Scientists Use Machine Learning To Spot Alzheimer's Before Onset of Symptoms

Scientists then presented the algorithm with a new set of brain scans, some of which were from patients who currently had mild cognitive impairment. All of the scans, however, were taken before any of the patients had developed the disease. The algorithm was able to predict which patients would end up impaired with an accuracy of 84 percent. "This is an example how big data and open science brings tangible benefits to patient care," said Rosa-Neto to McGill News. The biggest benefit to patient care could be improved clinical trials studying the effectiveness of drugs for Alzheimer's, the most common form of dementia. "By using this tool, clinical trials could focus only on individuals with a higher likelihood of progressing to dementia within the time frame of the study," said Dr. Serge Gauthier, the study's co-lead author, to McGill News. "This will greatly reduce the cost and the time necessary to conduct these studies." Research was funded by the Canadian Consortium on Neurodegeneration in Aging (CCNA) and the Canadian Institutes of Health Research.