Search

Background: Despite the increased use of mechanical thrombectomy (MT) in recent years, there remains a lack of research on in-hospital mortality rates following the procedure, the primary factors influencing these rates, and the potential for predicting them. This study aimed to utilize interpretable machine learning (ML) to help clarify these uncertainties. Methods: This retrospective study involved patients with anterior circulation large vessel occlusion (LVO)-related ischemic stroke who underwent MT. The patient division was made into two groups: (I) the in-hospital death group, referred to as miserable outcome, and (II) the in-hospital survival group, or favorable outcome. Python 3.10.9 was utilized to develop the machine learning models, which consisted of two types based on input features: (I) the Pre-MT model, incorporating baseline features, and (II) the Post-MT model, which included both baseline and MT-related features. After a feature selection process, the models were trained, internally evaluated, and tested, after which interpretation frameworks were employed to clarify the decision-making processes. Results: This study included 602 patients with a median age of 76 years (interquartile range (IQR) 65–83), out of which 54% (n = 328) were female, and 22% (n = 133) had miserable outcomes. Selected baseline features were age, baseline National Institutes of Health Stroke Scale (NIHSS) value, neutrophil-to-lymphocyte ratio (NLR), international normalized ratio (INR), the type of the affected vessel ('Vessel type'), peripheral arterial disease (PAD), baseline glycemia, and premorbid modified Rankin scale (pre-mRS). The highest odds ratio of 4.504 was observed with the presence of peripheral arterial disease (95% confidence interval (CI), 2.120–9.569). The Pre-MT model achieved an area under the curve (AUC) value of around 79% utilizing these features, and the interpretable framework discovered the baseline NIHSS value as the most influential factor. In the second data set, selected features were the same, excluding pre-mRS and including puncture-to-procedure-end time (PET) and onset-to-puncture time (OPT). The AUC value of the Post-MT model was around 84% with age being the highest-ranked feature. Conclusions: This study demonstrates the moderate to strong effectiveness of interpretable machine learning models in predicting in-hospital mortality following mechanical thrombectomy for ischemic stroke, with AUCs of 0.792 for the Pre-MT model and 0.837 for the Post-MT model. Key predictors included patient age, baseline NIHSS, NLR, INR, occluded vessel type, PAD, baseline glycemia, pre-mRS, PET, and OPT. These findings provide valuable insights into risk factors and could improve post-procedural patient management. [ABSTRACT FROM AUTHOR]

The worsening of neurological status that occurs early after acute ischemic stroke (AIS) remains a serious issue, and the inflammatory response plays a key role in stroke pathobiology. Recently, endovascular treatment (EVT) has revolutionized the management and outcome of patients with AIS due to either extracranial carotid disease or intracranial disease. The neutrophil-to-lymphocyte ratio (NLR) represents an easily available inflammatory biomarker. The aim of the study was to assess the relationship between the NLR at admission and the occurrence of early neurological deterioration (END) in patients with AIS who underwent EVT. Patients with AIS and proximal arterial occlusion in the anterior circulation undergoing EVT were retrospectively identified. Absolute neutrophil count (ANC) and absolute lymphocyte count (ALC) were collected from admission blood work to calculate the NLR. The study outcome was END defined as an increase in at least 4 points in NIHSS score or death between baseline and 24 h after the ischemic event. Patients included were 211, and END occurred in 30 (14.2%). Patients with older age (OR = 1.07, 95% CI: 1.02–1.13), higher serum glucose (OR = 1.01, 95% CI: 1.01–1.02), and higher NLR (OR = 1.011, 95% CI: 1.04–1.18) had an increased risk of END. The best predictive cut-off value of NLR was 6.4, and END occurred in 24.1% and 3.9% of the patients with NLR ≥ 6.4 and <6.4, respectively (p < 0.001). In patients with AIS undergoing EVT, higher NLR values predicted a higher risk of END. Biomarkers able to identify inflammatory mechanisms might identify novel treatment targets and enhance proof-of-concept trials of immunomodulation in stroke. [ABSTRACT FROM AUTHOR]

Futile recanalization remains a significant challenge for endovascular treatment (EVT) of acute ischemic stroke (AIS). The inflammatory response that occurs after cerebral infarct plays a central role in stroke pathobiology that can influence the outcome of a recanalization procedure. The aim of this study was to evaluate the relationship between the systemic inflammatory response index (SIRI) and futile recanalization in patients with AIS. We retrospectively identified consecutive patients with ischemic stroke due to proximal arterial occlusion in the anterior circulation, who were treated with EVT and achieved near-complete or complete recanalization. Absolute neutrophil count (ANC), absolute monocyte count (AMC), and absolute lymphocyte count (ALC) were collected from admission blood work to calculate SIRI as ANC × AMC/ALC. The study outcome was futile recanalization, defined as poor functional status [modified Rankin scale (mRS) score ≥ 3] at 3 months despite complete or near-complete recanalization. A total of 184 patients were included. Futile recanalization was observed in 110 (59.8%) patients. Older patients (odds ratio (OR) = 1.07, 95% confidence interval (CI): 1.04–1.10, p < 0.001), higher admission National Institutes of Health stroke scale score (OR = 1.10, 95% CI: 1.02–1.19, p = 0.013), and higher admission SIRI (OR = 1.08, 95% CI: 1.01–1.17, p = 0.028) increased the risk of the poor outcome at 3 months despite complete or near-complete recanalization. [ABSTRACT FROM AUTHOR]