Behind the Screen: A Narrative Review on the Translational Capacity of Passive Sensing for Mental Health Assessment

Bryan, Anastasia C.; Heinz, Michael V.; Salzhauer, Abigail J.; Price, George D.; Tlachac, M. L.; Jacobson, Nicholas C.

doi:10.1007/s44174-023-00150-4

Cited by 3 publications

(1 citation statement)

References 228 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our study has notable strengths, including a nationally-recruited, demographically diverse, moderate sample size. Further, unlike many digital mental health studies, 39 Therabot ran on both Android and iOS devices, increasing generalizability. However, we also acknowledge several limitations.…”

Section: Discussionmentioning

confidence: 99%

Evaluating Therabot: A Randomized Control Trial Investigating the Feasibility and Effectiveness of a Generative AI Therapy Chatbot for Depression, Anxiety, and Eating Disorder Symptom Treatment

Heinz,

Mackin,

Trudeau

et al. 2024

Preprint

View full text Add to dashboard Cite

Background:Chatbots powered by generative AI (Gen-AI) hold promise for building highly personalized, effective mental health treatments at scale, while also addressing existing user engagement and retention issues common among digital therapeutics. We present the first RCT testing an expert-fine-tuned Gen-AI-powered chatbot, Therabot, for mental health treatment.Methods:Participants (N=210) were randomized to a four-week Therabot intervention (N=106) or waitlist control (WLC; N=104). Subjects were clinically stratified into major depressive disorder (MDD), generalized anxiety disorder (GAD), or clinically high risk feeding and eating disorder (CHR-FED) groups using baseline symptom severity. Primary outcomes included disorder-specific symptom changes from baseline to four and eight weeks. Secondary outcomes included user engagement, acceptability, and therapeutic alliance. Cumulative link mixed models examined differential changes pre- to post-intervention and from pre-intervention to follow-up, between the Therabot and WLC groups.Results:The Therabot group showed large and significantly greater reductions in MDD (d = 0.845-0.903), GAD (d = 0.794-0.840), and CHR-FED (d = 0.627-0.819) symptoms relative to controls at post-intervention and follow-up. Therabot was well received and well-utilized (average use >6 hours), and participants rated the therapeutic alliance comparable to human therapists.Conclusions:This is the first RCT demonstrating the effectiveness of a fully Gen-AI therapy chatbot for treating mental health disorders. Results are promising for MDD, GAD, and CHR-FED symptom reduction. Participants were engaged with Therabot, reported exceptional therapeutic alliance, and rated the intervention highly. Fine-tuned Gen-AI chatbots are a feasible method for creating scalable, personalized interventions in mental health.

show abstract

Section: Discussionmentioning

confidence: 99%

Evaluating Therabot: A Randomized Control Trial Investigating the Feasibility and Effectiveness of a Generative AI Therapy Chatbot for Depression, Anxiety, and Eating Disorder Symptom Treatment

Heinz,

Mackin,

Trudeau

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Evaluating a mobile app’s effects on depression and anxiety in medication-treated opioid use disorder

Heinz,

Lekkas,

Abreu

et al. 2024

npj Mental Health Res

View full text Add to dashboard Cite

Depression and anxiety frequently co-occur with opioid use disorder (OUD) yet are often overlooked in standard OUD treatments. This study evaluated the feasibility, acceptability, and preliminary effectiveness of a mobile application designed to address these symptoms in individuals receiving medications for OUD (MOUD). A randomized controlled trial recruited N = 63 adults with OUD who received MOUD and screened positive for moderate depression or generalized anxiety. Participants were randomized to an app-based digital intervention or treatment-as-usual for 4 weeks, and completed follow-ups at 4 and 8 weeks. Primary outcomes were self-reported severity measures for depression and generalized anxiety, and urine drug screens (UDS). Secondary outcomes included self-reported OUD severity, craving intensity, and digital biomarkers derived from passive smartphone sensors. The application was well-received (median app rating = 4/5 stars). The intervention group showed significant reductions in depressive and generalized anxiety symptoms post-intervention and at 8 weeks follow-up ( d > 0.70), with large ( d = 0.78) and moderate ( d = 0.38) effect sizes, respectively, compared to controls. Both groups exhibited substantial decreases in self-reported severity of opioid use symptoms ( d > 2.50). UDS suggested similar between-group adherence to MOUD, with a marginal decrease in opioid (MOP) use in the intervention group and increase in controls, yielding medium between group effect sizes ( d = 0.44). Passive sensor data suggested significant increases in social connectedness in the intervention group, evidenced by a significant rise in incoming and outgoing calls and text connections. Initial evidence supports the feasibility and acceptability of a digital intervention for treating anxiety and depressive symptoms in persons receiving MOUD. While underpowered to confidently determine statistical significance beyond directionality, the intervention showed promise in reducing depressive and anxiety symptoms, suggesting its potential as a cost-effective and scalable adjunctive therapy alongside standard OUD treatment. Due to the preliminary nature of this pilot study, further research with sample sizes permitting greater statistical power is needed to confirm findings and explore long-term effects.

show abstract

Mental Health and Mobile Communication Profiles of Crowdsourced Participants

Tlachac,

Heinz

2024

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Behind the Screen: A Narrative Review on the Translational Capacity of Passive Sensing for Mental Health Assessment

Cited by 3 publications

References 228 publications

Evaluating Therabot: A Randomized Control Trial Investigating the Feasibility and Effectiveness of a Generative AI Therapy Chatbot for Depression, Anxiety, and Eating Disorder Symptom Treatment

Evaluating Therabot: A Randomized Control Trial Investigating the Feasibility and Effectiveness of a Generative AI Therapy Chatbot for Depression, Anxiety, and Eating Disorder Symptom Treatment

Evaluating a mobile app’s effects on depression and anxiety in medication-treated opioid use disorder

Mental Health and Mobile Communication Profiles of Crowdsourced Participants

Contact Info

Product

Resources

About