ARTIFICIAL INTELLIGENCE IN MUSCULOSKELETAL RADIOLOGY: A SYSTEMATIC REVIEW OF DIAGNOSTIC ACCURACY AND CLINICAL INTEGRATION
Bibliographic record
Abstract
Background: Artificial intelligence (AI) has rapidly emerged as a transformative tool in musculoskeletal radiology, offering the potential to enhance diagnostic accuracy, reduce radiologist workload, and streamline clinical workflows. Despite numerous studies exploring AI applications across various imaging modalities, there remains limited consensus on their diagnostic reliability and integration into routine clinical practice. This gap highlights the need for a comprehensive evaluation of AI’s effectiveness in musculoskeletal imaging. Objective: This systematic review aims to evaluate the diagnostic performance, clinical benefits, and limitations of AI tools in detecting musculoskeletal conditions through radiographic imaging. Methods: A systematic review was conducted in accordance with PRISMA guidelines. Literature searches were performed in PubMed, Scopus, Web of Science, and the Cochrane Library for studies published between 2018 and 2024. Eligible studies included randomized controlled trials, cohort studies, and cross-sectional designs evaluating AI in musculoskeletal radiology. Inclusion criteria encompassed human studies with comparative diagnostic data. Data were extracted using a standardized form and assessed for bias using the Cochrane Risk of Bias Tool and Newcastle-Ottawa Scale. Due to heterogeneity in study designs and outcomes, a qualitative synthesis was conducted. Results: Eight studies met inclusion criteria, encompassing a range of musculoskeletal conditions such as fractures, osteoarthritis, and skeletal maturity assessment. AI models, primarily deep learning algorithms, consistently demonstrated high diagnostic performance with sensitivity and specificity exceeding 85% and AUC values often above 0.90. Despite strong accuracy, methodological variability and limited external validation were noted across studies. Conclusion: AI tools show strong potential in musculoskeletal radiology, demonstrating diagnostic performance comparable to expert radiologists. However, real-world clinical implementation remains limited by variability in study methods and generalizability. Further large-scale, multicenter studies are necessary to confirm clinical utility and integration strategies.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.012 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".