A machine learning-based risk prediction model for Hospitalized patients with deep vein thrombosis
Open Access
Abstract
Background: Deep vein thrombosis (DVT) is a common thrombotic condition with substantial morbidity when not identified early. Machine learning (ML)–based predictive models may improve early identification of patients at high risk for DVT, but few clinically applicable early-risk models exist. Objectives: To develop and internally validate a ML model using routinely available clinical and laboratory indicators for early risk prediction of DVT, and to identify the most influential predictors using model explainability techniques. Methods: We retrospectively analyzed clinical data from 231 patients evaluated at the Fifth Affiliated Hospital of Southern Medical University between January 2017 and June 2024. Patients were labeled as DVT occurrence ( n = 159) or non-occurrence ( n = 72). Seven candidate predictors were selected by Least Absolute Shrinkage and Selection Operator (LASSO) regression. The dataset was split into training (70%, n = 162) and test (30%, n = 69) sets. Five ML algorithms were trained: XGBoost, CatBoost, Random Forest (RF), Logistic Regression, and Support Vector Machine, with hyperparameter tuning on the training set. Model performance was assessed by 5-fold cross-validation and on the held-out test set using Area Under the Receiver Operating Characteristic Curve (AUC), accuracy, recall, and F1 score. The best model was further interpreted via feature importance and Shapley Additive Explanations (SHAP). Results: LASSO selected seven predictors: hemoglobin, platelet count, leukocyte count, fibrinogen, prothrombin time, D-dimer (DD), and glucose. The Random Forest model showed the best discrimination (test-set AUC = 0.874), with favorable accuracy, recall, and F1 compared with other classifiers (detailed metrics reported in the manuscript). In the RF model, D-dimer had the highest feature-importance contribution; SHAP analysis confirmed DD as the dominant risk driver and characterized the directions and relative effects of other features. Conclusions: We developed an internally validated ML model for early DVT risk prediction using seven routine clinical variables; Random Forest achieved the best performance and identified D-dimer as the most influential predictor. This model may support earlier identification and intervention for patients at risk of DVT, pending external validation and prospective evaluation.Keywords
Funding Information
- President Foundation of The Fifth Affiliated Hospital, Southern Medical University (YZ2023ZX01)
This publication has 40 references indexed in Scilit:
- Artificial intelligence in clinical thrombosis and hemostasis: A reviewResearch and Practice in Thrombosis and Haemostasis, 2025
- Optimizing resource allocation: Cost-effectiveness of specified D-dimer cut-offs in cancer patients with suspected venous thromboembolismJournal of Thrombosis and Thrombolysis, 2024
- Machine learning prediction model of major adverse outcomes after pediatric congenital heart surgery: a retrospective cohort studyInternational Journal of Surgery, 2024
- Risk prediction models for deep venous thrombosis in patients with acute stroke: A systematic review and meta-analysisInternational Journal of Nursing Studies, 2023
- A review on longitudinal data analysis with random forestBriefings in Bioinformatics, 2023
- Machine learning predicts cancer-associated venous thromboembolism using clinically available variables in gastric cancer patientsHeliyon, 2023
- Pearson's goodness-of-fit tests for sparse distributionsJournal of Applied Statistics, 2021
- Effect of testing for cancer on cancer- or venous thromboembolism (VTE)-related mortality and morbidity in people with unprovoked VTECochrane Database of Systematic Reviews, 2021
- Comparison of machine learning and logistic regression models in predicting acute kidney injury: A systematic review and meta-analysisInternational Journal of Medical Informatics, 2021
- A Test in Context: D-DimerJACC, 2017