How Machine Learning Can Improve Treatment of Psychiatric Disorders

July 21, 2017

Earlier this year, IBM scientists collaborated with researchers at the University of Alberta and the IBM Alberta Centre for Advanced Studies to publish new research regarding the use of artificial intelligence and machine learning algorithms to predict instances of schizophrenia with a 74% accuracy.

In the US, up to 20 per cent of adults suffer from a mental health condition, with four per cent having a serious mental illness. Of those with severe psychiatric disorders, roughly half receive no treatment.

While early diagnosis and treatment tends to mean improved outcomes, there continues to be barriers. For schizophrenia, there is no medical testing that can provide an absolute diagnosis; this can translate into significant delay.

Computational psychiatry provides physicians with tools that enable them to objectively assess patients. In this schizophrenia research, it was learned that technology can be used to predict the likelihood of a previously-unseen patient having schizophrenia. Clinicians could, in theory, quantitatively determine the severity of common symptoms and measure the progression of the disease and effectiveness of treatment.

“This kind of innovative collaboration is just one example of the work being done between IBM and the University of Alberta through the IBM Alberta Centre for Advanced Studies,” says Guillermo A. Cecchi, Principal Research Staff Member, Computational Neuroscience, IBM Research. “For more than a decade, the Centre’s unique public/private approach to research has become an example at a global level of how teaming world-class scientists and researchers can drive greater discovery and progression of disruptive technologies to address some of our greatest challenges.”

“As part of the ongoing relationship, research teams will continue to investigate areas and connections in the brain that hold significant links to schizophrenia, and also explore ways to extend these techniques to other psychiatric disorders, such as depression or post-traumatic stress disorder,” added Irina Rish, Research Staff Member, AI Foundations Group, IBM Research. “IBM has always recognized that investment in research and development is an important driver in solving some of our greatest global health problems, and this research is indicative of that commitment.”