Effects of an Artificial Intelligence–Assisted Health Program on Workers With Neck/Shoulder Pain/Stiffness and Low Back Pain: Randomized Controlled Trial
Bibliographic record
Abstract
BACKGROUND: Musculoskeletal symptoms such as neck and shoulder pain/stiffness and low back pain are common health problems in the working population. They are the leading causes of presenteeism (employees being physically present at work but unable to be fully engaged). Recently, digital interventions have begun to be used to manage health but their effectiveness has not yet been fully verified, and adherence to such programs is always a problem. OBJECTIVE: This study aimed to evaluate the improvements in musculoskeletal symptoms in workers with neck/shoulder stiffness/pain and low back pain after the use of an exercise-based artificial intelligence (AI)-assisted interactive health promotion system that operates through a mobile messaging app (the AI-assisted health program). We expected that this program would support participants' adherence to exercises. METHODS: We conducted a two-armed, randomized, controlled, and unblinded trial in workers with either neck/shoulder stiffness/pain or low back pain or both. We recruited participants with these symptoms through email notifications. The intervention group received the AI-assisted health program, in which the chatbot sent messages to users with the exercise instructions at a fixed time every day through the smartphone's chatting app (LINE) for 12 weeks. The program was fully automated. The control group continued with their usual care routines. We assessed the subjective severity of the neck and shoulder pain/stiffness and low back pain of the participants by using a scoring scale of 1 to 5 for both the intervention group and the control group at baseline and after 12 weeks of intervention by using a web-based form. We used a logistic regression model to calculate the odds ratios (ORs) of the intervention group to achieve to reduce pain scores with those of the control group, and the ORs of the subjective assessment of the improvement of the symptoms compared to the intervention and control groups, which were performed using Stata software (version 16, StataCorp LLC). RESULTS: We analyzed 48 participants in the intervention group and 46 participants in the control group. The adherence rate was 92% (44/48) during the intervention. The participants in the intervention group showed significant improvements in the severity of the neck/shoulder pain/stiffness and low back pain compared to those in the control group (OR 6.36, 95% CI 2.57-15.73; P<.001). Based on the subjective assessment of the improvement of the pain/stiffness at 12 weeks, 36 (75%) out of 48 participants in the intervention group and 3 (7%) out of 46 participants in the control group showed improvements (improved, slightly improved) (OR 43.00, 95% CI 11.25-164.28; P<.001). CONCLUSIONS: This study shows that the short exercises provided by the AI-assisted health program improved both neck/shoulder pain/stiffness and low back pain in 12 weeks. Further studies are needed to identify the elements contributing to the successful outcome of the AI-assisted health program. TRIAL REGISTRATION: University hospital Medical Information Network-Clinical Trials Registry (UMIN-CTR) 000033894; https://upload.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000038307.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.006 | 0.004 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.004 | 0.004 |
| Insufficient payload (model declined to judge) | 0.013 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".