Clinical translation of artificial intelligence in musculoskeletal care: a systematic review of current applications, evidence gaps, and implementation readiness
Journal of Orthopaedic Surgery and Research · 30 Jul 2026
† Impact is the editorial-priority score. All scores are out of 100. Clinical is a stored clinical-importance score from the earlier method; it has not been recalculated.
Why it matters
Orthopaedic surgeons increasingly encounter AI-assisted imaging tools, and this review shows the evidence supporting their clinical use remains extremely thin despite hype.
The evidence
This systematic review searched for studies validating AI tools for musculoskeletal imaging between 2022 and 2025, screening 1,245 records down to 123 full-text papers. Using strict criteria for quantitative clinical validation, only three studies qualified, and all three were limited to MRI-based segmentation and biomarker extraction, with no studies validating AI on other imaging modalities or in multi-centre, real-world settings.
A coherent primary effect estimate is unavailable. Clinical relevance does not estimate treatment benefit.
Why this rigour score?
Meta-analysis (mixed designs)
Methods at a glance
Recorded assessment- Comprehensive literature searchNot reported
- Risk of bias assessedNot reported
- Bias considered in synthesisNot reported
- Publication bias assessedNot reported
- Study exclusions justifiedNot reported
- Prospective registrationNot met
Not reported does not mean not done. Checks have different weights; this is not a count of boxes ticked.
How to read this assessment
The recorded methods are shown alongside the published score. A verified point-by-point calculation is not available for this version of the appraisal.
Checklist from the stored appraisal. “Not met” describes the recorded criterion; it does not always produce a deduction. This overview supports reading the full study.
For journal club
1.If only a handful of MRI-based AI segmentation tools have any rigorous validation, how should orthopaedic surgeons weigh AI-generated imaging reports when they appear in a patient's chart today?
2.What patient-centred outcomes (pain, function, reoperation) should be required before an AI diagnostic tool is trusted for surgical decision-making in MSK care?
Original publication title
Clinical translation of artificial intelligence in musculoskeletal care: a systematic review of current applications, evidence gaps, and implementation readiness