A mix of machine learning and artificial intelligence-based algorithms could redefine how schizophrenia is diagnosed.
Scientists at IBM Canada and the University of Alberta created a specialized program that was able to assist in predicting instances of schizophrenia with 74 percent accuracy.
The algorithms sifted through de-identified brain functional Magnetic Resonance Imaging (fMRI) data from an initiative called the Function Biomedical Informatics Research Network.
The neuroimaging information used in this study was of 95 patients diagnosed with schizophrenia and schizoaffective disorders as well as individuals that served as a healthy control group. Scientists can use fMRI to gage blood flow changes in specific areas of the brain, but this specific data set was reflective of research done on brain networks at different resolution levels.
Essentially, the machine learning algorithms were able to explore these scans to create a model of schizophrenia that pinpoints brain connections most associated with the illness. The data also indicated that the diagnostic could distinguish between patients with schizophrenia and the control group with 74 percent accuracy, even as these images were collected from multiple sites through different means.
Also, results from this analysis indicated the software could ascertain the severity of certain symptoms like inattentiveness along with bizarre behavior and formal thought disorder after they manifested in the patient.
“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 Dr. Serdar Dursun, a Professor of Psychiatry & Neuroscience with the University of Alberta, in a statement. “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.”
This research could aid in the design of an objective, data-driven approach that could help clinicians view the disease on a spectrum so they can create a customized treatment plan tailored for certain individuals.
Investigators will continue their work to refine the algorithms on larger datasets and explore its efficacy with other psychiatric disorders.
The study appeared in the journal Schizophrenia.