Machine-Learning Algorithm Analyzes Images to Identify Schizophrenia Patients

A team of researchers from the University of Alberta (Edmonton, Alberta, Canada) has developed a machine-learning algorithm to examine functional magnetic resonance imaging (fMRI) images for identifying patients suffering from schizophrenia and ascertaining if they would respond to treatment. In a study, the algorithm examined MRI images of both newly diagnosed, previously untreated schizophrenia patients and healthy subjects and successfully identified patients with schizophrenia at 78% accuracy. It also predicted whether or not a patient would respond positively to a specific antipsychotic treatment named risperidone with 82% accuracy.

Schizophrenia, a severe and disabling psychiatric disorder that comes with delusions, hallucinations and cognitive impairments, affects approximately one in 100 people at some point in their lives. Early diagnosis of schizophrenia and other mental disorders still remains a challenge, while clinicians face the difficult task of devising a personalized treatment strategy during the first visit with a patient. Currently, the treatment of schizophrenia is usually determined using a trial-and-error style. However, if a drug does not work properly, the patient can suffer prolonged symptoms and side effects, and miss the best time window to control and treat the disease.

The initial trial results of the machine-learning algorithm for the diagnosis and treatment of schizophrenia have been encouraging. However, further validations on large samples will be required and more refinement is needed to improve its accuracy before using it in a clinical environment. The researchers also expect to expand their work to include other mental illness such as major depressive and bipolar disorders.

"This is the first step, but ultimately we hope to find reliable biomarkers that can predict schizophrenia before the symptoms show up," said Bo Cao, an assistant professor of psychiatry at the University of Alberta, who led the research. "We also want to use machine learning to optimize a patient's treatment plan. It wouldn't replace the doctor. In the future, with the help of machine learning, if the doctor can select the best medicine or procedure for a specific patient at the first visit, it would be a good step forward."

Related Links:
University of Alberta