Currently, it can take several scans and tests to diagnose the condition, but AI can identify patterns in brain scans that cannot be seen by expert neurologists.
The system compares brain scans of people who suspect they might have dementia with those previously diagnosed with it. It may also predict whether the condition will remain stable for years, or if it requires immediate treatment.
Researchers say earlier diagnoses could greatly improve outcomes for patients.
Professor Zoe Kourtzi, of Cambridge University and a fellow of The Alan Turing Institute, the U.K.'s centre for AI and data science, told the BBC: "If we intervene early, the treatments can kick in early and slow down the progression of the disease and at the same time avoid more damage.
"And it's likely that symptoms occur much later in life or may never occur."
In pre-clinical tests, the algorithm was shown to diagnose dementia years before symptoms develop, even when there are no obvious signs of damage on the brain scan.
A new trial is expected to test about 500 patients at Addenbrooke's Hospital and other memory clinics around the U.K.
Kourtzi is also leading a project funded by Alzheimer's Research UK which combines digital data on sleep, fine motor skills, and brain activity from apps and wearable items to predict diseases like Alzheimer's up to 20 years earlier.
The U.S.-based Alzheimer's Drug Discovery Foundation has announced up to $2 million (£1.44 million) in funding for the research.
Kourtzi said: "Digital technology holds enormous potential to put us on the front foot when it comes to identifying diseases like Alzheimer's earlier."
Globally, there are 50 million people living with dementia, and that figure is set to rise.
COVER News
___________________
 could be used to diagnose dementia){kind=link}
0 facebook:
Post a Comment