A new study shows that an AI program is better than doctors at predicting who with early dementia will progress to Alzheimer’s disease. The AI correctly predicted in 4 out of 5 cases whether early dementia would stay the same or worsen into Alzheimer’s, according to the journal eClinical Medicine.
The AI was about three times more accurate than doctors, who used brain scans, cognitive tests, and spinal fluid analysis. “Our tool, using only data from cognitive tests and MRI scans, is much more sensitive than current methods at predicting Alzheimer’s progression,” said Zoe Kourtzi, a senior researcher at the University of Cambridge.
Researchers built the AI model using brain scans and cognitive tests from 400 people in a U.S. research project. They tested it with data from another 600 U.S. patients and 900 people from memory clinics in the U.K. and Singapore.
The AI correctly identified who would develop Alzheimer’s within three years 82% of the time and who would have mild but stable dementia in 81% of cases. It also grouped patients based on their risk: about 50% had stable dementia, 35% would slowly progress to Alzheimer’s, and 15% would progress rapidly.
This AI tool could help high-risk patients get early treatment and close monitoring. It could also help doctors identify other issues in patients with stable symptoms, like mood disorders instead of dementia.
The study suggests that this AI program could be used in real-world settings to improve patient care. “Memory problems are common as we age, and reducing uncertainty about dementia can ease worries for patients and their families,” said Dr. Ben Underwood, a researcher at the University of Cambridge.
The team plans to extend the AI model to other types of dementia and include more data like blood test results. “Our vision is to scale up our AI tool to help clinicians provide the right care at the right time,” Kourtzi said. “This tool can also help match patients to clinical trials, speeding up new drug discovery.”
Source: healthday
