AI’s Role in Improving Mental Health Care

Recent research from Cedars-Sinai has demonstrated that artificial intelligence (AI) can serve as an effective tool in mental health therapy. Two studies revealed that virtual therapists—AI-driven avatars—provide well-received, bias-free counseling, offering promising new methods for addressing mental health challenges.

Mental health depicted in sad, neutral and happy faces.

Image Credit: SewCreamStudio/Shutterstock.com

In one study, virtual therapy sessions with AI avatars received positive feedback from patients struggling with alcohol addiction. Another study provided evidence that these virtual therapists offer unbiased counseling regardless of factors like race, gender, or income level.

The research utilized a VR-based application developed at Cedars-Sinai, combining AI and virtual reality (VR) goggles. The system features AI-trained avatars designed to deliver therapy sessions in calming, virtual environments.

Study One: Supporting Patients with Alcohol Addiction

The first study, published in the Journal of Medical Extended Reality, explored the use of the VR-based application to deliver therapy to 20 patients suffering from alcohol-associated cirrhosis. This severe liver condition often results from long-term excessive alcohol consumption. Each participant engaged in a 30-minute counseling session with a virtual therapist avatar trained in motivational interviewing, cognitive behavioral therapy, and other behavioral modification techniques.

The results were overwhelmingly positive: over 85 % of participants reported finding the sessions beneficial, and 90 % expressed interest in continuing therapy with virtual therapists.

For individuals awaiting liver transplants for cirrhosis, alcohol addiction remains a high-risk factor. We see VR as a way to augment traditional interventions, which often fall short due to a shortage of mental health professionals, societal stigmatizing of alcoholism and other factors.

Brennan Spiegel, MD, MSHS, Study Corresponding Author, Professor and Director, Health Services Research, Cedars-Sinai

Dr. Spiegel also referenced previous research demonstrating that VR experiences can help regulate stress levels and even influence immune responses.

Study Two: Eliminating Bias in Counseling

The second study, published in Cyberpsychology, Behavior, and Social Networking, assessed whether virtual therapists could provide equitable care regardless of a patient's demographics. Researchers introduced virtual therapists to AI-simulated patients seeking help for anxiety or depression. Each virtual patient was assigned a randomized profile detailing traits such as age, gender, race, ethnicity, and annual income. A control group without specific profiles was also included.

Using a standardized "tone analytics" scale, researchers evaluated the language tone used by virtual therapists during over 400 simulated conversations. The findings revealed no significant differences in tone scores based on a patient’s demographic profile or lack thereof.

This data suggests that with thoughtful design, AI can offer equitable and personalized care,” added Spiegel.

These studies emphasize Cedars-Sinai's pioneering role in adopting innovative technologies to address complex healthcare challenges. Dr. Peter Chen, interim chair of the Department of Medicine and Medallion Chair in Molecular Medicine, highlighted the institution’s commitment to harnessing AI's potential responsibly.

These two studies underscore Cedars-Sinai’s commitment to exploring the tremendous potential of artificial intelligence for mental health therapy while ensuring that this technology does not perpetuate human biases in delivering healthcare. Cedars-Sinai has become a world leader in tackling this formidable challenge.

Peter Chen, MD, Professor, Medallion Chair and Acting Chair, the Department of Medicine, Molecular Medicine, Cedars-Sinai

Journal References:

Hui Yeo, Y., et al. (2024) The Feasibility and Usability of an Artificial Intelligence-Enabled Conversational Agent in Virtual Reality for Patients with Alcohol-Associated Cirrhosis: A Multi-Methods Study. Journal of Medical Extended Reality. doi.org/10.1089/jmxr.2024.0033

Hui Yeo, Y., et al. (2025) Evaluating for Evidence of Sociodemographic Bias in Conversational AI for Mental Health Support. Cyberpsychology, Behavior, and Social Networking. doi.org/10.1089/cyber.2024.0199

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.