AI detects Alzheimer’s-related brain changes 10 years before symptoms appear

A team of researchers have developed an algorithm that can spot structural changes in the brain related to Alzheimer’s on an MRI up to 10 years before symptoms appear.

The researchers, led by Marianna La Rocca of the University of Bari in Italy, first trained their machine learning algorithm how to decipher between a healthy brain and one with Alzheimer’s using a total of 67 MRI scans, including 38 from Alzheimer’s patients and 29 from healthy individuals. The researchers then divided the brain scans into smaller groups for the artificial intelligence (AI) to study the neuronal connectivity within each scan.

The AI was then instructed to process brains from 148 subjects—of which 52 were healthy, 48 had Alzheimer’s and the remaining 48 had mild cognitive impairment (MCI) converting to Alzheimer’s. The last 48 were known to have developed Alzheimer’s later in life.

AI distinguished between healthy brains and Alzheimer’s with 86 percent accuracy. It was also able to distinguish between a healthy brain and one with MCI with 84 percent accuracy.

The detection of MCI implies that AI can identify brain changes that could lead to Alzheimer’s later in life.

“Understanding the biological changes, occurring in these early phases, is of paramount importance, as it would open a window of opportunity for future disease-modifying treatments,” the authors wrote.

""

As a senior news writer for TriMed, Subrata covers cardiology, clinical innovation and healthcare business. She has a master’s degree in communication management and 12 years of experience in journalism and public relations.

Trimed Popup
Trimed Popup