Today’s best treatment for Alzheimer’s is early detection.
Researchers around the world are developing methods to detect the condition early, as it empowers people to seek immediate treatment in hopes of limiting the disease’s effects. It also gives breathing room to organize legal and financial affairs.
Some scientists have dedicated their focus to blood and cerebrospinal fluid tests, while others are developing gadgets that can look for early signs.
A team of researchers from the University of Bari in Italy is taking a unique approach with their research, examining an area no other researchers have ventured to: artificial intelligence.
The Italian team created an algorithm that spots tiny, structural changes in the brain that are caused by the disease – changes that can be detected a decade before symptoms even appear.
To develop the algorithm, the team trained the AI by ‘feeding’ it 67 MRI scans – 38 from Alzheimer’s patients, and 29 from health controls. The researchers divided the scans into even smaller regions, and had the AI analyze the neuronal connectivity between each region.
They tested the algorithm upon completion, having the AI process brain scans from 148 subjects. Out of that total, 48 scans came from people with Alzheimer’s, while another 48 were from people with mild cognitive impairment, who eventually developed Alzheimer’s.
The results are promising: the AI successfully diagnosed Alzheimer’s 86% of the time. Equally important, it detected mild cognitive impairment 84% of the time, meaning it could be a potential tool for early diagnosis.
A caveat to the otherwise encouraging study is that the researchers were limited to the scans in USC LA’s Alzheimer’s Disease Neuroimaging Initiative database. But with more samples and refinement, the team’s AI may be accurate enough to be used as a reliable, non-invasive, early detection system for Alzheimer and other cognitive diseases.
Photo Credit: Jakub Jirsak/BigStock; monsitj/Bigstock