Explainable ML Predicts First-Pass Reperfusion in Stroke Thrombectomy

First-pass reperfusion (mTICI 2c-3) after a single device pass was achieved in 46% (94/204) of acute stroke thrombectomy patients. An explainable ML model (Random Forest) predicted FPE from collateral status, systolic BP, hypertension, age with best accuracy/specificity/F1; AdaB…

• Retrospective single-center study of 204 consecutive AIS patients (June 2021–June 2025) undergoing EVT; 19 clinical, imaging, and procedural variables analyzed.
• Collateral circulation, systolic BP, hypertension, and age were most influential per SHAP; non-linear relationship between BP and FPE observed.
• Limited events (94 FPEs), no external validation; findings preliminary—confirmation in multicenter cohorts needed before clinical use.

RadPigeon summaries are original and for information only. They are not clinical advice.