Explainable machine learning for predicting venous thromboembolism in septic shock patients.
Random forest model predicted venous thromboembolism in septic shock with AUC 0.97 externally
Explainable machine learning for predicting venous thromboembolism in septic shock patients.
Venous thromboembolism (venous thromboembolism) frequently complicates septic shock, yet precise, individualized risk stratification tools remain scarce.
This study aimed to develop and externally validate an explainable machine learning (machine learning) framework to predict venous thromboembolism in this critically ill population.
A retrospective cohort study was conducted including adult septic shock patients admitted between January 2020 and December 2025.
The venous thromboembolism incidence within the development cohort was 17.74% (130/733).
SHAP analysis revealed that heightened thrombo-inflammatory markers combined with abbreviated coagulation intervals fundamentally drove venous thromboembolism risk, offering personalized predictive insights via individual force plots.
We successfully established a highly accurate and interpretable Random Forest-based predictive model for venous thromboembolism in septic shock patients.
By leveraging six routine clinical biomarkers and SHAP-derived transparency, this tool bridges complex algorithmic forecasting with clinical intuition, providing a transparent risk assessment framework that may assist in risk stratification for thromboprophylaxis after prospective validation.
Future implementation studies are needed to assess its real-world clinical utility and impact on patient outcomes.