AI voice trainer shows promise in depression, anxiety treatment

Artificial intelligence could be a useful tool in mental health treatment, according to the results of a new pilot study led by University of Illinois Chicago researchers.

The study, which is the first to test an AI voice-based virtual trainer for behavioral therapy, found changes in patients’ brain activity along with improved symptoms of depression and anxiety after using Lumen, an AI voice assistant that provides a form of psychotherapy.

The UIC team said the results, which were published in the journal Translational Psychiatryoffers encouraging evidence that virtual therapy can play a role in filling gaps in mental health care, where waiting lists and disparities in access are often hurdles for patients, particularly from vulnerable communities, to overcome to receive care.

“We had a tremendous explosion of need, especially after COVID, with soaring levels of anxiety and depression and a shortage of practitioners,” said Dr. Olusola A. Ajilore, UIC professor of psychiatry and first co-author of the paper. “Technology like this can be a bridge. It is not intended to be a substitute for traditional therapy, but it may be an important gap before someone can seek treatment.

Lumen, which operates as a expertise within the Amazon Alexa app, was developed by Ajilore and senior study author Dr. Jun Ma, Beth and George Vitoux Professor of Medicine at UIC, and collaborator at the University of Washington in St. Louis and the State of Pennsylvania University, with $2 million grant support from the National Institute of Mental Health.

UIC researchers recruited more than 60 patients for a clinical study exploring the app’s effect on symptoms of mild to moderate depression and anxiety, and activity in areas of the brain previously shown to be associated with the benefits of problem-solving therapy.

Two-thirds of patients used Lumen on a study-provided iPad for eight sessions of problem-solving therapy, with the remainder serving as a “waiting list” control receiving no intervention.

After the intervention, study participants who used the Lumen app showed reduced scores for depression, anxiety, and psychological distress compared to the control group. The Lumen group also showed improvements in problem-solving skills that correlated with increased activity in the dorsolateral prefrontal cortex, an area of ​​the brain associated with cognitive control. Promising results for women and underrepresented populations were also found.

“It’s about changing the way people think about problems and how to deal with them, and not get overwhelmed emotionally,” said Ma. “It is an established patient-driven, pragmatic behavioral therapy, which makes it suitable for delivery using voice-based technologies.”

Larger trials comparing Lumen use with a control group on a waiting list, and patients receiving human-trained problem-solving therapy are currently being conducted by researchers. They stress that virtual coaches don’t need to outperform human therapists to meet an urgent need in the mental health system.

“The way we have to think about digital mental health services is not for these apps to replace people, but rather to recognize the gaps we have between supply and demand, and then find new, effective, and safe ways to provide care to individuals who are otherwise. don’t have access, to fill that gap,” Ma said.

The study’s first co-author is Thomas Kannampalil at the University of Washington in St. Louis.

Other investigators include Aifeng Zhang, Nan Lv, Nancy E. Wittels, Corina R. Ronneberg, Vikas Kumar, Susanth Dosala, Amruta Barve, Kevin C. Tan, Kevin K. Cao, Charmi R. Patel and Emily A. Kringle, all UIC ; Joshua Smyth and Jillian A. Johnson at Pennsylvania State University; and Lan Xiao at Stanford University.