The effectiveness of artificial intelligence-based interventions on treatment outcomes for low back pain: A systematic review and meta-analysis of randomized controlled trials.
Kumaran Ramanujam, Samyr Carneiro, Mohamed Mohsen Helal et al.
✦ AI-curated · Sources linked
In 30 seconds
This systematic review and meta-analysis of randomized controlled trials assessed artificial intelligence-based interventions versus standard interventions for pain and functional outcomes in adults with low back pain. Five studies were included in the review, with four contributing to the meta-analysis. At endpoint, AI-based interventions were associated with lower pain scores (p = 0.001) and lower disability scores (p = 0.02) than controls. Findings for quality of recovery and psychological factors were mixed, with studies reporting either significant improvement or no improvement between groups. The authors conclude that further research is needed to establish clinical relevance.
Key findings
- Five studies met the review criteria; four were included in the meta-analysis.
- AI-based interventions had lower endpoint pain scores than standard interventions (p = 0.001).
- AI-based interventions had lower endpoint disability scores than standard interventions (p = 0.02).
- Quality-of-recovery and psychological outcomes showed mixed findings across studies.
Why it matters
The pooled findings suggest that AI-guided approaches may improve pain and disability outcomes in adults with low back pain compared with standard interventions. However, the small evidence base and mixed results for other outcomes mean the findings do not yet establish how clinically meaningful these differences are or which approaches may be useful in practice.
What to keep in mind
Only five studies were included in the review and four in the meta-analysis; findings for recovery quality and psychological factors were mixed.