Development and validation of machine learning models for venous thromboembolism risk assessment at admission: a retrospective study

Frontiers in Cardiovascular Medicine

Cardiovascular Medicine

Xiaoli Wang¹  Wenxiang Xu²  Wenbo Sheng²  Zedong Hao²  Handong Ma²  Shaodian Zhang³ 

[1]Pudong Institute for Health Development, Shanghai, China

[2]Research and Development Department, Shanghai Synyi Medical Technology Co., Ltd., Shanghai, China

[3]Research and Development Department, Shanghai Synyi Medical Technology Co., Ltd., Shanghai, China

[4]Division of Medical Affairs, Shanghai Tenth People's Hospital, Shanghai, China

关键词: venous thromboembolism;    risk assessment model;    machine learning;    predictive modeling;    risk stratification;   

DOI  :  10.3389/fcvm.2023.1198526

 received in 2023-04-01, accepted in 2023-08-10,  发布年份 2023

来源: Frontiers

【 摘 要 】

IntroductionVenous thromboembolism (VTE) risk assessment at admission is of great importance for early screening and timely prophylaxis and management during hospitalization. The purpose of this study is to develop and validate novel risk assessment models at admission based on machine learning (ML) methods.MethodsIn this retrospective study, a total of 3078 individuals were included with their Caprini variables within 24 hours at admission. Then several ML models were built, including logistic regression (LR), random forest (RF), and extreme gradient boosting (XGB). The prediction performance of ML models and the Caprini risk score (CRS) was then validated and compared through a series of evaluation metrics.ResultsThe values of AUROC and AUPRC were 0.798 and 0.303 for LR, 0.804 and 0.360 for RF, and 0.796 and 0.352 for XGB, respectively, which outperformed CRS significantly (0.714 and 0.180, P < 0.001). When prediction scores were stratified into three risk levels for application, RF could obtain more reasonable results than CRS, including smaller false positive alerts and larger lower-risk proportions. The boosting results of stratification were further verified by the net-reclassification-improvement (NRI) analysis.DiscussionThis study indicated that machine learning models could improve VTE risk prediction at admission compared with CRS. Among the ML models, RF was found to have superior performance and great potential in clinical practice.

【 授权许可】

Unknown   
© 2023 Sheng, Wang, Xu, Hao, Ma and Zhang.