Funding Source
National Center for Complementary and Integrative Health (NCCIH) / NIH Office of the Director,1R34AT013641-01
Project Period
9/1/2026 – 8/31/2029
Principal Investigator
Nicholas C. Jacobson, PhD (Geisel School of Medicine at Dartmouth); Michael Heinz, MD (Geisel School of Medicine at Dartmouth)
Other Project Staff
Project Summary
Depression and anxiety disorders are among the most prevalent mental health conditions, affecting millions of individuals and imposing a significant burden on individuals, families, and society. Despite the availability of effective treatments, many people face barriers to accessing care, including cost, stigma, and limited availability of mental health providers. Digital mental health interventions, particularly those leveraging artificial intelligence (AI), offer a promising avenue to increase access to personalized, on-demand support. However, most existing digital interventions lack the ability to dynamically adapt to an individual’s real-time physiological and behavioral state. In response to this need, our team developed Therabot, a generative AI chatbot that has shown promise in reducing symptoms of depression and anxiety in prior research. In a recent randomized controlled trial, Therabot demonstrated significant symptom reduction compared to a waitlist control, high user engagement, and strong therapeutic alliance ratings.
To further enhance the personalization and effectiveness of Therabot, this project seeks to develop and pilot test an enhanced version, called Therabot+, which integrates real-time biofeedback and passive sensing data from smartphones. Therabot+ will leverage heart rate variability (HRV) biofeedback, a mind-body technique with demonstrated efficacy in reducing stress and anxiety. During prompted biofeedback sessions, Therabot+ will collect HRV data through a smartphone’s camera and provide the user with personalized feedback and guidance on relaxation techniques, such as deep breathing and mindfulness exercises. Therabot+ will also utilize passive sensing data, including measures of sleep, activity, and social engagement, to personalize interventions and initiate just-in-time adaptive interventions (JITAIs) when potential triggers for depression or anxiety are detected. This R34 feasibility trial will enroll 60 adults diagnosed with major depressive disorder and/or generalized anxiety disorder. Participants will be randomized to receive either Therabot+ or standard Therabot for eight weeks. The study has three specific aims: (1) determine the feasibility of recruitment, retention, and data collection procedures; (2) assess the feasibility and acceptability of Therabot+ compared to standard Therabot; and (3) gather exploratory data on the feasibility of collecting variables (e.g., HRV, rumination, physiological flexibility), which have basis for mediation/moderation aims in a subsequent R01 application.
This feasibility trial will provide critical data to refine Therabot+ and inform the design of a future, fully powered randomized controlled trial to evaluate its efficacy in improving mental health outcomes. The long- term goal of this research program is to develop and disseminate a scalable, personalized, and engaging digital therapeutic intervention that leverages the power of AI, biofeedback, and passive sensing to increase access to care and improve mental health for individuals with depression and anxiety.
Public Health Relevance
This research aims to transform mental health care by developing and pilot testing a smartphone application that integrates artificial intelligence, biofeedback, and personalized support to help individuals manage depression and anxiety. By harnessing the power of technology and real-time data, this research has the potential to improve treatment outcomes, increase access to care, and empower individuals to take a more active role in managing their mental health.