Agentic AI for Neurodegenerative Disease — Scaling Diagnosis and Care
OVERVIEWA Nature publication examines agentic AI as a framework for scaling diagnosis and care in neurodegenerative diseases, where specialist shortages, long diagnostic timelines, and the need for continuous monitoring create significant unmet need. Agentic AI systems capable of autonomous data collection, pattern recognition, and care coordination could extend specialist reach to underserved populations and enable earlier intervention. A complementary framework, CogCBR, applies Case-Based Reasoning to gait-based neurodegenerative disease screening using wearable force-sensitive insoles. The system operationalizes the complete R4 cycle (Retrieve, Reuse, Revise, Retain) with confidence-based clinical triage and longitudinal case-base maintenance, achieving an AUC of 0.861 on the PhysioNet GaitPDB cohort and 0.902 on the GaitNDD cohort. Unlike conventional ML pipelines, CogCBR provides per-case reliability estimates, case-based explanations, and longitudinal knowledge base maintenance—features aligned with clinical reasoning requirements. For Alzheimer's disease specifically, a machine learning model using the Digital Clock and Recall (DCR™) digital cognitive assessment predicted MMSE scores with an RMSE of 2.43 in a test set and 2.62 in external validation—within the test-retest reliability range of the manual MMSE itself. The model showed comparable performance across racial and ethnic groups, addressing equity concerns that have limited the clinical adoption of digital cognitive…
Subscribe to read full wiki analysis
Full wiki content — including source provenance, contradiction tracking, related pages, and analyst notes — is available to Subscriber members.
View Plans & SubscribeNew users get a 7-day trial — no credit card required.