Various researchers around the globe are developing ways to detect Alzheimer's as early as possible. An algorithm developed by a team from the University of Bari proved that AI can be a powerful weapon against the dreaded disease.
They developed an algorithm that can spot tiny structural changes in the brain caused by the disease a decade before symptoms even appear. The researchers divided the scans into small regions to maximize identification, and let the AI analyze the neural connectivity.
The researchers fed their machine learning system with a set of 67 MRI scans - 38 of which were from people with Alzheimer's, while 29 were from healthy controls. They then put the AI to the test by scanning the brains of 148 subjects, 48 of whom had Alzheimer's, while another 48 had mild cognitive impairments that later led to Alzheimer's. Crucially, it could also tell the difference between healthy brains and those with MCI with an accuracy of 84%.
The researchers were limited to using scans available in the USC LA's Alzheimer's Disease Neuroimaging Initiative database, but more samples and further development could make this technology more accurate, until it's reliable enough to be utilized as a non-invasive detection system.
The AI was able to identify Alzheimer's 86% of the time in the brain scans.
A ruinous chronic neurodegenerative disease, Alzheimer's disease (AD) presently affects around 5.5 million people in the United States alone, increasing mental declination, it ultimately advances to influence basic functions of body such as walking and swallowing.
While a full on cure for Alzheimer's has yet to be discovered, researchers are making progress when it comes to early detection. This machine learning algorithm is now based on a small set of data, but when fed with more data, it could be developed into a full-fledged, non-invasive tool for early Alzheimer's detection.