A computer algorithm based on artificial intelligence can go head-to-head with neurologists, accurately diagnosing Alzheimer’s disease and predicting risk, according to researchers from Boston University School of Medicine.

The algorithm model uses data from brain magnetic resonance imaging and patient demographics (such as age and gender) to make assessments. Investigators asked neurologists to use the same data to detect Alzheimer’s disease in groups of study participants, comparing the clinicians’ assessments to those of the algorithm model.  

The model performed slightly better than the average neurologist, said corresponding author Vijaya B. Kolachalama, Ph.D. In addition, brain regions flagged as having high disease risk by the algorithm were also “highly aligned” with autopsy report findings of the brains of a few deceased individuals.

“If we have accurate tools to predict the risk of Alzheimer’s disease … that are readily available and which can use routinely available data such as a brain MRI scan, then they have the potential to assist clinical practice, especially in memory clinics,” Kolachalama concluded.

The study was published in the journal Brain.