DefinePK

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.