Machine Learning Helps to Predict The Treatment Outcomes of Schizophrenia


Source: University of Alberta Faculty of Medicine & Dentistry

Summary: New research is bringing us closer to that future through a study that could the diagnose and treat of mental health disorders one day be aided through the help of machine learning.


Approximately one in 100 people will be affected by schizophrenia at some point in their lives, a severe and disabling psychiatric disorder that comes with delusions, hallucinations and cognitive impairments. Most patients with schizophrenia develop the symptoms early in life and will struggle with them for decades. Early diagnosis of schizophrenia and many mental disorders is an ongoing challenge. Coming up with the personalized treatment strategy at the first visit with a patient is also a challenge for clinicians. Current treatment of schizophrenia is still often determined by a trial-and-error style. New research from the University of Alberta is bringing us closer to that future through a study that could the diagnose and treat of mental health disorders one day be aided through the help of machine learning. The study findings were published in the journal Molecular Psychiatry.

Mental disorder

Bo Cao led a research team that used a machine learning algorithm to examine functional MRI images of both newly diagnosed schizophrenia patients and healthy subjects. Credit: Ross Neitz

The research team used a machine-learning algorithm to examine functional magnetic resonance imaging (MRI) images of both newly diagnosed, previously untreated schizophrenia patients and healthy subjects. By measuring the connections of a brain region called the superior temporal cortex to other regions of the brain, the algorithm successfully identified patients with schizophrenia at 78% accuracy. It also predicted with 82% accuracy whether or not a patient would respond positively to a specific antipsychotic treatment named risperidone. Further validations on large samples will be necessary and more refinement is needed to increase accuracy before the work can be translated into a useful tool in a clinical environment.

Asst. Prof. Bo Cao said, “This is the first step, but ultimately we hope to find reliable biomarkers that can predict schizophrenia before the symptoms show up” and further added, 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.”


More Information: Bo Cao et al, “Treatment response prediction and individualized identification of first-episode drug-naïve schizophrenia using brain functional connectivity”, Molecular Psychiatry (2018). DOI: 10.1038/s41380-018-0106-5 


You may also like...

Leave a Reply

Your email address will not be published. Required fields are marked *