Abstract
PURPOSE: This study aimed to evaluate the predictive value of automatically assessed collateral circulation (CC) and infarct core for functional outcome in acute ischemic stroke (AIS) patients treated with endovascular thrombectomy (EVT). METHODS: We conducted a retrospective cohort study of 208 patients with anterior large vessel occlusion treated with EVT. Two AI-powered software were used to automatically assess CC and infarct core. Comparative analyses included patient demographics, clinical and imaging data, and functional outcome. Univariate and multivariable logistic regression analyses were conducted to predict the 90-day functional outcome. A favorable outcome was defined as a modified Rankin scale (mRS) score ≤ 2. RESULTS: Among the 208 patients, 114 (54.8%) were women and 94 were men, with a mean age of 71.4 ± 13.3 years. Patients with higher collateral score (CS) exhibited lower infarct core volumes (p < 0.001) and better mRS score at 90 days (p = 0.008). Among patients with a favorable outcome, the mean infarct core volume was lower compared to those with poor outcomes (5 mL vs. 8.6 mL, p = 0.003). In univariate logistic regression, both infarct core (OR 0.94, p = 0.005) and CS (OR 1.84, p = 0.014) were predictors of favorable outcome. However, in multivariable models, only infarct core remained a significant independent predictor [AORs of 0.95 (p = 0.021) and 0.96 (p = 0.039)]. CONCLUSION: Automatically assessed infarct core is a robust predictor of functional outcome in AIS patients post-EVT, while CS's predictive value diminishes when adjusted for infarct core. These findings support the integration of AI-powered evaluations in clinical settings to improve prognosis and treatment strategies for AIS.