Aims. Machine learning (ML) holds significant promise in optimizing various aspects of total shoulder arthroplasty (TSA), potentially improving patient outcomes and enhancing surgical decision-making. The aim of this systematic review was to identify ML algorithms and evaluate their effectiveness, including those for predicting clinical outcomes and those used in image analysis. Methods. We searched the PubMed, EMBASE, and Cochrane Central Register of Controlled Trials databases for studies applying ML algorithms in TSA. The analysis focused on dataset characteristics, relevant subspecialties, specific ML algorithms used, and their performance outcomes. Results. Following the final screening process, 25 articles satisfied the eligibility criteria for our review. Of these, 60% focused on tabular data while the remaining 40% analyzed image data. Among them, 16 studies were dedicated to developing new models and nine used transfer learning to leverage existing pretrained models. Additionally, three of these models underwent external validation to confirm their reliability and effectiveness. Conclusion. ML algorithms used in TSA demonstrated fair to good performance, as evidenced by the reported metrics. Integrating these models into daily clinical practice could revolutionize TSA, enhancing both surgical precision and patient outcome predictions. Despite their potential, the lack of transparency and generalizability in many current models poses a significant challenge, limiting their clinical utility. Future research should prioritize addressing these limitations to truly propel the field forward and maximize the benefits of ML in enhancing patient care. Cite this article: Bone Jt Open 2025;6(2):126–134

Aims. Metal allergy in knee arthroplasty patients is a controversial topic. We aimed to conduct a scoping review to clarify the management of metal allergy in primary and revision total knee arthroplasty (TKA). Methods. Studies were identified by searching electronic databases: Cochrane Central Register of Controlled Trials, Ovid MEDLINE, and Embase, from their inception to November 2020, for studies evaluating TKA patients with metal hypersensitivity/allergy. All studies reporting on diagnosing or managing metal hypersensitivity in TKA were included. Data were extracted and summarized based on study design, study population, interventions and outcomes. A practical guide is then formulated based on the available evidence. Results. We included 38 heterogeneous studies (two randomized controlled trials, six comparative studies, 19 case series, and 11 case reports). The evidence indicates that metal hypersensitivity is a rare complication with some histopathological features leading to pain and dissatisfaction with no reliable screening tests preoperatively. Hypoallergenic implants are viable alternatives for patients with self-reported/confirmed metal hypersensitivity if declared preoperatively; however, concerns remain over their long-term outcomes with ceramic implants outperforming titanium nitride-coated implants and informed consent is paramount. For patients presenting with painful TKA, metal hypersensitivity is a diagnosis of exclusion where patch skin testing, lymphocyte transformation test, and synovial biopsies are useful adjuncts before revision surgery is undertaken to hypoallergenic implants with shared decision-making and informed consent. Conclusion. Using the limited available evidence in the literature, we provide a practical approach to metal hypersensitivity in TKA patients. Future national/registry-based studies are needed to identify the scale of metal hypersensitivity, agreed diagnostic criteria, and management strategies. Cite this article: Bone Jt Open 2021;2(10):785–795

Aims. This systematic review and meta-analysis was conducted to compare open reduction and internal fixation (ORIF) with primary arthrodesis (PA) in the treatment of Lisfranc injuries, regarding patient-reported outcome measures (PROMs), and risk of secondary surgery. The aim was to conclusively determine the best available treatment based on the most complete and recent evidence available. Methods. A systematic search was conducted in PubMed, Cochrane Controlled Register of Trials (CENTRAL), EMBASE, CINAHL, PEDro, and SPORTDiscus. Additionally, ongoing trial registers and reference lists of included articles were screened. Risk of bias (RoB) and level of evidence were assessed using the Cochrane risk of bias tools and the Grading of Recommendations Assessment, Development and Evaluation (GRADE) tool. The random and fixed-effect models were used for the statistical analysis. Results. A total of 20 studies were selected for this review, of which 12 were comparative studies fit for meta-analysis, including three randomized controlled trials (RCTs). This resulted in a total analyzed population of 392 patients treated with ORIF and 249 patients treated with PA. The mean differences between the two groups in American Orthopedic Foot and Ankle Society (AOFAS), VAS, and SF-36 scores were -7.41 (95% confidence interval (CI) -13.31 to -1.51), 0.77 (95% CI -0.85 to 2.39), and -1.20 (95% CI -3.86 to 1.46), respectively. Conclusion. This is the first study to find a statistically significant difference in PROMs, as measured by the AOFAS score, in favour of PA for the treatment of Lisfranc injuries. However, this difference may not be clinically relevant, and therefore drawing a definitive conclusion requires confirmation by a large prospective high-quality RCT. Such a study should also assess cost-effectiveness, as cost considerations might be decisive in decision-making. Level of Evidence: I. Cite this article: Bone Jt Open 2021;2(10):842–849

Aims

Machine-learning (ML) prediction models in orthopaedic trauma hold great promise in assisting clinicians in various tasks, such as personalized risk stratification. However, an overview of current applications and critical appraisal to peer-reviewed guidelines is lacking. The objectives of this study are to 1) provide an overview of current ML prediction models in orthopaedic trauma; 2) evaluate the completeness of reporting following the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement; and 3) assess the risk of bias following the Prediction model Risk Of Bias Assessment Tool (PROBAST) tool.

Aims

Giant cell tumour of bone (GCTB) treatment changed since the introduction of denosumab from purely surgical towards a multidisciplinary approach, with recent concerns of higher recurrence rates after denosumab. We evaluated oncological, surgical, and functional outcomes for distal radius GCTB, with a critically appraised systematic literature review.

Aims

Recurrent dislocation is both a cause and consequence of glenoid bone loss, and the extent of the bony defect is an indicator guiding operative intervention. Literature suggests that loss greater than 25% requires glenoid reconstruction. Measuring bone loss is controversial; studies use different methods to determine this, with no clear evidence of reproducibility. A systematic review was performed to identify existing CT-based methods of quantifying glenoid bone loss and establish their reliability and reproducibility

Aims

Avulsion of the proximal hamstring tendon origin can result in significant functional impairment, with surgical re-attachment of the tendons becoming an increasingly recognized treatment. The aim of this study was to assess the outcomes of surgical management of proximal hamstring tendon avulsions, and to compare the results between acute and chronic repairs, as well as between partial and complete injuries.

Aims

It is important to understand the rate of complications associated with the increasing burden of revision shoulder arthroplasty. Currently, this has not been well quantified. This review aims to address that deficiency with a focus on complication and reoperation rates, shoulder outcome scores, and comparison of anatomical and reverse prostheses when used in revision surgery.

Aims

To analyze outcomes reported in studies of Ponseti correction of idiopathic clubfoot.