An autonomous AI system capable of screening for cognitive decline using routine clinical documentation has been developed by researchers at the Boston-based Mass General Brigham.
The system, which requires no human intervention or prompting after deployment, achieved 98% specificity in real-world validation testing: that is, the rate at which it reduces false positives.
Corresponding author on the study Hossein Estiri said: “This AI system includes five specialised agents that critique each other and refine their reasoning, just like clinicians would in a case conference.”
Cognitive impairment remains significantly underdiagnosed in routine clinical care, and traditional screening tools and cognitive tests are highly resource-intensive to administer and difficult for patients to access.
The Alzheimer’s Society estimates that a third of people living with dementia in England and Northern Ireland, and nearly half of people living with dementia in Wales, don’t have a formal diagnosis.
Yet...