July 21, 2017 Written by: Dr. Guillermo Cecchi In the U.S. about 20 percent of adults suffer from a mental health condition, ranging from depression to bipolar disorder to schizophrenia, and about half of those with severe psychiatric disorders receive no treatment. While early identification, diagnosis, and treatment for patients with psychosis tends to mean improved outcomes, there continues to be significant barriers in achieving this. For schizophrenia, there is no medical testing that can provide an absolute diagnosis; this can mean significant delay before a symptomatic person is successfully diagnosed. Earlier this year, IBM scientists collaborated with researchers at the University of Alberta and the IBM Alberta Centre for Advanced Studies (CAS) to publish new research regarding the use of AI and machine learning algorithms to predict instances of schizophrenia with a 74 percent accuracy. The research also shows a further capability to predict the severity of specific symptoms in schizophrenia patients – something that was not possible before.

A team of researchers from the University of Alberta, Canada and tech giant IBM has developed artificial intelligence and machine learning algorithms, which can diagnose schizophrenia by studying the blood flow of the brain. Mina Gheiratmand, the lead author of the study published in the journal Nature, said the algorithm was able to provide diagnosis with 74 percent accuracy. Using the algorithm, doctors might not just be able to be diagnose the disease but even determine its severity using a simple MRI scan and the AI-based neural network, which studies the blood flow. "This unique, innovative multidisciplinary approach opens new insights and advances our understanding of the neurobiology of schizophrenia, which may help to improve the treatment and management of the disease," Serdar Dursun, a professor of psychiatry & neuroscience with the University of Alberta, said in a statement to Engadget. The researchers studied 95 subjects, including 46 schizophrenia patients.