IBM creates AI models to detect Schizophrenia

In today’s advanced world, any big disease or mental health problem can be treated very easily. Similarly, schizophrenia, a mental health disorder which affects around 3.2 million people around the world can be a very dangerous.

However, IBM and the University of Alberta have conducted a pioneering research using Artificial Intelligence (AI) that could help doctors detect the onset of the disease and severity of its symptoms. It uses an MRI scan and a neural network built to look at the blood flow to the brain.

The neural network is trained by looking at the MRI images of the brain of patients who are healthy and those who have been diagnosed with schizophrenia. The images show the blood flow through different parts of the brain as patients completed an audio based exercise and the neural network then put together a predictive model of whether the patient has schizophrenia based on the blood flow.

These AI created models have been able to accurately distinguish between the control group and those with schizophrenia with 74 percent accuracy.

Endgadget reports that Dr. Serdar Dursun, a Professor of Psychiatry & Neuroscience with the University of Alberta said, “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.” He added that these insights could lead researchers to more effective diagnostic tools and treatment options.