Machine Learning Enhances Mental Illness Diagnosis

By combining machine learning with brain imaging, scientists have developed a way to differentiate different kinds of mental illnesses based on MRI scans.

AsianScientist (Oct. 2, 2020) – A machine learning algorithm has grasped how to identify mental health conditions such as autism and schizophrenia from magnetic resonance imaging (MRI) brain scans. These findings, by researchers at the University of Tokyo, Japan, have been published in Translational Psychiatry.

While most of modern medicine has physical tests or objective techniques to define much of what ails us, there is currently no blood or genetic test that can definitively diagnose a mental illness, and certainly none to distinguish between different psychiatric disorders with similar symptoms.

“Psychiatrists, including me, often talk about symptoms and behaviors with patients and their teachers, friends and parents. We only meet patients in the hospital or clinic, not out in their daily lives. We have to make medical conclusions using subjective, secondhand information,” explained Shinsuke Koike, an associate professor at the University of Tokyo and a senior author of the study. “Frankly, we need objective measures.”

Using the brain scans of 206 participants—including patients already diagnosed with autism spectrum disorder or schizophrenia, individuals considered high risk for schizophrenia and those who have experienced their first instance of psychosis—Koike and his team were able to train a machine learning algorithm to distinguish between the different conditions.

The algorithm learned to associate different psychiatric diagnoses with variations in the thickness, surface area or volume of areas of the brain in MRI images. It is not yet known why any physical difference in the brain is often linked to a specific mental health condition.

After the training period, the algorithm was tested with brain scans from 43 additional patients. The machine’s diagnosis matched the psychiatrists’ assessments with high reliability and up to 85 percent accuracy. Importantly, the algorithm could distinguish between non-patients, patients with autism spectrum disorder, and patients with either schizophrenia or schizophrenia risk factors.

“Autism spectrum disorder patients have a ten-times higher risk of schizophrenia than the general population. Social support is needed for autism, but generally the psychosis of schizophrenia requires medication, so distinguishing between the two conditions or knowing when they co-occur is very important,” said Koike.

The team found that the thickness of the cerebral cortex was the most useful feature for correctly distinguishing between individuals with autism spectrum disorder, schizophrenia and neurotypical individuals. This highlights the role of cortex thickness in distinguishing between different psychiatric disorders and may direct future studies on understanding the causes of mental illness.

Now that their machine learning algorithm has proven its value, the researchers plan to begin using larger datasets and hopefully coordinate multisite studies to train the program to work regardless of the MRI differences.

The article can be found at: Yassin et al. (2020) Machine-learning Classification Using Neuroimaging Data in Schizophrenia, Autism, Ultra-high Risk and First-episode Psychosis.


Source: University of Tokyo; Photo: Shinsuke Koike.
Disclaimer: This article does not necessarily reflect the views of AsianScientist or its staff.

Asian Scientist Magazine is an award-winning science and technology magazine that highlights R&D news stories from Asia to a global audience. The magazine is published by Singapore-headquartered Wildtype Media Group.

Related Stories from Asian Scientist