AI voice assistant found to be effective in mental health treatment

summary: Researchers conducted a pioneering pilot study using Lumen, an AI voice-based virtual coach, for behavioral therapy. The study showed encouraging results in patients’ depression and anxiety symptoms improving, along with marked changes in brain activity.

This study brings hope of using virtual therapy to alleviate problems associated with accessing mental health care. While this technology does not replace conventional therapy, it may serve as an important interim solution for patients awaiting treatment.

Important facts:

  1. Lumen, an AI voice assistant, was used in a pilot study to provide a form of psychotherapy, leading to improvements in patients’ depression and anxiety symptoms.
  2. The UIC study reported changes in brain activity in patients, particularly increased activity in the dorsolateral prefrontal cortex, a region associated with cognitive control.
  3. Researchers stress that while Lumen and similar technologies cannot replace human therapists, they can help bridge the supply and demand gap in mental health care.

sauce: University of Illinois

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

This study, the first to test an AI voice-based virtual coach for behavioral therapy, found changes in patients’ brain activity after using Lumen, an AI voice assistant that provides a form of psychotherapy, I found that my depression and anxiety symptoms improved.

The results presented by the UIC team were published in a magazine. translational psychiatryprovide encouraging evidence that virtual therapy can play a role in bridging the gap in mental health care. In mental health care, waiting lists and disparities in access are often hurdles that patients, especially in vulnerable areas, must overcome to receive treatment.

“Anxiety and depression rates have skyrocketed, especially in the aftermath of COVID-19, and health care workers are in short supply, creating an unbelievable explosion of need,” says UIC Psychiatry. Orsola A. Agiloa, Ph.D., professor and co-author of the book, said. paper.

“This kind of technology could be a bridge. It doesn’t replace conventional treatments, but it could be an important stopgap before treatment.”

Lumen, which runs as a skill in the Amazon Alexa application, is a collaboration between Asiloa and lead authors of the study, Dr. Jun Ma, M.D. Beth and George Vitout of UIC, St. Louis and the University of Washington in Pennsylvania. developed by He received the support of a $2 million grant from the university, the National Institute of Mental Health.

UIC researchers conducted a clinical study investigating the effects of the application on mild to moderate depression and anxiety symptoms, as well as activity in brain regions previously shown to be associated with the benefits of problem-solving therapy. recruited more than 60 patients for

Two-thirds of patients used Lumen on the study-provided iPad for eight problem-solving therapy sessions, while the remainder served as no-intervention “waiting list” controls.

After the intervention, study participants who used the Lumen app were shown to have lower depression, anxiety and distress scores compared to controls. The Lumen group also showed improved problem-solving skills that correlated with increased activity in the dorsolateral prefrontal cortex, a brain region associated with cognitive control. Promising results were also obtained for women and underrepresented populations.

“It’s important to change the way people think about the problem so they don’t get emotionally overwhelmed,” Ma said. “It is a well-established, practical, patient-driven behavioral therapy that is well suited for treatment using voice-based technology.”

Researchers are now conducting a large trial comparing Lumen use to both waiting-list controls and patients undergoing human-guided problem-solving therapy. They stress that virtual coaches do not have to outperform human therapists to meet the desperate needs of the mental health system.

“What we should be thinking about digital mental health services is not that these apps will replace humans, but that we recognize how much gap there is between supply and demand, and if we get other treatments, It’s about finding novel, effective and safe ways to provide treatment to people who are “don’t have access to fill that gap,” Ma said.

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

Other collaborators 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, Emily A. Includes Kringle. All about UIC. Joshua Smith and Jillian A. Johnson of Pennsylvania State University. And Mr. Lan Xiao of Stanford University.

About this AI and psychology research news

author: Brian Flood
sauce: University of Illinois
contact: Brian Flood – University of Illinois
image: Image credited to Neuroscience News

Original research: open access.
“Effects of Virtual Voice-Based Coaches Providing Problem-Solving Treatments for Emotional Distress and Brain Function: A Pilot RCT in Depression and Anxiety.” Olusola A. Ajilore et al. translational psychiatry


Effects of Virtual Voice-Based Coaches Providing Problem-Solving Treatments for Emotional Distress and Brain Function: A Pilot RCT in Depression and Anxiety

Consumer-based voice assistants have the ability to provide evidence-based care, but little is known about their therapeutic potential.

In a pilot trial of Lumen, a virtual voice-based coach that provides problem-solving therapy, adults with mild to moderate depression and anxiety were randomly assigned to the Lumen intervention.n= 42) or wait list control (n= 21).

Primary outcomes include changes in neural indices of emotional reactivity and cognitive control, hospital anxiety and depression scales. [HADS] Symptom scores over 16 weeks.

Participants were 37.8 years old (SD = 12.4), 68% female, 25% black, 24% Latino and 11% Asian. Activation of the right dlPFC (a neural region of interest in cognitive control) was decreased in the intervention group but increased in the control group, with effect sizes meeting pre-specified thresholds for meaningful effects. (Cohen’s theory) d= 0.3).

Between-group differences in changes in activation of the left dlPFC and bilateral amygdala were observed, but on a smaller scale (d= 0.2). Changes in right dlPFC activation were also significantly associated (r≥ 0.4), with changes in self-reported problem-solving ability and avoidance of intervention.

Lumen interventions also led to reductions in HADS depression, anxiety, and global psychological distress scores, with modest effect sizes (Cohen’s d= 0.49, 0.51, 0.55, respectively) compared with the wait list control group.

This pilot study showed promising effects of a novel digital mental health intervention on cognitive control using neuroimaging and depression and anxiety symptoms, providing foundational evidence for future confirmatory studies.

Source link

Leave a Reply

Your email address will not be published. Required fields are marked *