Initial-Stage Alzheimer's Caught by AI in a Population-Level Sample

A study published in the Journal of Prevention of Alzheimer's Disease details how a machine learning algorithm accurately identified individuals in initial-stage Alzheimer's, reports AI in Healthcare . The algorithm was trained to recognize patterns predictive of Alzheimer's in combinations of drug treatments, doctor visits, diagnostic tests, therapeutic procedures, and verified clinical diagnoses. Participants ranged in age from 50 to 85, and approximately 667,000 had at least one record of Alzheimer's diagnosis or treatment. About 3.7 million lacked Alzheimer's and were categorized as controls. A "gradient boosted tree" algorithm exhibited the best ability, identifying 222,721 subjects in the prodromal Alzheimer's stage with 80 percent accuracy, of whom 76 percent were in the primary care setting. The researchers suggested the second result "could drive major advances in Alzheimer's disease research by enabling more accurate and earlier prodromal Alzheimer's disease diagnosis at the primary care physician level, which would facilitate timely referral to expert sites for in-depth assessment and potential enrolment in clinical trials."