Artificial intelligence can pick up on symptoms of Alzheimer’s disease in brain scans long before doctors or patients.
A computer-driven algorithm was able to accurately foresee whether or not a person would develop Alzheimer’s disease up to two years before he or she displays symptoms, according to a new study from McGill University.
It was correct in its predictions 84% of the time. Researchers are excited for the AI’s potential to help choose patients for clinical trials and drugs ahead of the disease’s onset that could delay its debilitating effects.
“If you can tell from a group of individuals who is the one that will develop the disease, one can better test new medications that could be capable or preventing the disease,” Dr. Pedro Rosa-Neto, a study co-author, told Live Science.
The study’s findings, published in the journal Neurobiology of Aging, suggest that the technology could better alert doctors to an inevitable Alzheimer’s diagnosis more accurately than a patient describing how they’re feeling.
Alzheimer’s is the most common form of dementia and clinical trials for drugs to combat the disease must meet a minimum 18 to 24 month run time. But it’s impossible to know if these drugs are effective if people who enter a clinical trial never experience symptoms during that time span.
“You want to include people who will be progressing from mild cognitive impairment to dementia in the time of the clinical trial,” Rosa-Neto said.
Enter the study’s new technology. Scientists have a tough time predicting the disease on their own through amyloid (a protein that builds up and leads to cognitive damage) PET scans, especially considering that the existence of amyloids in the brain does not necessarily always lead to a dementia diagnosis.
The AI algorithm had three steps from development to trial: writing the software, training it and testing. It was presented with before and after scans of the study’s 200 volunteers to get a sense of what a pre and post-amyloid built-up brain looks like.
The AI technology was then shown the scans of 270 new individuals who had mild cognitive impairments 43 of whom eventually developed Alzheimer’s from before they were diagnosed. Using its knowledge and the before scans, the algorithm was able to accurately predict 84% of the cases in which a person would eventually have the disease.
Source: NY Daily News