Doctors may be no match for computers when it comes to Alzheimer's.
A study published in July in the journal Neurobiology of Aging found that artificial intelligence could detect signs of the disease in patient brain scans before physicians. The computer-based algorithm was able to correctly predict if a person would develop Alzheimer's disease up to two years before he or she actually displayed symptoms. It was correct 84 percent of the time.
Researchers are hopeful that the tool will be helpful in determining before the onset of the disease which patients to choose for clinical trials or for drugs that could slow its progression and delay its crippling 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 of preventing the disease," co-lead study author Dr. Pedro Rosa-Neto, an associate professor of neurology, neurosurgery and psychiatry at McGill University, told Live Science.
The researchers were able to train the artificial intelligence program to recognize Alzheimer's disease in the brain by showing it before and after scans of 200 people who had the disease. The AI technology was then shown scans of 270 volunteers – 43 of whom eventually developed Alzheimer's. The AI technology was able to accurately predict 84 percent of the cases in which the volunteers eventually developed the disease.
More …
https://www.usnews.com/news/health-care-news/articles/2017-09-01/artificial-intelligence-could-predict-alzheimers-years-before-doctors?
