Purpose: Individual regions of the Alberta Stroke Programme Early CT Score (ASPECTS) may contribute differently to clinical symptoms in large vessel occlusion (LVO). This study aimed to investigate whether considering specific ASPECTS subregions improves predictive performance for clinical outcomes.

Methods: We analyzed a consecutive series of patients with LVO affecting the middle cerebral artery territory who underwent endovascular treatment (EVT) between January 2015 and July 2020. A multivariate logistic regression was performed to assess the individual impact of ASPECTS regions on good clinical outcome (defined as a modified Rankin scale score of 0–2 at 90 days). We trained machine-learning-driven logistic regression models to predict good clinical outcomes using i) cumulative ASPECTS and ii) location-specific ASPECTS. Performance was compared using deLong’s test. Additional analyses using binarized and linear clinical outcomes were performed to further assess the predictive value of individual ASPECTS regions and their combinations.

Results: Of 1109 patients (mean age 77.3 years ±11.6, 43.8% male), 419 achieved a good clinical outcome. The strongest effects on good clinical outcome in multivariate logistic regression were observed for the insula (OR 0.56, 95% CI 0.42–0.75) and M5 (OR 0.53, 95% CI 0.29–0.97) regions. Accuracy in predicting a good clinical outcome was similar when considering cumulative ASPECTS (ACC = 0.619, 95% CI 0.58–0.64) versus location-specific ASPECTS (ACC = 0.629, 95% CI 0.60–0.65; p = 0.933).

Conclusion: Cumulative ASPECTS assessment in LVO remains a stable and reliable predictor of clinical outcome and is not inferior to a weighted, location-specific ASPECTS assessment.