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.
Featured photo at top of Summit supercomputer courtesy of Oak Ridge National Laboratory.
Related Stories
Recent advances may speed time to endometriosis diagnosis
March 16, 2026
The average time to clinical diagnosis of endometriosis is nine years. Definitive diagnosis of the disease is difficult, and until recently, has relied on laparoscopic surgery. Now, as Medscape recently reported, novel clinical recommendations, advanced diagnostic tools and research into inflammation and immune responses, are bringing promise that women with endometriosis will find relief sooner and without surgery, according to experts, including Katie Burns, PhD, University of Cincinnati College of Medicine associate professor.
Position-specific helmets may not improve protection
March 16, 2026
Local 12 highlighted a new study by biomedical engineering researchers that looked at how well new football helmets protected players from impacts that can cause concussions.
UC biologist talks about 'pearmageddon'
March 16, 2026
WLWT talks to UC biologist and Department Head Theresa Culley about invasive, nonnative Callery pear trees that are spreading across Ohio forests after they were introduced by landscapers more than 50 years ago.