AI ‘learns’ to predict schizophrenia from brain MRI

Twitter icon
Facebook icon
LinkedIn icon
e-mail icon
Google icon
 - Brain iron content
Mean fractional anisotropy image of all patients (grayscale) at the 2-year follow-up MRI, overlapped with the mean skeleton (green), on base of which the statistical group comparisons are calculated. Significant differences between groups are presented in red-yellow. The image showing differences based on patient age at disease onset (P < .05) is focused on the right thalamus (a) and that based on MCI (P < .1) is focused on the left capsula externa (b), both structures marked with an arrow.
Source: Academic Radiology

A collaborative effort between IBM and the University of Alberta in Canada has produced artificial intelligence (AI) and machine learning algorithms were able to examine MRI and predict schizophrenia with 74 percent accuracy.

The retrospective analysis, published July 21 in Schizophrenia, also showed the technology was able to determine the severity of symptoms by examining activity in various regions of the brain.

The team examined brain MRI of 95 participants, using the images to develop a machine-learned model of schizophrenia. The AI was then able to distinguish between those with schizophrenia and a control group.

“The ultimate goal of this research effort is to identify and develop objective, data-driven measures for characterizing mental states, and apply them to psychiatric and neurological disorders” said Ajay Royyuru, vice president of healthcare and life sciences with IBM Research. “We also hope to offer new insights into how AI and machine learning can be used to analyze psychiatric and neurological disorders to aid psychiatrists in their assessment and treatment of patients.”

The full study is available for free at Schizophrenia.