Clinical Efficacy of Multimodal Exercise Telerehabilitation Based on AI for Chronic Nonspecific Low Back Pain: Randomized Controlled Trial

Background: Exercise therapy is strongly recommended as a treatment for chronic nonspecific low back pain (CNSLBP). However, therapist-guided exercise therapy requires significant medical resources. Ordinary digital telerehabilitation affects efficacy due to a lack of guidance and dynamic support. Artificial intelligence (AI)-assisted interactive health promotion systems may solve these problems. Objective: We aimed to explore whether AI-assisted multimodal exercise telerehabilitation is superior to conventional telerehabilitation in the treatment of people with CNSLBP. Methods: This study was a prospective, double-arm, open-label, randomized clinical controlled trial. People with CNSLBP were randomly allocated to either the AI or video group, receiving AI-assisted multimodal exercise therapy or conventional video guidance, respectively, via a WeChat application add-in. The multimodal exercise consisted of deep core muscle, flexibility, Mackenzie, and breathing exercises. The exercises were performed for 30-45 minutes per session, 3 times a week, for 4 weeks. Participants underwent face-to-face assessment at baseline and week 4, and web-based assessment at weeks 2 and 8. The primary outcome was the change in Numerical Rating Scale (NRS) relative to baseline at week 4. Secondary outcomes included changes in the Roland-Morris Disability Questionnaire (RMDQ), Oswestry Disability Index (ODI), Pain Castastrophizing Scale (PCS), Timed Up-and-Go (TUG) test, and thickness of the transverse abdominus (TrA) and multifidus (MF) muscles relative to baseline at week 4. Generalized estimating equation and covariance were used to examine the efficacy of the interventions. Results: A total of 38 participants (19 participants per group) were recruited. Eighteen participants in the AI group and 16 participants in the video group completed and were included in the final analysis. There was a significant difference in NRS at week 4 between the AI group and video group (most severe NRS: -3.00 vs-1.50; adjusted mean difference-1.08, 95% CI-1.68 to-0.49; P<.001; mean NRS: -2.61 vs-1.62; adjusted mean difference-0.67, 95% CI-1.19 to-0.15; P=.01). The difference in most severe NRS persisted until week 8 (-3.06 vs -1.69; adjusted mean difference -0.95, 95% CI -1.73 to -0.18;P=.02). Compared with the video group at week 4, the AI group showed significant improvement in secondary outcomes,including RMDQ, PCS, and core muscle thickness of left TrA, right TrA, left MF, and right MF. Conclusions: We showed that 4 weeks of telerehabilitation based on AI-assisted multimodal exercise has better therapeuticeffects compared to conventional exercise telerehabilitation in people with CNSLBP. This study provides guidance fordeveloping effective real-time home-based exercise therapies for people with CNSLBP, which may help reduce economic andhuman resource costs associated with treatment.