Abstract Number: Esoc2026a1366 Early and 24-Hour Xgboost Models Predict 90-Day Functional Outcome in Posterior Circulation Thrombectomy: Derivation and External Validation of the “Forecast-Pc” Prediction Scores

View Full Paper

Ask AI

Bookmark

Share

Key Points

This research aims to create and validate prediction models for functional outcomes after endovascular treatment in posterior circulation strokes.
Included patients with posterior circulation stroke selected for EVT within 24 hours of last seen well with mRS ≤2.
Developed gradient-boosted decision tree models at four stages: baseline, pre-EVT, immediately post-EVT, and 24 hours post-EVT.
Performed derivation in 384 patients from 3 centers and external validation in 247 patients from 11 centers.
Among 384 patients, 173 (45%) had unfavorable outcomes at 90 days.
24-hour model demonstrated highest performance (AUC=0.89, p<0.001) compared to baseline and other stages.
Light models performed comparably to full models, with 24-hour NIHSS as the strongest predictor.

We only have this paper's title and publication details.

Develops and validates prediction scores for functional outcomes in posterior circulation stroke, suggesting reliable prognostic tools.

No takes yet. Share an insight, caveat, or question.

Salerno et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Share