An explainable XGBoost machine learning model predicted incident in-hospital venous thromboembolism in older adults with a test AUC of 0.712.
Observational (n=28,231)
Does a machine learning-based risk prediction model accurately predict incident in-hospital VTE in hospitalized older adult patients?
An explainable XGBoost machine learning model demonstrated moderate discriminative ability (test AUC 0.712) for predicting incident in-hospital VTE in older adults, potentially aiding in individualized thromboprophylaxis.
Effect estimate: Test AUC 0.712
Venous thromboembolism (VTE) is a leading preventable cause of in-hospital mortality in older adults, yet early risk stratification remains a key clinical challenge. This study aimed to develop and internally validate an explainable machine learning model for incident VTE prediction in hospitalized older adult patients. We enrolled 28,231 patients aged ≥65 years admitted between January 2023 and December 2024, excluding those with VTE on admission. The primary endpoint was imaging-confirmed incident in-hospital VTE. Patients were split into training/test sets (7:3) via outcome-stratified sampling. Missing data were handled with multivariate imputation by chained equations imputation (training set only). Five machine learning models were constructed with 10-fold cross-validation and hyperparameter tuning, evaluated by pooled area under the curve (AUC), calibration curves, and decision curve analysis, with SHAP for model interpretation. 1797 (6.38%) incident VTE events were recorded. XGBoost showed optimal performance, with a training AUC of 0.753 and a test AUC of 0.712, favorable calibration, and stable clinical net benefit. Top predictors included diabetic nephropathy, triglycerides, great saphenous vein varicosity, fatty liver, cerebrovascular accident and age. We developed and validated an explainable XGBoost model for VTE risk prediction in older inpatients, enabling early risk stratification to support individualized thromboprophylaxis. Multicenter prospective external validation is warranted for clinical implementation.
Zhou et al. (Fri,) conducted a observational in Venous thromboembolism (n=28,231). Machine learning-based risk prediction model (XGBoost) was evaluated on imaging-confirmed incident in-hospital VTE (Test AUC 0.712). An explainable XGBoost machine learning model predicted incident in-hospital venous thromboembolism in older adults with a test AUC of 0.712.