Enhancing Stroke Diagnosis and Management: The Role of AI and Teleneurology in Improving Patient Outcomes in a Single Centre Retrospective Study

Abstract

Stroke represents a critical health crisis, causing significant global mortality and long-term disability due to the obstruction of blood flow to the brain. Acute ischemic stroke treatment focuses on timely interventions such as tPA administration and mechanical thrombectomy, but the narrow time window and shortage of specialists pose challenges. Tele neurology has enhanced recovery rates by providing remote consultations, while artificial intelligence (AI) offers promising solutions to improve stroke management. AI and machine learning (ML) in stroke care analyze complex brain imaging data, aiding in diagnosis and treatment planning through supervised and unsupervised learning methods. Despite challenges like the need for large datasets and algorithm complexity, AI's integration has shown high accuracy in early ischemic changes detection, exemplified by the computer-assisted ASPECTS. This retrospective study evaluated the efficacy of AI in detecting intracranial bleed, large vessel occlusion , and ASPECT scores in stroke patients. AI demonstrated perfect sensitivity in identifying ICH and LVO, with high specificity and negative predictive value, though radiologist confirmation is essential to address false positives. The study underscores AI's potential to improve diagnostic accuracy and patient outcomes in stroke care, highlighting its reliability in extreme ASPECT score categories and variability in intermediate scores, necessitating continued radiologist involvement.