Researchers from IBM and the University of Alberta have collaborated to bring new AI technology that can predict symptoms of schizophrenia with 74 percent accuracy. With their findings recently published in Schizophrenia, the researchers monitored activity in different regions of the brain to determine the severity of individual symptoms.
According to the World Health Organization, 21 million people suffer from schizophrenia, and 50 percent of those living with the condition do not get adequate care. Symptoms manifest in various ways including delusions, hallucinations, and abnormal motor behavior. Most males experience their first schizophrenic episode around age 21 and females exhibit their first signs around age 27.
Through utilizing machine learning techniques, researchers analyzed scans from 95 participants to identify the connections in the brain most commonly associated with schizophrenia. “We studied whole-brain fMRI functional networks, both at the voxel level and lower-resolution supervoxel level,” the researchers wrote. “Targeting Auditory Oddball task data on the FBIRN fMRI dataset (n = 95), we considered node-degree and link weight network features and evaluated stability and generalization accuracy of statistically significant feature sets in discriminating patients vs. controls.”
This is a pioneering step in using machine learning to advance healthcare diagnoses. “We’ve discovered a number of significant abnormal connections in the brain that can be explored in future studies,” said one of the study’s authors, Serdar Dursun, MD, professor of psychiatry and neuroscience at the University of Alberta. “AI-created models bring us one step closer to finding objective neuroimaging-based patterns that are diagnostic and prognostic markers of schizophrenia.”