AI Model Distinguishes EDSS Subgroup Patterns in Multiple Sclerosis, Study Shows

AI Clusters Disability Patterns: Analysis using AI-based clustering algorithms identified distinguishable disability patterns among MS patients with identical Expanded Disability Status Scale (EDSS) scores, particularly in those with EDSS scores of 4 or higher.
Study Participants: The research involved 1636 patients with secondary progressive MS, part of the EXPAND trial, and examined 13,103 assessments.
Distinct Subscore Patterns: Four distinct subscore patterns were identified within each EDSS score increment of 0.5 from 4.0 to 6.5, indicating varied functional impairments.
Clinical Implications: The patterns reveal more granular details regarding functional impairment, possibly aiding in more effective patient treatment selection and enhancing clinical trial outcomes.
Increased Granularity in MS Assessments: Leveraging AI to describe disability patterns beyond ambulation could improve the selection of MS patients who might benefit from specific treatments.
Implications for Clinical Trials: Enhanced granularity in assessing functional impairment may potentiate clinical trials to better detect treatment effects on relevant patient deficits.
Expanded Use of AI in Neurology: The study highlights the growing role of AI, machine learning, and data integration in diagnosing, monitoring, and managing neurological conditions.

AI Model Distinguishes EDSS Subgroup Patterns in Multiple Sclerosis, Study Shows | NeurologyLive