Stanford Medicine study identifies brain connectivity pattern that predicts Alzheimer's risk
Researchers at Stanford Medicine developed a brain-scan based score that distinguishes older adults at higher risk of Alzheimer’s up to a decade before symptoms appear, achieving about 85% accuracy.
A Stanford Medicine team has created a computer model that analyzes resting-state brain scans to detect functional connectivity patterns linked to Alzheimer’s disease. The model generates an Alzheimer’s resilience-vulnerability connectome (ARC) score, which differentiated patients with Alzheimer’s from cognitively high-performing “super agers” with roughly 85% accuracy, according to a study published in Science Advances.
The researchers then applied the ARC score to more than 1,300 cognitively normal adults aged 55 to 70. Although all participants performed normally on memory tests, their scans showed varying patterns: some resembled super agers, while others matched Alzheimer’s profiles. Over follow-up periods of up to 12 years, individuals whose brain activity aligned with Alzheimer’s patterns experienced faster cognitive decline, accumulated more amyloid plaques, and faced a higher likelihood of receiving a diagnosis.
"We compared the ARC score with existing biomarkers in predicting people converting to Alzheimer's disease," said lead author Kanhao Zhao, a postdoctoral scholar in psychiatry at Stanford Medicine.
"Our model shows comparable or better prediction ability, and it can do so at an earlier time point. And if we combine our score with the existing biomarkers, the prediction performance improves," Zhao added.
The ARC score performed on par with or better than traditional risk measures, including amyloid and tau biomarkers and genetic testing. However, the researchers cautioned that the method is not yet ready for clinical diagnosis and requires further validation.
"There are two main components: One is to know which part of the brain to target. The other is how we should change it," said senior author Yu Zhang, an assistant professor of psychiatry and behavioral sciences at Stanford Medicine. "That's why identifying the super ager brain resilience pattern is a critical component — so we know what a good pattern should be."
The findings suggest that early detection of altered brain connectivity could aid future therapeutic strategies, such as non-invasive brain stimulation, aimed at preserving cognitive function.