AI predicts schizophrenia with 74% accuracy, study finds

A team of researchers from Edmonton, Canada-based University of Alberta and IBM developed an artificial intelligence algorithm to detect schizophrenia in patients.

The researchers analyzed de-identified brain functional MRI data for patients with schizophrenia and schizoaffective disorders, and compared it to a data from a healthy control group. After examining scans from 95 participants, the researchers developed a machine learning algorithm to identify neuroimaging-based patterns associated with schizophrenia.

Their findings, published in Nature's partner journal Schizophrenia, determined the machine learning algorithm could differentiate between patients with and without the disorder with 74 percent accuracy. The algorithm also helped to assess the severity of schizophrenia symptoms related to inattentiveness, lack of motivation and formal thought disorder, among others.

"We've discovered a number of significant abnormal connections in the brain that can be explored in future studies, and AI-created models bring us one step closer to finding objective neuroimaging-based patterns that are diagnostic and prognostic markers of schizophrenia," said Serdar Dursun, MD, a professor of psychiatry and neuroscience with the University of Alberta and coauthor of the study.

More articles on health IT:
Allscripts partners with Conversa for clinical conversation platform
Congressional App Challenge names director
Kalorama: Physician frustration drives regular EMR vendor switching

© Copyright ASC COMMUNICATIONS 2019. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.


Top 40 Articles from the Past 6 Months