Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: Journal of Medical Internet Research

Date Submitted: Oct 15, 2024
Date Accepted: Apr 7, 2025

The final, peer-reviewed published version of this preprint can be found here:

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

Campellone TR, Flom M, Montgomery RM, Bullard L, Pirner MC, Pavez A, Morales M, Harper D, Oddy C, O'Connor T, Daniels J, Eaneff S, Forman-Hoffman VL, Sackett C, Darcy A

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

J Med Internet Res 2025;27:e67365

DOI: 10.2196/67365

PMID: 40408143

PMCID: 12144468

Validating the safety and user experience of a generative AI digital mental health intervention

  • 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

ABSTRACT

Background:

General awareness and exposure to generative artificial intelligence (AI) has increased in recent years. 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 utilized and controlled, this technology can introduce risks to users that may result in harm and erode trust.

Objective:

This randomized controlled trial (RCT) aims to explore the user relationship, satisfaction, safety and technical guardrails of a DMHI using generative AI compared against a rules-based intervention.

Methods:

We conducted a 2-week exploratory RCT of 160 adult participants randomized to receive a generative AI (n = 81) or rules-based (n = 79) version of a DMHI. Self-report measures of the user relationship and satisfaction were collected. 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.

Results:

In general, measures of user relationship and satisfaction 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. There were no serious- or device-related adverse events and technical guardrails were shown to be very effective in post-trial review of generated statements.

Conclusions:

This 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. Clinical Trial: The study was first posted on ClinicalTrials.gov (#NCT05948670) on July 17th, 2023.


 Citation

Please cite as:

Campellone TR, Flom M, Montgomery RM, Bullard L, Pirner MC, Pavez A, Morales M, Harper D, Oddy C, O'Connor T, Daniels J, Eaneff S, Forman-Hoffman VL, Sackett C, Darcy A

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

J Med Internet Res 2025;27:e67365

DOI: 10.2196/67365

PMID: 40408143

PMCID: 12144468

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.