Accepted for/Published in: JMIR Formative Research
Date Submitted: Jun 10, 2025
Date Accepted: Dec 26, 2025
A Gamified Pain Management Intervention for Adults with Chronic Pain in Mainland China: A Single-Arm Pre-Post Pilot Study with Machine Learning Predictive Modeling
ABSTRACT
Background:
Chronic pain (CP) is a widespread condition that significantly impacts daily functioning and quality of life. Despite the endorsement of biopsychosocial approaches in clinical guidelines, individuals with CP often struggle with maintaining physical activity.
Objective:
This study aimed to evaluate the effects of a Gamified Pain Management (GPM) program on chronic pain and psychological outcomes and to explore the use of machine learning (ML) models to predict treatment response, facilitating personalized pain interventions.
Methods:
An open for 10-week web-based GPM intervention was delivered to individuals with chronic pain. The intervention integrated educational content, progressive physical activities, and gamified elements. Pre- and post-intervention data were collected using validated instruments assessing pain intensity, pain interference, pain catastrophizing, depression, anxiety, and physical activity. ML models including Gradient Boosting and Random Forest were trained to predict clinically meaningful pain reductions. SHAP analysis and survival modeling were used to identify key predictors and estimate optimal treatment durations across pain subgroups. LASSO regression and Kaplan–Meier survival analysis were used to identify sessions or treatment time associated with improvement.
Results:
A total of 16 participants engaged, reporting significant improvements in pain intensity, pain interference, and psychological distress. ML models demonstrated high predictive accuracy, with key predictors including pain interference, catastrophizing, and engagement levels. LASSO regression identified session 3 and session 5 mostly predictive of clinical success, while association rule mining revealed effective session combinations for different patient subgroups. Time-to-event analyses indicated that individuals with low back pain and higher baseline severity required longer intervention durations for improvement.
Conclusions:
GPM effectively improved pain and psychological outcomes, while ML and data-driven analyses enabled personalized insight into treatment mechanisms and duration needs. These findings support the integration of AI-driven tools in scalable, adaptive self-management strategies for chronic pain. Clinical Trial: ChiCTR2400094247
Citation
The author of this paper has made a PDF available, but requires the user to login, or create an account.
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.