The increasing need for mental health support and a shortage of therapists have led to the development of the eXtended-reality Artificial Intelligence Assistant (XAIA). This platform combines spatial computing, virtual reality (VR), and artificial intelligence (AI) to provide immersive mental health support. Utilizing GPT-4 for AI-driven therapy, XAIA engaged participants with mild-to-moderate anxiety or depression in biophilic VR environments. Speaking with an AI therapy avatar in VR was considered acceptable, helpful, and safe, with participants observed to engage genuinely with the program. However, some still favored human interaction and identified shortcomings with using a digital VR therapist. The study provides initial evidence of the acceptability and safety of AI psychotherapy via spatial computing, warranting further research on technical enhancements and clinical impact.
The rising prevalence of mental health issues in the United States, exacerbated by factors such as the COVID-19 pandemic, economic strain, and the ubiquity of isolating technologies like social media, has outpaced the availability of psychotherapeutic care1,2,3,4. This situation, coupled with the high costs and stigma associated with psychotherapy, demands innovative solutions to deliver accessible, affordable, and stigma-free mental healthcare5,6,7.
Virtual reality (VR) employs spatial computing to create meaningful psychological experiences, promoting a sense of presence8. VR’s versatility enables users to experience serene natural settings or meditative landscapes, supporting treatments for conditions like anxiety and depression when integrated with cognitive behavioral therapy (CBT)9. However, personalizing CBT in VR remains a challenge, historically relying on real-time therapist interaction or pre-scripted content.
Advancements in artificial intelligence (AI), particularly Large Language Models (LLMs), provide an opportunity to enhance VR’s therapeutic potential. These models can simulate naturalistic conversations, paving the way for AI-driven digital therapists10. Yet, the efficacy of combining VR with AI therapy, including the establishment of a therapeutic alliance with a virtual avatar and the ability to address diverse biopsychosocial issues, has not been examined.
In this brief communication, we describe the eXtended-reality Artificial Intelligence Assistant (XAIA), a program developed at Cedars-Sinai that merges VR and AI to offer personalized, CBT-based mental health support. Users select from nine nature scenes and interact with “XAIA,” a robot avatar. Conversations are processed through a HIPAA-compliant server: audio is recorded, transcribed by speech-to-text AI, and responded to by LLM (GPT-4). The LLM output is sent through an “Appropriateness Classifier”—a stand-alone AI to detect potentially dangerous or unhelpful responses. If triggered, the LLM is again queried, and its response is again analyzed. Otherwise, the output is released to a text-to-speech AI, which finally, together with sentiment analysis meta-data controlling XAIAs expressions, plays to the user (Fig. 1). The system’s development involved iterative testing with therapists role-playing clinical scenarios, leading to continuous refinement of its psychotherapeutic communication.