Search papers, labs, and topics across Lattice.
This scoping review analyzed 183 systematic reviews and meta-analyses published between 2015 and 2025 to map the landscape of artificial intelligence (AI) applications in orthopaedics, revealing exponential growth in publications, particularly in fracture, arthroplasty, and surgery-related studies focused on the spine, knee, and hip. Deep learning was predominantly applied to imaging datasets, while machine learning was more common in structured clinical data applications, with notable gaps in underrepresented anatomical regions and prescriptive modelling. The methodological quality of included reviews was appraised using AMSTAR-2.
AI applications in orthopaedics are rapidly expanding, but this review identifies key gaps in anatomical regions and applications like prescriptive modelling, highlighting opportunities for targeted research to better align AI with clinical needs.
BackgroundArtificial intelligence (AI) has rapidly gained momentum in the field of orthopaedics, with an increasing number of systematic reviews and meta-analyses providing synthesised evidence. However, most studies have focused on individual subspecialties or specific applications, and a comprehensive overview across the discipline is lacking.AimThe aim of this study is to chart publication trends and geographical distribution, classify clinical and anatomical focus, and map AI methodologies and applications in orthopaedic settings, thereby highlighting research opportunities in underexplored areas.MethodsWe conducted a scoping review of freely accessible systematic reviews with and without meta-analysis across PubMed, Web of Science and Scopus databases from year 2015 up to July 2025 that evaluated the use of AI in orthopaedics. Data were extracted on publication characteristics, geographical origin, orthopaedic subspecialty focus, anatomical region, AI methodologies, data modalities, and application types. The methodological quality of the included reviews was appraised using the A Measurement Tool to Assess Systematic Reviews-2 (AMSTAR-2). Descriptive trends were summarised, and associations between variables were analysed using R software.ResultsWe identified 183 eligible systematic reviews published in the last 10 years, with an exponential increase in publications over the past 5 years. Most reviews concentrated on fractures, arthroplasty, and surgery-related studies, particularly in the spine, knee, and hip. Imaging datasets predominated, with deep learning most frequently applied to radiological tasks, while machine learning methods were more common in structured clinical data applications. Notable gaps remain in underrepresented anatomical regions and in underexplored applications such as prescriptive modelling.ConclusionOur review highlights that while there is rapid growth in AI research across orthopaedics, certain clinical domains remain underexplored. These gaps represent opportunities for future work to align AI methods with clinical needs. By addressing these areas, AI has the potential to effectively support orthopaedic care and improve patient outcomes.
