Researchers at IBM and the University of Alberta have developed artificial intelligence (AI) algorithms capable of predicting schizophrenia with 74 percent accuracy.
Published in Schizophrenia, a study outlined how the tool aims to be a starting point for scientists in identifying neurological biomarkers for predicting schizophrenia and its severity. Researchers analyzed brain MRI data from patients with schizophrenia and schizoaffective disorders, as well as healthy patients, to train the AI to identify schizophrenic behavior.
“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,” said Serdar Dursun, MD, PhD, professor of psychiatry and neuroscience at the University of Alberta. “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.”
The tool examined 95 scans from participants to develop models of schizophrenia to identify connections in the brain associated with the chronic disease. Results showed the AI algorithm could tell the difference between patients with schizophrenia and control individuals with a 74 percent rate of accuracy. The AI could also determine the severity of symptoms
“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.”