Scientists develop AI-powered tool to accurately diagnose schizophrenia

Alone man

A team of researchers at the University of Alberta in Canada led by an Indian origin scientist has apparently developed an artificial intelligence (AI) powered tool that is capable of accurately diagnosing schizophrenia.

The AI tool has been named EMPaSchiz and it is expected to create a new revolution in the area of schizophrenia treatments and diagnosis.

During the study, researchers examined the brain scans of people using EMPaSchiz and found that schizophrenia was predicted accurately by 87 percent.

As per reports, this is for the first time that an AI tool is succeeding in predicting schizophrenia with a high rate of accuracy. Earlier, in 2017, researchers at IBM and Alberta developed a tool capable of predicting schizophrenia with 74 percent accuracy.

"Schizophrenia is characterized by a constellation of symptoms that might co-occur in patients. Two individuals with the same diagnosis might still present different symptoms. This often leads to misdiagnosis. Machine learning, in this case, is able to drive an evidence-based approach that looks at thousands of features in a brain scan to lead to an optimal prediction," said Sunil Kalmady, a postdoctoral researcher at the University of Alberta, and the lead author of the study in a statement.

In the study report published in the journal NPJ Schizophrenia, researchers noted that EMPaSchiz is one of the first AI owered learning tools trained exclusively on data from patients who were diagnosed but are not yet taking any forms of medication to treat their illness.

Researchers also revealed that use of this AI tool will be quite valuable in treating schizophrenia in its early stages.

A few days ago, another study conducted by researchers at the King's College London's Institute of Psychiatry, Psychology and Neuroscience and the University of Roehampton found that playing certain kinds of video games could reduce the visual hallucinations which are quite common among people with schizophrenia.

This article was first published on February 2, 2019
Related topics : Artificial intelligence