Machine Learning Predicts VTE From Blood Genes

Researchers report in JMIR Medical Informatics (2026) a VTE prediction study using whole-blood gene expression and 20 machine-learning algorithms. They trained models on GSE19151 (70 VTE, 63 controls) and validated on GSE48000 (107 VTE, 25 controls); nine algorithms achieved external AUCs above 0.75 while k-nearest neighbor underperformed. The authors suggest combining these models with D-dimer testing could enhance VTE diagnostic accuracy.
Scoring Rationale
Solid external validation and journal publication drive score, but moderate novelty and limited cohort sizes constrain impact.
Practice interview problems based on real data
1,500+ SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems

