Acute imaging does not improve ASTRAL score's accuracy despite having a prognostic value

Abstract

Background The ASTRAL score was recently shown to reliably predict three-month functional outcome in patients with acute ischemic stroke. Aim The study aims to investigate whether information from multimodal imaging increases ASTRAL score's accuracy. Methods All patients registered in the ASTRAL registry until March 2011 were included. In multivariate logistic-regression analyses, we added covariates derived from parenchymal, vascular, and perfusion imaging to the 6-parameter model of the ASTRAL score. If a specific imaging covariate remained an independent predictor of three-month modified Rankin score>2, the area-under-the-curve (AUC) of this new model was calculated and compared with ASTRAL score's AUC. We also performed similar logistic regression analyses in arbitrarily chosen patient subgroups. Results When added to the ASTRAL score, the following covariates on admission computed tomography/magnetic resonance imaging-based multimodal imaging were not significant predictors of outcome: any stroke-related acute lesion, any nonstroke-related lesions, chronic/subacute stroke, leukoaraiosis, significant arterial pathology in ischemic territory on computed tomography angiography/magnetic resonance angiography/Doppler, significant intracranial arterial pathology in ischemic territory, and focal hypoperfusion on perfusion-computed tomography. The Alberta Stroke Program Early CT score on plain imaging and any significant extracranial arterial pathology on computed tomography angiography/magnetic resonance angiography/Doppler were independent predictors of outcome (odds ratio: 093, 95% CI: 087-099 and odds ratio: 149, 95% CI: 108-205, respectively) but did not increase ASTRAL score's AUC (0849 vs. 0850, and 08563 vs. 08564, respectively). In exploratory analyses in subgroups of different prognosis, age or stroke severity, no covariate was found to increase ASTRAL score's AUC, either. Conclusions The addition of information derived from multimodal imaging does not increase ASTRAL score's accuracy to predict functional outcome despite having an independent prognostic value. More selected radiological parameters applied in specific subgroups of stroke patients may add prognostic value of multimodal imaging.