Safety and User Experience of a Generative Artificial Intelligence Digital Mental Health Intervention: Exploratory Randomized Controlled Trial

BackgroundGeneral awareness and exposure to generative artificial intelligence (AI) have increased recently. This transformative technology has the potential to create a more dynamic and engaging user experience in digital mental health interventions (DMHIs). However, if not...

Full description

Saved in:
Bibliographic Details
Main Authors: Timothy R Campellone, Megan Flom, Robert M Montgomery, Lauren Bullard, Maddison C Pirner, Aaron Pavez, Michelle Morales, Devin Harper, Catherine Oddy, Tom O'Connor, Jade Daniels, Stephanie Eaneff, Valerie L Forman-Hoffman, Casey Sackett, Alison Darcy
Format: Article
Language:English
Published: JMIR Publications 2025-05-01
Series:Journal of Medical Internet Research
Online Access:https://www.jmir.org/2025/1/e67365
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850150991591112704
author Timothy R Campellone
Megan Flom
Robert M Montgomery
Lauren Bullard
Maddison C Pirner
Aaron Pavez
Michelle Morales
Devin Harper
Catherine Oddy
Tom O'Connor
Jade Daniels
Stephanie Eaneff
Valerie L Forman-Hoffman
Casey Sackett
Alison Darcy
author_facet Timothy R Campellone
Megan Flom
Robert M Montgomery
Lauren Bullard
Maddison C Pirner
Aaron Pavez
Michelle Morales
Devin Harper
Catherine Oddy
Tom O'Connor
Jade Daniels
Stephanie Eaneff
Valerie L Forman-Hoffman
Casey Sackett
Alison Darcy
author_sort Timothy R Campellone
collection DOAJ
description BackgroundGeneral awareness and exposure to generative artificial intelligence (AI) have increased recently. This transformative technology has the potential to create a more dynamic and engaging user experience in digital mental health interventions (DMHIs). However, if not appropriately used and controlled, it can introduce risks to users that may result in harm and erode trust. At the time of conducting this trial, there had not been a rigorous evaluation of an approach to safely implementing generative AI in a DMHI. ObjectiveThis study aims to explore the user relationship, experience, safety, and technical guardrails of a DMHI using generative AI compared with a rules-based intervention. MethodsWe conducted a 2-week exploratory randomized controlled trial (RCT) with 160 adult participants randomized to receive a generative AI (n=81) or rules-based (n=79) version of a conversation-based DMHI. Self-report measures of the user relationship (client satisfaction, working alliance bond, and accuracy of empathic listening and reflection) and experience (engagement metrics, adverse events, and technical guardrail success) were collected. Descriptions and validation of technical guardrails for handling user inputs (eg, detecting potentially concerning language and off-topic responses) and model outputs (eg, not providing medical advice and not providing a diagnosis) are provided, along with examples to illustrate how they worked. Safety monitoring was conducted throughout the trial for adverse events, and the success of technical guardrails created for the generative arm was assessed post trial. ResultsIn general, the majority of measures of user relationship and experience appeared to be similar in both the generative and rules-based arms. The generative arm appeared to be more accurate at detecting and responding to user statements with empathy (98% accuracy vs 69%). There were no serious or device-related adverse events, and technical guardrails were shown to be 100% successful in posttrial review of generated statements. A majority of participants in both groups reported an increase in positive sentiment (62% and 66%) about AI at the end of the trial. ConclusionsThis trial provides initial evidence that, with the right guardrails and process, generative AI can be successfully used in a digital mental health intervention (DMHI) while maintaining the user experience and relationship. It also provides an initial blueprint for approaches to technical and conversational guardrails that can be replicated to build a safe DMHI. Trial RegistrationClinicalTrials.gov NCT05948670; https://clinicaltrials.gov/study/NCT05948670
format Article
id doaj-art-5f5c9ad183474f47a0f96cfc92410366
institution OA Journals
issn 1438-8871
language English
publishDate 2025-05-01
publisher JMIR Publications
record_format Article
series Journal of Medical Internet Research
spelling doaj-art-5f5c9ad183474f47a0f96cfc924103662025-08-20T02:26:24ZengJMIR PublicationsJournal of Medical Internet Research1438-88712025-05-0127e6736510.2196/67365Safety and User Experience of a Generative Artificial Intelligence Digital Mental Health Intervention: Exploratory Randomized Controlled TrialTimothy R Campellonehttps://orcid.org/0000-0002-8793-9576Megan Flomhttps://orcid.org/0000-0002-4896-1009Robert M Montgomeryhttps://orcid.org/0000-0001-9637-9753Lauren Bullardhttps://orcid.org/0000-0002-7368-2618Maddison C Pirnerhttps://orcid.org/0000-0002-3993-0606Aaron Pavezhttps://orcid.org/0009-0005-9358-7588Michelle Moraleshttps://orcid.org/0009-0005-0440-4373Devin Harperhttps://orcid.org/0009-0005-0955-8523Catherine Oddyhttps://orcid.org/0009-0000-9550-9560Tom O'Connorhttps://orcid.org/0009-0005-8214-0270Jade Danielshttps://orcid.org/0000-0001-8593-3712Stephanie Eaneffhttps://orcid.org/0000-0002-3657-5063Valerie L Forman-Hoffmanhttps://orcid.org/0000-0001-7885-8873Casey Sacketthttps://orcid.org/0009-0001-6314-0305Alison Darcyhttps://orcid.org/0000-0002-5082-7685 BackgroundGeneral awareness and exposure to generative artificial intelligence (AI) have increased recently. This transformative technology has the potential to create a more dynamic and engaging user experience in digital mental health interventions (DMHIs). However, if not appropriately used and controlled, it can introduce risks to users that may result in harm and erode trust. At the time of conducting this trial, there had not been a rigorous evaluation of an approach to safely implementing generative AI in a DMHI. ObjectiveThis study aims to explore the user relationship, experience, safety, and technical guardrails of a DMHI using generative AI compared with a rules-based intervention. MethodsWe conducted a 2-week exploratory randomized controlled trial (RCT) with 160 adult participants randomized to receive a generative AI (n=81) or rules-based (n=79) version of a conversation-based DMHI. Self-report measures of the user relationship (client satisfaction, working alliance bond, and accuracy of empathic listening and reflection) and experience (engagement metrics, adverse events, and technical guardrail success) were collected. Descriptions and validation of technical guardrails for handling user inputs (eg, detecting potentially concerning language and off-topic responses) and model outputs (eg, not providing medical advice and not providing a diagnosis) are provided, along with examples to illustrate how they worked. Safety monitoring was conducted throughout the trial for adverse events, and the success of technical guardrails created for the generative arm was assessed post trial. ResultsIn general, the majority of measures of user relationship and experience appeared to be similar in both the generative and rules-based arms. The generative arm appeared to be more accurate at detecting and responding to user statements with empathy (98% accuracy vs 69%). There were no serious or device-related adverse events, and technical guardrails were shown to be 100% successful in posttrial review of generated statements. A majority of participants in both groups reported an increase in positive sentiment (62% and 66%) about AI at the end of the trial. ConclusionsThis trial provides initial evidence that, with the right guardrails and process, generative AI can be successfully used in a digital mental health intervention (DMHI) while maintaining the user experience and relationship. It also provides an initial blueprint for approaches to technical and conversational guardrails that can be replicated to build a safe DMHI. Trial RegistrationClinicalTrials.gov NCT05948670; https://clinicaltrials.gov/study/NCT05948670https://www.jmir.org/2025/1/e67365
spellingShingle Timothy R Campellone
Megan Flom
Robert M Montgomery
Lauren Bullard
Maddison C Pirner
Aaron Pavez
Michelle Morales
Devin Harper
Catherine Oddy
Tom O'Connor
Jade Daniels
Stephanie Eaneff
Valerie L Forman-Hoffman
Casey Sackett
Alison Darcy
Safety and User Experience of a Generative Artificial Intelligence Digital Mental Health Intervention: Exploratory Randomized Controlled Trial
Journal of Medical Internet Research
title Safety and User Experience of a Generative Artificial Intelligence Digital Mental Health Intervention: Exploratory Randomized Controlled Trial
title_full Safety and User Experience of a Generative Artificial Intelligence Digital Mental Health Intervention: Exploratory Randomized Controlled Trial
title_fullStr Safety and User Experience of a Generative Artificial Intelligence Digital Mental Health Intervention: Exploratory Randomized Controlled Trial
title_full_unstemmed Safety and User Experience of a Generative Artificial Intelligence Digital Mental Health Intervention: Exploratory Randomized Controlled Trial
title_short Safety and User Experience of a Generative Artificial Intelligence Digital Mental Health Intervention: Exploratory Randomized Controlled Trial
title_sort safety and user experience of a generative artificial intelligence digital mental health intervention exploratory randomized controlled trial
url https://www.jmir.org/2025/1/e67365
work_keys_str_mv AT timothyrcampellone safetyanduserexperienceofagenerativeartificialintelligencedigitalmentalhealthinterventionexploratoryrandomizedcontrolledtrial
AT meganflom safetyanduserexperienceofagenerativeartificialintelligencedigitalmentalhealthinterventionexploratoryrandomizedcontrolledtrial
AT robertmmontgomery safetyanduserexperienceofagenerativeartificialintelligencedigitalmentalhealthinterventionexploratoryrandomizedcontrolledtrial
AT laurenbullard safetyanduserexperienceofagenerativeartificialintelligencedigitalmentalhealthinterventionexploratoryrandomizedcontrolledtrial
AT maddisoncpirner safetyanduserexperienceofagenerativeartificialintelligencedigitalmentalhealthinterventionexploratoryrandomizedcontrolledtrial
AT aaronpavez safetyanduserexperienceofagenerativeartificialintelligencedigitalmentalhealthinterventionexploratoryrandomizedcontrolledtrial
AT michellemorales safetyanduserexperienceofagenerativeartificialintelligencedigitalmentalhealthinterventionexploratoryrandomizedcontrolledtrial
AT devinharper safetyanduserexperienceofagenerativeartificialintelligencedigitalmentalhealthinterventionexploratoryrandomizedcontrolledtrial
AT catherineoddy safetyanduserexperienceofagenerativeartificialintelligencedigitalmentalhealthinterventionexploratoryrandomizedcontrolledtrial
AT tomoconnor safetyanduserexperienceofagenerativeartificialintelligencedigitalmentalhealthinterventionexploratoryrandomizedcontrolledtrial
AT jadedaniels safetyanduserexperienceofagenerativeartificialintelligencedigitalmentalhealthinterventionexploratoryrandomizedcontrolledtrial
AT stephanieeaneff safetyanduserexperienceofagenerativeartificialintelligencedigitalmentalhealthinterventionexploratoryrandomizedcontrolledtrial
AT valerielformanhoffman safetyanduserexperienceofagenerativeartificialintelligencedigitalmentalhealthinterventionexploratoryrandomizedcontrolledtrial
AT caseysackett safetyanduserexperienceofagenerativeartificialintelligencedigitalmentalhealthinterventionexploratoryrandomizedcontrolledtrial
AT alisondarcy safetyanduserexperienceofagenerativeartificialintelligencedigitalmentalhealthinterventionexploratoryrandomizedcontrolledtrial