The thing with a lot of diseases and health problems is that it is usually better when it is detected early. In some cases early detection means a higher chance of being cured, or in some cases where it is incurable, early detection can mean that victims can take measures to slow its progress and to prevent it from becoming too severe, such as in the case of schizophrenia.
So how does one detect schizophrenia? There are methods that are being employed, but it seems that IBM believes it could be a lot more efficient, and in research efforts conducted together with the University of Alberta, it looks like AI could be used in helping to diagnose the onset of the disease.
The neural network was trained by looking at anonymized fMRI images of brains, which was a mixture of both patients who are healthy and those who have been diagnosed with schizophrenia. The images show the blood flow through various parts of the brain as patients completed an audio-based exercise, and the neural network then put together a predictive model of whether or not a patient had schizophrenia based on the blood flow.
According to Dr. Serdar Dursun, a Professor of Psychiatry & Neuroscience with the University of Alberta, “We’ve discovered a number of significant abnormal connections in the brain that can be explored in future studies, and AI-created models bring us one step closer to finding objective neuroimaging-based patterns that are diagnostic and prognostic markers of schizophrenia.”