Alateya, Aysha

Background Left ventricular assist devices (LVADs) are used as definitive therapy or as a bridge to heart transplant in patients with advanced heart failure. Thromboembolic complications such as acute ischemic stroke (AIS) are common among patients with LVAD support. This study aims to evaluate the current evidence on the efficacy and safety of mechanical thrombectomy (MT) in patients with AIS due to large vessel occlusions (LVO) and LVAD-support. Methods A comprehensive systematic review was conducted in PubMed, Embase, and Scopus to find observational studies with reports of ≥5 MTs in adult patients with LVAD support (PROSPERO registration code CRD42024597541). Rates of successful and complete reperfusion, favorable functional outcomes at 90 days (modified Rankin Scale (mRS) 0–2 or equal to pre-stroke mRS), mortality at 90 days, any intracerebral hemorrhage (ICH) and symptomatic ICH (sICH) were pooled using generalized linear mixed models. Results Eight studies were included with data from 51 patients and 62 MTs. The rate of successful reperfusion was 87.4% (95% CI 62.5% to 96.6%) and complete reperfusion rate was 57.3% (95% CI 35.1% to 76.9%). Rate of favorable functional recovery was 62.5% (95% CI 42.2% to 79.2%). Rate of sICH was 6.4% (95% CI 0.9% to 34.0%). Mortality rate was 16.7% (95% CI 7.1% to 34.7%). Between 25–40% of patients who were waiting for a heart transplant before their stroke received a heart transplant after MT. Conclusions MT for the emergent treatment of AIS in the setting of LVAD is relatively safe and efficacious for achieving successful reperfusion and good functional recovery.

Introduction: In recent years, artificial intelligence (AI) has emerged as a transformative tool for enhancing stroke diagnosis, aiding treatment decision making, and improving overall patient care. Leading AI-driven platforms such as RapidAI, Brainomix®, and Viz.ai have been developed to assist healthcare professionals in the swift and accurate assessment of stroke patients. Methods: Following the PRISMA guidelines, a comprehensive systematic review was conducted using PubMed, Embase, Web of Science, and Scopus. Characteristic descriptive measures were gathered as appropriate from all included studies, including the sensitivity, specificity, accuracy, and comparison of the available tools. Results: A total of 31 studies were included, of which 29 studies focused on detecting acute ischemic stroke (AIS) or large vessel occlusions (LVOs), and 2 studies focused on hemorrhagic strokes. The four main tools used were Viz.ai, RapidAI, Brainomix®, and deep learning modules. Conclusions: AI tools in the treatment of stroke have demonstrated usefulness for diagnosing different stroke types, providing high levels of accuracy and helping to make quicker and more precise clinical judgments.