The combination of carotid plaques characteristics and white matter lesions burden may predict ischemic stroke severity in symptomatic patients

Motivation: Acute care decisions, such as the initiation of anticoagulant therapy, are affected by infarction degree. Goal(s): To assess the severity of ischemic stroke and prognosis in patients with symptomatic carotid artery stenosis, this study combined cerebral WMLs burden derived from FLAIR and carotid plaque characteristics based on HRVW-MRI to construct a noninvasive model. Approach: Logistic regression analysis and LASSO regression analysis were utilized to develop predictive nomogram model. Results: The AUC of predictive model was 0.92 in the training and 0.88 in the validation cohort, and showed good clinical utility. The hybrid model-derived score was an independent predictor of mRS score. Impact: The high discriminative ability indicates the potential of this model for classifying patients with nervous functional defect according to NIHSS score.The hybrid model-derived score is related to judge the neurological function recovery.