Reader's digest version of scientific writing: comparative evaluation of summarization capacity between large language models and medical students in analyzing scientific writing in sleep medicine.

Introduction: As artificial intelligence systems like large language models (LLM) and natural language processing advance, the need to evaluate their utility within medicine and medical education grows. As medical research publications continue to grow exponentially, AI systems offer valuable opportunities to condense and synthesize information, especially in underrepresented areas such as Sleep Medicine. The present study aims to compare summarization capacity between LLM generated summaries of sleep medicine research article abstracts, to summaries generated by Medical Student (humans) and to evaluate if the research content, and literary readability summarized is retained comparably.

Cerebral collateral flow state in acute ischemic stroke correlates with clinical functional outcomes in non-thrombectomy patients.

Introduction: Hypoperfusion index ratio (HIR) measured by computerized tomography perfusion (CTP) has been shown to predict collateral flow state in acute ischemic stroke (AIS). Low HIR (<0.4) is indicative of good collateral flow state.