AUC) and accuracy. Then, the 5 candidate algorithms were hyperparameter tuned by 5-fold crossvalidation grid search, and performance was evaluated by AUC, accuracy, sensitivity, specificity, and recall. Finally, an optimal ML model was constructed, and the predictive results were explained using the SHapley Additive exPlanations (SHAP) framework. A total of 14,843 older patients with HF were consecutively enrolled. CatBoost model was selected as the best prediction model, and AUC was 0.732, with 0.712 accuracy, 0.619 sensitivity, and 0.722 specificity. NT.proBNP, length of stay (LOS), triglycerides, blood phosphorus, blood potassium, and lactate dehydrogenase had the greatest effect on 30-day unplanned readmission in older patients with HF, according to SHAP results. Conclusions: The study developed a CatBoost model to predict the risk of unplanned 30-day special-cause readmission in older patients with HF, which showed more significant performance compared with the traditional logistic regression model. 2023 The Italian Diabetes Society, the Italian Society for the Study of Atherosclerosis, the Italian Society of Human Nutrition and the Department of Clinical Medicine and Surgery, Federico II University. Published by Elsevier B.V. All rights reserved."

基金机构：Special key project of technological innovation and application development in Chongqing [CSTB2022TIAD-KPX0169]; Joint key projects of the Science and Technology Commission [2019ZDXM036]; Independent research project of Medical Engineering Laboratory of Chinese PLA General Hospital [2022SYSZZKY26]

基金资助正文："Special key project of technological innovation and application development in Chongqing (CSTB2022TIAD-KPX0169) and Joint key projects of the Science and Technology Commission (2019ZDXM036) . Independent research project of Medical Engineering Laboratory of Chinese PLA General Hospital (grant number 2022SYSZZKY26) . The funding source had no role in the design of our analyses, its interpretation, or the decision to submit the manuscript for publication."