Open access
Jul 2026
A machine learning-based risk prediction model for Hospitalized patients with deep vein thrombosis
An internally validated ML model for early DVT risk prediction using seven routine clinical variables was developed and identified D-dimer as the most influential predictor; Random Forest achieved the best performance and identified D-dimer as the most influential predictor.
Xue Wang, Xiankai Chen, Jun Mao et al.
· PeerJ · 0 citations