Jie Jin,1 Jie Lu,1 Xinyang Su,2 Yinhuan Xiong,3 Shasha Ma,4 Yang Kong,5 Hongmei Xu1 

1School of Nursing, Binzhou Medical University, Binzhou, People’s Republic of China; 2Department of Spine Surgery, Binzhou Medical University Hospital, Binzhou, People’s Republic of China; 3Department of Nursing, Binzhou People’s Hospital, Binzhou, People’s Republic of China; 4Department of Neurosurgery, Binzhou Medical University Hospital, Binzhou, People’s Republic of China; 5School of Health Management, Binzhou Medical University, Yantai, People’s Republic of China

Correspondence: Hongmei Xu, School of Nursing, Binzhou Medical University, No. 525 Huanghe 3rd Road, Binzhou, 256600, People’s Republic of China, Tel +86-13754689536, Email hmx58@163.com Yang Kong, School of Health Management, Binzhou Medical University, No. 346 Guanhai Road, Yantai, 264003, People’s Republic of China, Tel +86-13773576163, Email kongyang@bzmc.edu.cn

Purpose: The purpose of this study was to establish and validate machine learning-based models for predicting the risk of venous thromboembolism (VTE) in intensive care unit (ICU) patients.
Patients and Methods: The clinical data of 1494 ICU patients who underwent Doppler ultrasonography or venography between December 2020 and March 2023 were extracted from three tertiary hospitals. The Boruta algorithm was used to screen the essential variables associated with VTE. Five machine learning algorithms were employed: Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Gradient Boosting Decision Tree (GBDT), and Logistic Regression (LR). Hyperparameter optimization was conducted on the predictive model of the training dataset. The performance in the validation dataset was measured using indicators, including the area under curve (AUC) of the receiver operating characteristic (ROC) curve, specificity, and F1 score. Finally, the optimal model was interpreted using the SHapley Additive exPlanation (SHAP) package.
Results: The incidence of VTE among the ICU patients in this study was 26.04%. We screened 19 crucial features for the risk prediction model development. Among the five models, the RF model performed best, with an AUC of 0.788 (95% CI: 0.738– 0.838), an accuracy of 0.759 (95% CI: 0.709– 0.809), a sensitivity of 0.633, and a Brier score of 0.166.
Conclusion: A machine learning-based model for prediction of VTE in ICU patients were successfully developed, which could assist clinical medical staff in identifying high-risk populations for VTE in the early stages so that prevention measures can be implemented to reduce the burden on the ICU patients.

Keywords: venous thromboembolism, machine learning, algorithm, prediction model, intensive care unit