Related Experiment Video
Updated: Jul 16, 2026
06:28
Biomechanical Changes Related to Low Back Pain: An Innovative Tool for Movement Pattern Assessment and Treatment Evaluation in Rehabilitation
Published on: December 13, 2024
Artificial Intelligence-Based Physical Therapy Interventions for Non-Specific Low Back Pain: A Systematic Review and
Faizan Kashoo1, Shagun Agarwal2, Naif Ziyad Alrashdi1,3
1Department of Physical Therapy and Health Rehabilitation, College of Applied Medical Sciences, Majmaah University, Al Majmaah 11952, Saudi Arabia.
Journal of Clinical Medicine
|July 15, 2026
Summary
Artificial intelligence (AI) in physical therapy (PT) offers statistically significant pain and disability relief for non-specific low back pain (NSLBP). However, these improvements are clinically small, necessitating further research for definitive conclusions.
Area of Science:
- Rehabilitation Medicine
- Digital Health
- Biomedical Engineering
Background:
- Non-specific low back pain (NSLBP) is a global health issue, causing significant disability.
- Artificial intelligence (AI) is emerging in healthcare, with potential applications in NSLBP management.
- The efficacy of AI-driven physical therapy (PT) for NSLBP requires rigorous evaluation.
Purpose of the Study:
- To systematically review and meta-analyze randomized controlled trials (RCTs) on AI-based PT interventions for NSLBP.
- To assess the impact of AI-based PT on pain intensity and disability.
- To determine if improvements meet minimal clinically important differences.
Main Methods:
- A systematic literature search was performed across six electronic databases.
- Included studies were RCTs comparing AI-based interventions against usual care or other interventions for NSLBP.
- Data were pooled using random-effects models to calculate mean differences (MD) and 95% confidence intervals (CIs).
Main Results:
- Five RCTs (1939 participants) were included in the systematic review.
- Meta-analysis of three RCTs (594 participants) showed significant reductions in pain (MD -0.721) and disability (MD -1.031).
- Neither outcome reached minimal clinically important difference thresholds; evidence certainty was low due to bias and imprecision.
Conclusions:
- AI-based PT interventions demonstrate statistically significant but clinically minor benefits for NSLBP.
- Current evidence suggests AI-based PT is safe, with no serious adverse events reported.
- Larger, high-quality, blinded RCTs with standardized outcomes are essential to confirm efficacy and clinical utility.