Log in or Register for enhanced features | Forgotten Password?
White Papers | Suppliers | Events | Report Store | Companies | Dining Club | Medical Devices | Videos
Drug Research
Drug Delivery
Return to: PBR Home | Drug Research | Drug Delivery

Study says machine learning algorithms can help predict schizophrenia

PBR Staff Writer Published 24 July 2017

A new study has found that artificial intelligence (AI) and machine learning algorithms helped predict instances of schizophrenia with 74% accuracy.

IBM scientists and the University of Alberta in Edmonton, Canada, have published new data in Nature's partner journal.

The research was on computational psychiatry which uses AI to explore the prediction and assessment of the disease.

Based on correlations between activity noted across different areas of the brain, the research analysis showed that computational psychiatry could predict the severity of specific symptoms in schizophrenia patients with significant correlation.

University of Alberta Psychiatry & Neuroscience professor Serdar Dursun said: “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.

“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.”

By using machine learning algorithms, scientists could analyze functional magnetic resonance imaging (fMRI) during the research to gauge changes in blood flow to assess activity across different regions of the brain.

By looking at scans from 95 patients, the scientists deployed machine learning techniques to create a schizophrenia model to identify the connections in the brain that are commonly related to the disease.

The research also demonstrated that functional network connectivity is helpful in determining the severity of several symptoms after they had begun to show in the patient.

IBM Research Healthcare & Life Sciences vice president Ajay Royyuru said: “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,

“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.”


Image: Regions of the brain that showed a statistically significant difference between patients with schizophrenia and patients without it. Photo: courtesy of IBM.