A study on predicting the length of hospital stay for Chinese patients with ischemic stroke based on the XGBoost algorithm

作者：Rui Chen, Shengfa Zhang, Jie Li, Dongwei Guo, Weijun Zhang, Xiaoying Wang, Donghua Tian, Zhiyong Qu, Xiaohua Wang · 发表于：BMC Medical Informatics and Decision Making · 年份：2023 · DOI：10.1186/s12911-023-02140-4 · 被引用次数：38 · 研究领域：Acute Ischemic Stroke Management、Machine Learning in Healthcare、Artificial Intelligence in Healthcare

BACKGROUND: The incidence of stroke is a challenge in China, as stroke imposes a heavy burden on families, national health services, social services, and the economy. The length of hospital stay (LOS) is an essential indicator of utilization of medical services and is usually used to assess the efficiency of hospital management and patient quality of care. This study established a prediction model based on a machine learning algorithm to predict ischemic stroke patients' LOS. METHODS: A total of 18,195 ischemic stroke patients' electronic medical records and 28 attributes were extracted from electronic medical records in a large comprehensive hospital in China. The prediction of LOS was regarded as a multi classification problem, and LOS was divided into three categories: 1-7 days, 8-14 days and more than 14 days. After preprocessing the data and feature selection, the XGBoost algorithm was used to build a machine learning model. Ten fold cross-validation was used for model validation. The accuracy (ACC), recall rate (RE) and F1 measure were used to evaluate the performance of the prediction model of LOS of ischemic stroke patients. Finally, the XGBoost algorithm was used to identify and remove irrelevant features by ranking all attributes based on feature importance. RESULTS: Compared with the naive Bayesian algorithm, logistic region algorithm, decision tree classifier algorithm and ADaBoost classifier algorithm, the XGBoot algorithm has higher ACC, RE and F1 measure. The a...