A group of researchers affiliated with Kaunas University of Technology (KUT) in Lithuania created an algorithm capable of predicting early development of Alzheimer’s disease with an accuracy of more than 99%, helping medical communities better treat their patients.
“Although this was not the first attempt to diagnose the early onset of Alzheimer’s from similar data, our main breakthrough is the accuracy of the algorithm,” says Prof Rytis Maskeliūnas, KTU Faculty of Informatics. “Technologies can make medicine more accessible and cheaper. Although they will never replace the medical professional, technologies can encourage seeking timely diagnosis and help.”
The team used a total of 51,443 images taken using functional magnetic resonance imaging from 138 subjects. Once analyzed, the images fell into six categories – from healthy through the spectre of mild cognitive impairment to Alzheimer’s disease – and the classification results showed up to a whopping 99.99% accuracy. By detecting the early stages of Alzheimer’s through neuroimaging, patients have access to better care and better drugs.