医学
单变量
凝血病
重症监护室
置信区间
急诊医学
败血症
单变量分析
死亡率
入射(几何)
百分位
特征选择
集合预报
重症监护医学
内科学
统计
多元分析
机器学习
多元统计
计算机科学
物理
数学
光学
作者
X. Liu,Hao Niu,Jiahua Peng
出处
期刊:Medicine
[Ovid Technologies (Wolters Kluwer)]
日期:2024-04-05
卷期号:103 (14): e37634-e37634
标识
DOI:10.1097/md.0000000000037634
摘要
The incidence of sepsis-induced coagulopathy (SIC) is high, leading to increased mortality rates and prolonged hospitalization and intensive care unit (ICU) stays. Early identification of SIC patients at risk of in-hospital mortality can improve patient prognosis. The objective of this study is to develop and validate machine learning (ML) models to dynamically predict in-hospital mortality risk in SIC patients. A ML model is established based on the Medical Information Mart for Intensive Care IV (MIMIC-IV) database to predict in-hospital mortality in SIC patients. Utilizing univariate feature selection for feature screening. The optimal model was determined by calculating the area under the curve (AUC) with a 95% confidence interval (CI). The optimal model was interpreted using Shapley Additive Explanation (SHAP) values. Among the 3112 SIC patients included in MIMIC-IV, a total of 757 (25%) patients experienced mortality during their ICU stay. Univariate feature selection helps us to pick out the 20 most critical variables from the original feature. Among the 10 developed machine learning models, the stacking ensemble model exhibited the highest AUC (0.795, 95% CI: 0.763–0.827). Anion gap and age emerged as the most significant features for predicting the mortality risk in SIC. In this study, an ML model was constructed that exhibited excellent performance in predicting in-hospital mortality risk in SIC patients. Specifically, the stacking ensemble model demonstrated superior predictive ability.
科研通智能强力驱动
Strongly Powered by AbleSci AI