Early sepsis mortality prediction model based on interpretable machine learning approach: development and validation study

doi:10.1007/s11739-024-03732-2

科研成果详情

题名	Early sepsis mortality prediction model based on interpretable machine learning approach: development and validation study
作者	Wang, Yiping1; Gao, Zhihong2; Zhang, Yang 2; Lu, Zhongqiu1; Sun, Fangyuan 2
发表日期	2024-08-14
发表期刊	INTERNAL AND EMERGENCY MEDICINE 影响因子和分区
语种	英语
原始文献类型	Article ; Early Access
关键词	Machine learning Artificial intelligence XGBoost Mortality prediction model Sepsis Septic shock
其他关键词	INTERNATIONAL CONSENSUS DEFINITIONS ; LOGISTIC-REGRESSION
摘要	Sepsis triggers a harmful immune response due to infection, causing high mortality. Predicting sepsis outcomes early is vital. Despite machine learning's (ML) use in medical research, local validation within the Medical Information Mart for Intensive Care IV (MIMIC-IV) database is lacking. We aimed to devise a prognostic model, leveraging MIMIC-IV data, to predict sepsis mortality and validate it in a Chinese teaching hospital. MIMIC-IV provided patient data, split into training and internal validation sets. Four ML models logistic regression (LR), support vector machine (SVM), deep neural networks (DNN), and extreme gradient boosting (XGBoost) were employed. Shapley additive interpretation offered early and interpretable mortality predictions. Area under the ROC curve (AUROC) gaged predictive performance. Results were cross verified in a Chinese teaching hospital. The study included 27,134 sepsis patients from MIMIC-IV and 487 from China. After comparing, 52 clinical indicators were selected for ML model development. All models exhibited excellent discriminative ability. XGBoost surpassed others, with AUROC of 0.873 internally and 0.844 externally. XGBoost outperformed other ML models (LR: 0.829; SVM: 0.830; DNN: 0.837) and clinical scores (Simplified Acute Physiology Score II: 0.728; Sequential Organ Failure Assessment: 0.728; Oxford Acute Severity of Illness Score: 0.738; Glasgow Coma Scale: 0.691). XGBoost's hospital mortality prediction achieved AUROC 0.873, sensitivity 0.818, accuracy 0.777, specificity 0.768, and F1 score 0.551. We crafted an interpretable model for sepsis death risk prediction. ML algorithms surpassed traditional scores for sepsis mortality forecast. Validation in a Chinese teaching hospital echoed these findings.
资助项目	Key Research and Development Program of Zhejiang Province
出版者	SPRINGER-VERLAG ITALIA SRL
ISSN	1828-0447
EISSN	1970-9366
DOI	10.1007/s11739-024-03732-2
页数	10
WOS类目	Medicine, General & Internal
WOS研究方向	General & Internal Medicine
WOS记录号	WOS:001291546300002
收录类别	SCIE ; PUBMED
URL	查看原文
PubMed ID	39141286
通讯作者地址	[Lu, Zhongqiu]WenZhou Med Univ, Affiliated Hosp 1, Dept Emergency, Wenzhou 325000, Peoples R China. ; [Sun, Fangyuan]WenZhou Med Univ, Affiliated Hosp 1, Dept Comp Technol & Informat Management, Wenzhou 325000, Peoples R China.
引用统计
文献类型	期刊论文
条目标识符	https://kms.wmu.edu.cn/handle/3ETUA0LF/217496
专题	附属第一医院附属第一医院_急诊科附属第一医院_计算机技术与信息管理处
通讯作者	Lu, Zhongqiu; Sun, Fangyuan
作者单位	1.WenZhou Med Univ, Affiliated Hosp 1, Dept Emergency, Wenzhou 325000, Peoples R China; 2.WenZhou Med Univ, Affiliated Hosp 1, Dept Comp Technol & Informat Management, Wenzhou 325000, Peoples R China
第一作者单位	附属第一医院; 急诊科
通讯作者单位	附属第一医院; 急诊科; 计算机技术与信息管理处
第一作者的第一单位	附属第一医院
推荐引用方式 GB/T 7714	Wang, Yiping,Gao, Zhihong,Zhang, Yang,et al. Early sepsis mortality prediction model based on interpretable machine learning approach: development and validation study[J]. INTERNAL AND EMERGENCY MEDICINE,2024.
APA	Wang, Yiping, Gao, Zhihong, Zhang, Yang, Lu, Zhongqiu, & Sun, Fangyuan. (2024). Early sepsis mortality prediction model based on interpretable machine learning approach: development and validation study. INTERNAL AND EMERGENCY MEDICINE.
MLA	Wang, Yiping,et al."Early sepsis mortality prediction model based on interpretable machine learning approach: development and validation study".INTERNAL AND EMERGENCY MEDICINE (2024).