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 20, 2023
Open Peer Review Period: Oct 20, 2023 - Dec 15, 2023
Date Accepted: Aug 15, 2024
(closed for review but you can still tweet)

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

An Automated Conversational Agent Self-Help Program: Randomized Controlled Trial

Foran HM, Kubb C, Mueller J, Poff S, Ung M, Li M, Smith EM, Akinyemi A, Kambadur M, Waller F, Graf M, Boureau YL

An Automated Conversational Agent Self-Help Program: Randomized Controlled Trial

J Med Internet Res 2024;26:e53829

DOI: 10.2196/53829

PMID: 39641985

PMCID: 11662185

A randomized controlled trial of an automated conversational agent self-help program

  • Heather M. Foran; 
  • Christian Kubb; 
  • Janina Mueller; 
  • Spencer Poff; 
  • Megan Ung; 
  • Margaret Li; 
  • Eric M. Smith; 
  • Akinniyi Akinyemi; 
  • Melanie Kambadur; 
  • Franziska Waller; 
  • Mario Graf; 
  • Y-Lan Boureau

ABSTRACT

Background:

Health promotion and growth-based interventions can be effective in improving well-being for individuals, but large gaps in access remain.

Objective:

The aim of this study was to develop and test the effectiveness and implementation of a new widely targeted conversational agent prevention program (Zenny) aimed at improving well-being.

Methods:

A total of 1244 individuals in the United States were randomized to either (1) a self-help program delivered via an automated conversational agent on WhatsApp or (2) evidence-based wellness resources available on the web. The primary outcomes were well-being (World Health Organization Well-being Scale), psychosocial flourishing (Flourishing Scale) and positive psychological health (Mental Health Continuum Short Form). Outcome measures were assessed at pre-assessment and at 1-month post-assessment. All analyses were performed with an intention-to-treat approach.

Results:

Both groups significantly improved in well-being (intervention: d = 0.20; active control: d = 0.37), psychosocial flourishing (intervention: d = 0.14; active control: d = 0.29), and positive psychological health (intervention: d = 0.13; active control: d = 0.39) at post-assessment but did not significantly differ in effectiveness. As hypothesized a priori, more days active engaging with the conversational agent was associated with larger improvements in well-being at post-assessment among participants in the intervention group. This indicates that the degree of engagement was important for change. Future studies should expand on ways to increase engagement when using conversational agents for self-help.

Conclusions:

Findings from this study suggest that this free conversational agent wellness self-help program had similar effectiveness to evidence-based web resources. Further studies should explore ways to increase engagement with the resources over time, since only a portion of participants were engaged, and engagement was associated with larger well-being improvements. Long-term follow-up studies are also needed to evaluate whether effects remain stable over time. Clinical Trial: ClinicalTrials.gov Identifier: NCT06208566


 Citation

Please cite as:

Foran HM, Kubb C, Mueller J, Poff S, Ung M, Li M, Smith EM, Akinyemi A, Kambadur M, Waller F, Graf M, Boureau YL

An Automated Conversational Agent Self-Help Program: Randomized Controlled Trial

J Med Internet Res 2024;26:e53829

DOI: 10.2196/53829

PMID: 39641985

PMCID: 11662185

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.