Background: The prognostic value of the neutrophil–lymphocyte ratio (NLR) in ischemic stroke remains debated due to cohort variability and treatment heterogeneity across studies. This study evaluates the relationship between admission NLR, stroke severity and 90-day outcomes in patients with anterior circulation large vessel occlusion (LVO) undergoing early, successful revascularization. Methods: A retrospective multicenter study was conducted with 1082 patients treated with mechanical thrombectomy for acute ischemic stroke. The relationship between admission NLR, baseline National Institutes of Health Stroke Scale (NIHSS), 24 h NIHSS and 90-day modified Rankin Scale (mRS) outcomes was analyzed using logistic regression. Results: Admission NLR correlated weakly but significantly with both baseline (p = 0.018) and 24 h (p = 0.005) NIHSS scores, reflecting stroke severity. However, multivariate analysis showed that higher 24 h NIHSS scores (OR 0.831, p = 0.000) and prolonged puncture-to-recanalization times (OR 0.981, p = 0.000) were independent predictors of poor 90-day outcomes, whereas NLR was not (p = 0.557). Conclusions: Admission NLR is associated with stroke severity but does not independently predict clinical outcomes at 90 days in patients achieving early and successful revascularization. These findings underscore the critical role of inflammation in the acute phase of stroke but suggest that its prognostic value for long-term outcomes is limited in this context.

Background/Objectives: The C-reactive protein-to-lymphocyte ratio (CLR) has emerged as an inflammatory biomarker reflecting innate and adaptive immune responses. Its prognostic value in acute ischemic stroke patients undergoing mechanical thrombectomy remains unclear. This study investigated whether CLR predicts functional outcome, mortality, and symptomatic intracranial hemorrhage (sICH). Methods: In this multicenter retrospective study, 714 patients with anterior circulation large-vessel occlusion treated with mechanical thrombectomy between January 2024 and January 2025 were analyzed. Clinical, angiographic, and laboratory data, including CLR, were collected. CLR was calculated as CRP divided by lymphocyte count/1000. Outcomes were 90-day modified Rankin Scale (mRS; poor outcome = 3–6; mortality = 6) and sICH per ECASS II. Receiver operating characteristic (ROC) analyses identified optimal CLR cut-offs. Logistic regression analyses determined independent predictors of outcomes. Results: sICH occurred in 39 patients (5.5%). CLR correlated with higher baseline NIHSS and lower ASPECTS. ROC analyses showed that CLR predicted poor functional outcome and mortality with an identical cut-off (≥7.51; AUCs 0.634 and 0.664), and demonstrated strong discrimination for sICH (cut-off ≥ 10.64; AUC 0.855). In multivariable analyses, CLR remained an independent predictor across all outcomes (ORs 1.02, 1.02, and 1.03, all p < 0.001), in addition to established clinical factors. Conclusions: Admission CLR was independently associated with poor outcomes, mortality, and sICH after mechanical thrombectomy. As an easily obtainable marker from routine laboratory tests, CLR may provide additional prognostic information and complement established predictors, but prospective validation is required.

Objective To determine the relative effectiveness of proximal and distal protection in prevention of cerebral ischemic events during carotid artery stent (CAS) placement using diffusion-weighted MRI (DW-MRI). Methods We analyzed data from patients who had undergone DW-MRI before and within 24 hours of CAS for symptomatic internal carotid artery (ICA) stenosis (with last ischemic events within 3 months). The study was performed prospectively; patients were not randomized, and were treated either with a proximal balloon occlusion system (Mo.Ma; Invatec, Roncadelle, Italy) or filter-type distal protection device (Spider device; ev3, Plymouth, Minnesota, USA). Results Of the 45 patients (mean age±SD: 66.9±9.8 years; 73.3% were men) who underwent CAS, 19 had proximal protection and 26 distal protection. New ischemic lesions were detected in 26/45 patients on DW-MRI scans obtained within 24 hours after CAS. The proportion of patients with new lesions on DW-MRI at 24 hours was not different between the two groups (47.4% vs 65.4% for proximal and distal protection, respectively). The mean number of new ischemic lesions on post-CAS DW-MRI was non-significantly higher in patients who underwent CAS with distal protection (2.80±3.54 for proximal protection vs 4.96±5.11 for distal protection; p=0.12). The proportion of patients with new lesions >1 cm did not differ between the two groups (5.3% for proximal protection vs 11.5% for distal protection; p=0.62). There was no difference in the rates of ischemic stroke between patients who underwent CAS treatment using proximal and distal protection (5.3% vs 7.7%; p=1.000). Conclusions We found a relatively high rate of new ischemic lesions in patients undergoing CAS with cerebral protection. There was no difference in the proportion of patients with new lesions between patients treated using distal protection and those treated using proximal protection.

Introduction: Computer vision models have been used to diagnose some disorders using computer tomography (CT) and magnetic resonance (MR) images. In this work, our objective is to detect large and small brain vessel occlusion using a deep feature engineering model in acute of ischemic stroke. Methods: We use our dataset. which contains 324 patient’s CT images with two classes; these classes are large and small brain vessel occlusion. We divided the collected image into horizontal and vertical patches. Then, pretrained AlexNet was utilized to extract deep features. Here, fc6 and fc7 (sixth and seventh fully connected layers) layers have been used to extract deep features from the created patches. The generated features from patches have been concatenated/merged to generate the final feature vector. In order to select the best combination from the generated final feature vector, an iterative selector (iterative neighborhood component analysis—INCA) has been used, and this selector has chosen 43 features. These 43 features have been used for classification. In the last phase, we used a kNN classifier with tenfold cross-validation. Results: By using 43 features and a kNN classifier, our AlexNet-based deep feature engineering model surprisingly attained 100% classification accuracy. Conclusion: The obtained perfect classification performance clearly demonstrated that our proposal could separate large and small brain vessel occlusion detection in non-contrast CT images. In this aspect, this model can assist neurology experts with the early recanalization chance.