MétaCan
Menu
← Back to cohort
Record W4410591093 · doi:10.2196/56176

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

2025· article· en· W4410591093 on OpenAlexvenueno aff
Chongwu Xiao, Yijin Zhao, Gege Li, Zhuodong Zhang, Siyu Liu, Weichao Fan, Jinjing Hu, Qiuru Yao, Chengduan Yang, Jihua Zou, Guozhi Huang

Bibliographic record

VenueJMIR mhealth and uhealth · 2025
Typearticle
Languageen
FieldMedicine
TopicMusculoskeletal pain and rehabilitation
Canadian institutionsnot available
Fundersnot available
KeywordsTelerehabilitationPhysical therapyMedicineRandomized controlled trialOswestry Disability IndexPhysical medicine and rehabilitationManual therapyVisual analogue scaleLow back painTelemedicineHealth care

Abstract

fetched live from OpenAlex

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 therapeutic effects compared to conventional exercise telerehabilitation in people with CNSLBP. This study provides guidance for developing effective real-time home-based exercise therapies for people with CNSLBP, which may help reduce economic and human resource costs associated with treatment.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.005
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Randomized trial · Consensus signal: Randomized trial
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.012
Threshold uncertainty score0.040

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.005
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0070.004
Bibliometrics0.0010.001
Science and technology studies0.0010.002
Scholarly communication0.0020.002
Open science0.0020.001
Research integrity0.0030.003
Insufficient payload (model declined to judge)0.0120.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.026
GPT teacher head0.410
Teacher spread0.383 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designRandomized trial
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations12
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJMIR mhealth and uhealth→Same topicMusculoskeletal pain and rehabilitation→French-language works237,207→