Researchers from the Perm National Research Polytechnic University (PNRPU) trained a neural network to diagnose Alzheimer’s disease in the early stage of development. They shared the details of their patented development in Algorithms magazine.
In the early stages, the symptoms of Alzheimer’s disease are vague, but over time the disease progresses and leads to long-term memory loss, speech disorders, loss of ability to navigate and look after oneself. Neural networks are already used in medical research, but often to a limited extent – filling in the data necessary for them requires consent from the patient and their relatives.
Therefore, the Permian neural network was trained on a relatively limited dataset: over five years, it collected data on 81 patients, 59 of whom were confirmed to have Alzheimer’s disease. The information collected included MRI images in which magnetic susceptibility values of cerebral vessels were highlighted.
The scientists proposed solving the limited data problem by using the complex evaluation mechanism – the “decision root” traditionally used to combine several indicators into a single evaluation. As a result, the Perm researchers’ neural network was able to diagnose the disease with high accuracy.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
