Forbes: Doctors use AI, supercomputer to predict and prevent mental illness

A collaboration between the University of Cincinnati, Cincinnati Children's Hospital, the University of Colorado and Oak Ridge National Laboratory is examining how artificial intelligence and the world's second most powerful supercomputer can help detect and diagnose mental illness.

John Pestian, PhD, a professor in UC’s Department of Pediatrics and director of the Computational Medicine Center at Cincinnati Children’s, told Forbes the technology could treat and alleviate up to 50% of mental illness that goes into adulthood.

“So catching it young, catching it early, and giving care is a very important part,” he said.

Pestian and his collaborators developed a model that assesses mental health risk factors and take into account personal, environmental, biological, emotional, social and thought process information. The supercomputer is needed to train the AI models in a helpful amount of time, more than 17,000 times faster than an average laptop could. 

The AI will in part analyze responses that children give to questions like "do you have secrets" or "are you angry," using additional data such as facal expressions and pauses between sentences to help identify if the patients are at a high, medium or low risk of depression or other mental health challenges. However, Pestian noted that there will continue to be a human element where physicians, mental health experts and school counselors help determine an individual child's risk.

The project's goal is to create "near real-time" modeling to help identify at-risk kids, especially those at risk for depression and suicidal thoughts.

Read the Forbes article.

Featured photo at top of Summit supercomputer courtesy of Oak Ridge National Laboratory.