LONG-TERM EFFECTS OF DEEP-LEARNING DIGITAL THERAPEUTICS ON PAIN, MOVEMENT CONTROL, AND PRELIMINARY COST-EFFECTIVENESS IN LOW BACK PAIN: A RANDOMIZED CONTROLLED TRIAL

Abstract

Objective: The present study aimed to compare the effects of a deep learning–based digital application, delivered as Digital Physical Therapy (DPT), with those of Conventional Physical Therapy (CPT) on pain intensity, trunk range of motion (ROM), functional movement, preliminary cost‑effectiveness, and perceived transmission risk of COVID‑19 in individuals with low back pain (LBP).

Methods: A total of 100 participants with chronic LBP were randomized into either DPT or CPT groups. Both interventions were delivered three times per week over four weeks. Outcome measures included the Numeric Pain Rating Scale (NPRS), Functional Movement Screen (FMS), AI‑based ROM analysis of trunk flexion, extension, and bilateral side bending, questionnaires assessing perceived COVID‑19 transmission risk, and preliminary cost‑effectiveness analysis. Statistical analyses were conducted using analysis of variance (ANOVA) with significance set at p < 0.05.

Results: Both groups demonstrated significant pre‑ to post‑intervention improvements in pain intensity, trunk mobility, and functional movement (p < 0.05). However, DPT showed superior effects compared with CPT in several domains, including hip extensor strength, Roland‑Morris Disability Questionnaire (RMDQ) scores, and COVID‑19 transmission risk reduction. Cost‑effectiveness analysis revealed that DPT was less costly and more beneficial, with an incremental therapeutic gain of 0.001 QALY relative to CPT.

Conclusions: This study provides novel evidence that DPT is as effective as CPT in improving structural and functional impairments, activity limitations, and participation restrictions among individuals with LBP. Importantly, DPT demonstrated added advantages in reducing perceived infection risk, enhancing accessibility, and improving preliminary cost‑effectiveness