Currently submitted to: JMIR Preprints
Date Submitted: May 23, 2026
Open Peer Review Period: May 22, 2026 - May 7, 2027
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
SomaAI: A Gamified, AI-Guided Somatic Tracking Application for Chronic Pain Self-Management
ABSTRACT
Background:
Chronic pain affects millions globally and frequently persists despite conventional biomedical treatment. Pain Reprocessing Therapy (PRT), a neuroscience-based intervention, has demonstrated significant efficacy, yet access remains limited to specialized clinical settings.
Objective:
This paper presents SomaAI, a prototype web application designed to deliver PRT-informed somatic tracking outside the clinic through an integrated combination of AI voice coaching, interactive 3D body mapping, and gamification mechanics.
Methods:
SomaAI was developed using Next.js 14, Unity WebGL, and ElevenLabs Conversational AI. System evaluation proceeded in two phases: synthetic user testing using five chronic pain profiles to stress-test the prototype, followed by a real-participant pilot study currently being initiated in collaboration with the Pain Psychology Center, recruiting 5-10 adults with chronic pain for 2-4 weeks of in-home use.
Results:
Synthetic testing informed iterative refinements to the Unity WebGL bridge, ElevenLabs agent prompt architecture, and safety-signal tracking interface. Real-participant pilot results are pending.
Conclusions:
SomaAI represents a proof-of-concept for embedding PRT-based somatic tracking within a gamified, AI-guided digital platform. If validated, this approach could democratize access to brain-based chronic pain recovery for the millions who currently lack access to specialized therapy.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© 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.