Background: With the expanding eligibility for endovascular therapy (EVT) of patients presenting in the late window (6-24 hours after last known well), we aimed to derive a score to predict favorable outcomes associated with EVT versus best medical management.

Methods and results: A multinational observational cohort of patients from the CLEAR (Computed Tomography for Late Endovascular Reperfusion) study with proximal intracranial occlusion (2014-2022) was queried (n=58 sites). Logistic regression analyses were used to derive a 9-point score for predicting good functional outcome (modified Rankin Scale score 0-2 or return to premorbid modified Rankin Scale score) at 90 days, with sensitivity analyses for prespecified subgroups conducted using bootstrapped random forest regressions. Secondary outcomes included 90-day functional independence (modified Rankin Scale score 0-2), poor outcome (modified Rankin Scale score 5-6), and 90-day survival. The score was externally validated with a single-center cohort (2014-2023). Of the 3231 included patients (n=2499 EVT), a 9-point score included age, early computed tomography ischemic changes, and stroke severity, with higher points indicating a higher probability of a good functional outcome. The areas under the curve for the primary outcome among EVT and best medical management subgroups were 0.72 (95% CI, 0.70-0.74) and 0.87 (95% CI, 0.84-0.90), respectively, with similar performance in the external validation cohort (area under the curve, 0.71 [95% CI, 0.66-0.76]). There was a significant interaction between the score and EVT for good functional outcome, functional independence, and poor outcome (all Pinteraction<0.001), with greater benefit favoring patients with lower and midrange scores.

Conclusions: This score is a pragmatic tool that can estimate the probability of a good outcome with EVT in the late window.

Registration: URL: https://www.Clinicaltrials.gov; Unique identifier: NCT04096248.