Could AI Testing Replace Doctors in Alzheimer's Prediction and Diagnosis?

A study by Boston University School of Medicine (BUSM) researchers published in Brain assessed a new artificial intelligence (AI) program that uses magnetic resonance imaging (MRI) brain scans, cognitive impairment measures, and data on age and gender to predict and diagnose Alzheimer's disease, reports Being Patient . The team fed the AI raw MRI brain scans along with demographic and clinical data on individuals with and without the disease. The AI can learn to identify Alzheimer's markers in new scans. In feeding the program information from just one sample group, then measuring its predictions for scans from the other cohorts, the researchers found that the AI predicted the scans accurately. The program also exhibited superior predictive capability to human scientists. "If computers can accurately detect debilitating conditions such as Alzheimer's disease using readily available data such as a brain MRI scan, then such technologies have a wide-reaching potential, especially in resource-limited settings," said BUSM Professor Vijaya B. Kolachalama. He also suggested that such a tool could potentially assist clinical practice, particularly in memory clinics.