Accepted for/Published in: JMIR Formative Research
Date Submitted: Feb 28, 2024
Date Accepted: Dec 12, 2024
Exploring the Effect of an Eight-Week AI-Composed Exercise Program on Pain Intensity and Well-Being in Patients with Spinal Pain: a retrospective cohort analysis
ABSTRACT
Background:
Back pain, one of the most common musculoskeletal disorders (MSDs), has a significant impact on global quality of life due to chronic pain and disability. Physical activity has shown promise in the management of back pain, although optimizing adherence to exercise remains a challenge. The digital development of artificial intelligence (AI)-driven applications offers a possibility for guiding and supporting patients with MSDs in their daily lives.
Objective:
The trial aims to investigate the effect of an eight-week AI-composed exercise programme on pain intensity and well-being in patients with back pain. It will also examine the relationship between exercise frequency, pain intensity and well-being. In addition, app-usage frequency is examined in order to make a statement about app-engagement.
Methods:
Data were collected retrospectively from the medicalmotion app between 1st January 2020 and 30th June 2023 from users who met the inclusion criteria. The intervention involved the use of the medicalmotion app, which provides 3-5 personalized exercise compositions each session based on individual user data. The primary outcomes assessed pain intensity and well-being, measured using numerical rating (NRS) and Likert scales, respectively. Data were collected at baseline (t0), 4 weeks (t1) and 8 weeks (t2). The correlation between exercise frequency and pain intensity as well as well-being was analyzed as a secondary outcome. In addition, average session length and frequency were measured to determine app-engagement. Statistical analysis included ANOVA, Greenhouse-Geisser correction, Bonferroni correction, and spearman correlation analysis.
Results:
The study included 379 participants with a mean age of 50.96 (12.22) years. At t2, there was a significant reduction of 1.76 points on the NRS (P<.001). The score on the Likert scale for well-being improved by 3.11 points after 8 weeks. Pain intensity showed a negative correlation with the number of daily exercises performed at t1 and t2. Well-being had a small negative correlation with the average number of exercises performed per day. The average number of exercises performed per day was 3.58. The average session length was approximately 10 minutes and was performed on an average of 49.2% of the available days.
Conclusions:
Overall, the study demonstrates that an app-based intervention programme can substantially reduce pain intensity and increase well-being in patients with back pain. This retrospective study showed that in a pre-selected population of app users, an app digitalizing multidisciplinary rehabilitation for the self-management of back pain reduced user-reported pain intensity significantly. The observed effect size was clinically relevant. Ongoing prospective randomized controlled trials (RCTs) will adjust for potential bias and selection effects. Clinical Trial: 05th August 2023 via OSF Registries https://doi.org/10.17605/OSF.IO/KJHEF
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.