Machine learning helps to identify early signs of Alzheimer’s

Researchers at the University of Southern California have discovered “hidden” indicators of Alzheimer’s in medical data that could result in earlier diagnosis of the disease and better prognosis for patients.

Using machine learning, USC researchers identified potential blood-based markers of Alzheimer’s disease that could be detected with a routine blood test.

“This type of analysis is a novel way of discovering patterns of data to identify key diagnostic markers of disease,” said Paul Thompson, associate director of the USC Mark and Mary Stevens Neuroimaging and Informatics Institute and professor in USC’s Keck School of Medicine. “In a very large database of health measures, it helped us discover predictive features of Alzheimer’s disease that nobody suspected were there.”

USC-CROP.jpg

Also See: MRI brain scans better ID people likely to develop Alzheimer’s

In their study, published in Frontiers in Aging Neuroscience, the USC research team analyzed medical data in the Alzheimer’s Disease Neuroimaging Initiative database—collected from 829 older adults—to identify predictors of cognitive decline and brain atrophy during a one-year period.

The machine learning algorithm they used—Correlation Explanation (CorEx), developed by Greg Ver Steeg, a senior research lead at the USC Information Sciences Institute—is able to tease out patterns in areas often overwhelmed by large amounts of data.

“While the relationships between some of the measures have been previously documented and several measures were known to be associated with (Alzheimer’s disease), the clustering achieved with CorEx provides more direct evidence for a network of related measures and how these measures jointly predict disease progression, brain atrophy and cognitive decline,” state the study’s authors.

“These results also demonstrate the power of CorEx to identify clusters of variables that involve synergistic and coherent sets of the original features, revealing stronger combinations of variables that may be only weakly predictive when examined as individual predictors,” add the authors. “Our results point to the consistent importance of amyloid and tau across the disease trajectory, but also to the timepoint specific contributions of the immune and inflammatory systems, and to the role of cardiovascular health, hormone levels and lipid and glucose metabolism.”

For reprint and licensing requests for this article, click here.