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: JMIR Rehabilitation and Assistive Technologies

Date Submitted: Nov 12, 2025
Date Accepted: Feb 10, 2026
Date Submitted to PubMed: Feb 19, 2026

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

A Therapeutic Conversational Agent (Solace) for Management of Chronic Pain: Acceptability and Usability Study

Slepian PM, Buryk-Iggers S, Lomanowska AM, Nguyen B, Janmohamed T, Clarke H, Katz J, Niederstrasser NG

A Therapeutic Conversational Agent (Solace) for Management of Chronic Pain: Acceptability and Usability Study

JMIR Rehabil Assist Technol 2026;13:e87689

DOI: 10.2196/87689

PMID: 41711568

Solace, a Therapeutic Conversational Agent for Management of Chronic Pain: Acceptability and Usability Study

  • P. Maxwell Slepian; 
  • Stephanie Buryk-Iggers; 
  • Anna M. Lomanowska; 
  • Binh Nguyen; 
  • Tahir Janmohamed; 
  • Hance Clarke; 
  • Joel Katz; 
  • Nils G. Niederstrasser

ABSTRACT

Background:

Chronic pain is a critical cause of personal suffering and societal concern. However, treatment options remain inadequate and access to efficacious treatment is limited by geography, economics, and scale. Digital health interventions for chronic pain are easily scaled solutions to this problem and autonomous conversational agents represent a new frontier in this treatment domain. Despite their potential impact, conversational agents powered by generative artificial intelligence (AI) have yet to be developed or examined for treatment of chronic pain.

Objective:

We sought to develop and test Solace, a first-of-its-kind, expert trained generative AI conversational agent designed to deliver support grounded in principles of evidence-based pain psychology.

Methods:

We conducted an acceptability and usability study of Solace in a group of individuals with chronic pain. Participants (n=175) were recruited from Prolific, an online crowdsourcing platform, and interacted with Solace for 30 minutes. Self-report measures of system usability, treatment acceptability, and therapeutic alliance were completed after the interaction and clinically relevant pain related measures were completed before and after the interaction.

Results:

Participants rated the usability of Solace to be excellent (System Usability Scale mean = 85.04) and found it to be an acceptable intervention for chronic pain. Therapeutic alliance between participants and Solace was rated highly. Participants also demonstrated improvements in anxiety, pain interference, kinesiophobia, and pain resilience. Safety guardrails designed to identify and manage instances of suicidal ideation, injury, or requests for medication recommendations performed appropriately during the study. Solace is a usable and acceptable treatment for chronic pain that facilitates forming a strong therapeutic alliance with users. A single 30-minute conversation with Solace was also associated with improvements in several clinically relevant domains.

Conclusions:

Solace is a usable and acceptable expert trained generative AI conversational agent for pain management. Randomized clinical trials are needed to evaluate the efficacy of Solace as a strategy for the treatment of chronic pain. Clinical Trial: This study has been registered with the Open Science Framework (OSF Registries osf.io/9c7tv, https://osf.io/9c7tv)


 Citation

Please cite as:

Slepian PM, Buryk-Iggers S, Lomanowska AM, Nguyen B, Janmohamed T, Clarke H, Katz J, Niederstrasser NG

A Therapeutic Conversational Agent (Solace) for Management of Chronic Pain: Acceptability and Usability Study

JMIR Rehabil Assist Technol 2026;13:e87689

DOI: 10.2196/87689

PMID: 41711568

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.