Aims. As an increasing number of female surgeons are choosing orthopaedics, it is important to recognize the impact of pregnancy within this cohort. The aim of this review was to examine common themes and data surrounding pregnancy, parenthood, and fertility within orthopaedics. Methods. A systematic review was conducted by searching Medline, Emcare, Embase, PsycINFO, OrthoSearch, and the Cochrane Library in November 2022. The Preferred Reporting Items for Systematic Reviews and Meta Analysis were adhered to. Original research papers that focused on pregnancy and/or parenthood within orthopaedic surgery were included for review. Results. Of 1,205 papers, 19 met the inclusion criteria. Our results found that orthopaedic surgeons have higher reported rates of obstetric complications, congenital abnormalities, and infertility compared to the general population. They were noted to have children at a later age and voluntarily delayed childbearing. Negative perceptions of pregnancy from fellow trainees and programme directors were identified. Conclusion. Female orthopaedic surgeons have high rates of obstetric complications and infertility. Negative perceptions surrounding pregnancy can lead to orthopaedic surgeons voluntarily delaying childbearing. There is a need for a pregnancy-positive culture shift combined with formalized guidelines and female mentorship to create a more supportive environment for pregnancy within orthopaedic surgery. Cite this article: Bone Joint J 2023;105-B(8):857–863

Aims. Large bone defects resulting from osteolysis, fractures, osteomyelitis, or metastases pose significant challenges in acetabular reconstruction for total hip arthroplasty. This study aimed to evaluate the survival and radiological outcomes of an acetabular reconstruction technique in patients at high risk of reconstruction failure (i.e. periprosthetic joint infection (PJI), poor bone stock, immunosuppressed patients), referred to as Hip Reconstruction In Situ with Screws and Cement (HiRISC). This involves a polyethylene liner embedded in cement-filled bone defects reinforced with screws and/or plates for enhanced fixation. Methods. A retrospective chart review of 59 consecutive acetabular reconstructions was performed by four surgeons in a single institution from 18 October 2018 to 5 January 2023. Cases were classified based on the Paprosky classification, excluding type 1 cases (n = 26) and including types 2 or 3 for analysis (n = 33). Radiological loosening was evaluated by an orthopaedic surgeon who was not the operating surgeon, by comparing the immediate postoperative radiographs with the ones at latest follow-up. Mean follow-up was 557 days (SD 441; 31 to 1,707). Results. Out of the 33 cases analyzed, six (18.2%) constructs required revision, with four revisions due to uncontrolled infection, one for dislocation, and one for aseptic loosening. Among the 27 non-revised constructs, only one showed wider radiolucencies compared to immediate postoperative radiographs, indicating potential loosening. Patients who underwent revision (n = 6) were significantly younger and had a higher BMI compared to those with non-revised constructs (p = 0.016 and p = 0.026, respectively). Sex, race, ethnicity, American Society of Anesthesiologists grade, infection status (patients with postoperative PJI diagnosis (septic) vs patients without such diagnosis (aseptic)), and mean follow-up did not significantly differ between revised and non-revised groups. Conclusion. The HiRISC technique may serve as a feasible short-term (about one to two years) alternative in patients with large acetabular defects, particularly in cases of PJI. Longer follow-up is necessary to establish the long-term survival of this technique. Cite this article: Bone Joint J 2024;106-B(5 Supple B):82–88

In order to assess current opinions on the long-term outcome after primary total hip replacement, we performed a multicentre, cross-sectional survey in 22 centres from 12 European countries. Different patient characteristics were categorised into ‘decreases chances’, ‘does not affect chances’, and ‘increases chances’ of a favourable long-term outcome, by 304 orthopaedic surgeons and 314 referring practitioners. The latter were less likely to associate age older than 80 years and obesity with a favourable outcome than orthopaedic surgeons (p < 0.001 and p = 0.006, respectively) and more likely to associate age younger than 50 years with a favourable outcome (p = 0.006). Comorbidity, rheumatoid arthritis, and poor bone quality were thought to be associated with a decreased chance of a favourable outcome. We found important differences in the opinions regarding long-term outcome after total hip replacement within and between referring practitioners and orthopaedic surgeons. These are likely to affect access to and the provision of total hip replacement

We have developed a teaching programme for non-radiologists who use fluoroscopy, which includes techniques for reducing the radiation received by the patient and the surgeon during orthopaedic procedures. The techniques resolve around the radiation protection concepts of time, distance and shielding. The programme has been very successful in reducing the total fluoroscopy times of orthopaedic surgeons; in our institute, durations have been reduced to about 10% of those before the training started. We review the aims and content of our programme

Aims

To investigate the extent of bone development around the scaffold of custom triflange acetabular components (CTACs) over time.

Aims. High-quality clinical research in children’s orthopaedic surgery has lagged behind other surgical subspecialties. This study used a consensus-based approach to identify research priorities for clinical trials in children’s orthopaedics. Methods. A modified Delphi technique was used, which involved an initial scoping survey, a two-round Delphi process and an expert panel formed of members of the British Society of Children’s Orthopaedic Surgery. The survey was conducted amongst orthopaedic surgeons treating children in the United Kingdom and Ireland. Results. A total of 86 clinicians contributed to both rounds of the Delphi process, scoring priorities from one (low priority) to five (high priority). Elective topics were ranked higher than those relating to trauma, with the top ten elective research questions scoring higher than the top question for trauma. Ten elective, and five trauma research priorities were identified, with the three highest ranked questions relating to the treatment of slipped capital femoral epiphysis (mean score 4.6/ 5), Perthes’ disease (4.5) and bone infection (4.5). Conclusion. This consensus-based research agenda will guide surgeons, academics and funders to improve the evidence in children’s orthopaedic surgery and encourage the development of multicentre clinical trials. Cite this article: Bone Joint J 2018;100-B:680–4

This paper offers a summary of the ethical guide for the European orthopaedic community; the full report will be published in the EFORT Journal.

Cite this article: Bone Joint J 2014;96-B:1130–2.

Aims

The aim of this study was to assess the current evidence relating to the benefits of virtual reality (VR) simulation in orthopaedic surgical training, and to identify areas of future research.

The aim of this study was to investigate the effect of training on the arthroscopic performance of a group of medical students and to determine whether all students could be trained to competence. Thirty-three medical students with no previous experience of arthroscopy were randomised to a ‘Trained’ or an ‘Untrained’ cohort. They were required to carry out 30 episodes of two simulated arthroscopic tasks (one shoulder and one knee). The primary outcome variable was task success at each episode. Individuals achieved competence when their learning curve stabilised. The secondary outcome was technical dexterity, assessed objectively using a validated motion analysis system. Six subjects in the ‘Untrained’ cohort failed to achieve competence in the shoulder task, compared with one in the ‘Trained’ cohort. During the knee task, two subjects in each cohort failed to achieve competence. Based on the objective motion analysis parameters, the ‘Trained’ cohort performed better on the shoulder task (p < 0.05) but there was no significant difference for the knee task (p > 0.05).

Although specific training improved the arthroscopic performance of novices, there were individuals who could not achieve competence despite focused training.These findings may have an impact on the selection process for trainees and influence individual career choices.

Despite increasing scientific investigation, the best method for preventing post-operative deep-vein thrombosis remains unclear. In the wake of the publication of the Pulmonary Embolism Prevention trial and the Scottish Intercollegiate Guidelines Network (SIGN) on the prevention of thromboembolism, we felt that it was timely to survey current thromboprophylactic practices. Questionnaires were sent to all consultants on the register of the British Orthopaedic Association. The rate of response was 62%. The survey showed a dramatic change in practice towards the use of chemoprophylaxis since the review by Morris and Mitchell in 1976. We found that there was a greater uniformity of opinion and prescribing practices in Scotland, consistent with the SIGN guidelines, than in the rest of the UK. We argue in favour of the use of such documents which are based on a qualitative review of current scientific literature.

Aims. This study evaluated the effect of treating clinician speciality on management of zone 2 fifth metatarsal fractures. Methods. This was a retrospective cohort study of patients with acute zone 2 fifth metatarsal fractures who presented to a single large, urban, academic medical centre between December 2012 and April 2022. Zone 2 was the region of the fifth metatarsal base bordered by the fourth and fifth metatarsal articulation on the oblique radiograph. The proportion of patients allowed to bear weight as tolerated immediately after injury was compared between patients treated by orthopaedic surgeons and podiatrists. The effects of unrestricted weightbearing and foot and/or ankle immobilization on clinical healing were assessed. A total of 487 patients with zone 2 fractures were included (mean age 53.5 years (SD 16.9), mean BMI 27.2 kg/m. 2. (SD 6.0)) with a mean follow-up duration of 2.57 years (SD 2.64). Results. Overall, 281 patients (57.7%) were treated by orthopaedic surgeons, and 206 patients (42.3%) by podiatrists. When controlling for age, sex, and time between symptom onset and presentation, the likelihood of undergoing operative treatment was significantly greater when treated by a podiatrist (odds ratio (OR) 2.9 (95% CI 1.2 to 8.2); p = 0.029). A greater proportion of patients treated by orthopaedic surgeons were allowed to immediately bear weight on the injured foot (70.9% (178/251) vs 47.3% (71/150); p < 0.001). Patients treated by podiatrists were immobilized for significantly longer (mean 8.4 weeks (SD 5.7) vs 6.8 weeks (SD 4.3); p = 0.002) and experienced a significantly longer mean time to clinical healing (12.1 (SD 10.6) vs 9.0 weeks (SD 7.3), p = 0.003). Conclusion. Although there was considerable heterogeneity among zone 2 fracture management, orthopaedic surgeons were less likely to treat patients operatively and more likely to allow early full weightbearing compared to podiatrists. Cite this article: Bone Joint J 2024;106-B(9):942–948

Aims. The aim of this study was to determine the consensus best practice approach for the investigation and management of children (aged 0 to 15 years) in the UK with musculoskeletal infection (including septic arthritis, osteomyelitis, pyomyositis, tenosynovitis, fasciitis, and discitis). This consensus can then be used to ensure consistent, safe care for children in UK hospitals and those elsewhere with similar healthcare systems. Methods. A Delphi approach was used to determine consensus in three core aspects of care: 1) assessment, investigation, and diagnosis; 2) treatment; and 3) service, pathways, and networks. A steering group of paediatric orthopaedic surgeons created statements which were then evaluated through a two-round Delphi survey sent to all members of the British Society for Children’s Orthopaedic Surgery (BSCOS). Statements were only included (‘consensus in’) in the final agreed consensus if at least 75% of respondents scored the statement as critical for inclusion. Statements were discarded (‘consensus out’) if at least 75% of respondents scored them as not important for inclusion. Reporting these results followed the Appraisal Guidelines for Research and Evaluation. Results. A total of 133 children’s orthopaedic surgeons completed the first survey, and 109 the second. Out of 43 proposed statements included in the initial Delphi, 32 reached ‘consensus in’, 0 ‘consensus out’, and 11 ‘no consensus’. These 11 statements were then reworded, amalgamated, or deleted before the second Delphi round of eight statements. All eight were accepted as ‘consensus in’, resulting in a total of 40 approved statements. Conclusion. In the many aspects of medicine where relevant evidence is not available for clinicians to base their practice, a Delphi consensus can provide a strong body of opinion that acts as a benchmark for good quality clinical care. We would recommend clinicians managing children with musculoskeletal infection follow the guidance in the consensus statements in this article, to ensure care in all medical settings is consistent and safe. Cite this article: Bone Joint J 2023;105-B(7):815–820

Aims. This study evaluated variation in the surgical treatment of stable (A1) and unstable (A2) trochanteric hip fractures among an international group of orthopaedic surgeons, and determined the influence of patient, fracture, and surgeon characteristics on choice of implant (intramedullary nailing (IMN) versus sliding hip screw (SHS)). Methods. A total of 128 orthopaedic surgeons in the Science of Variation Group evaluated radiographs of 30 patients with Type A1 and A2 trochanteric hip fractures and indicated their preferred treatment: IMN or SHS. The management of Type A3 (reverse obliquity) trochanteric fractures was not evaluated. Agreement between surgeons was calculated using multirater kappa. Multivariate logistic regression models were used to assess whether patient, fracture, and surgeon characteristics were independently associated with choice of implant. Results. The overall agreement between surgeons on implant choice was fair (kappa = 0.27 (95% confidence interval (CI) 0.25 to 0.28)). Factors associated with preference for IMN included USA compared to Europe or the UK (Europe odds ratio (OR) 0.56 (95% CI 0.47 to 0.67); UK OR 0.16 (95% CI 0.12 to 0.22); p < 0.001); exposure to IMN only during training compared to surgeons that were exposed to both (only IMN during training OR 2.6 (95% CI 2.0 to 3.4); p < 0.001); and A2 compared to A1 fractures (Type A2 OR 10 (95% CI 8.4 to 12); p < 0.001). Conclusion. In an international cohort of orthopaedic surgeons, there was a large variation in implant preference for patients with A1 and A2 trochanteric fractures. This is due to surgeon bias (country of practice and aspects of training). The observation that surgeons favoured the more expensive implant (IMN) in the absence of convincing evidence of its superiority suggests that surgeon de-biasing strategies may be a useful focus for optimizing patient outcomes and promoting value-based healthcare. Cite this article: Bone Joint J 2021;103-B(4):775–781

Aims. The aim of this study was to characterize the influence of social deprivation on the rate of complications, readmissions, and revisions following primary total shoulder arthroplasty (TSA), using the Social Deprivation Index (SDI). The SDI is a composite measurement, in percentages, of seven demographic characteristics: living in poverty, with < 12 years of education, single-parent households, living in rented or overcrowded housing, households without a car, and unemployed adults aged < 65 years. Methods. Patients aged ≥ 40 years, who underwent primary TSA between 2011 and 2017, were identified using International Classification of Diseases (ICD)-9 Clinical Modification and ICD-10 procedure codes for TSA in the New York Statewide Planning and Research Cooperative System database. Readmission, reoperation, and other complications were analyzed using multivariable Cox proportional hazards regression controlling for SDI, age, ethnicity, insurance status, and Charlson Comorbidity Index. Results. A total of 17,698 patients with a mean age of 69 years (SD 9.6), of whom 57.7% were female, underwent TSA during this time and 4,020 (22.7%) had at least one complication. A total of 8,113 patients (45.8%) had at least one comorbidity, and the median SDI in those who developed complications 12 months postoperatively was significantly greater than in those without a complication (33 vs 38; p < 0.001). Patients from areas with higher deprivation had increased one-, three-, and 12-month rates of readmission, dislocation, humeral fracture, urinary tract infection, deep vein thrombosis, and wound complications, as well as a higher three-month rate of pulmonary embolism (all p < 0.05). Conclusion. Beyond medical complications, we found that patients with increased social deprivation had higher rates of humeral fracture and dislocation following primary TSA. The large sample size of this study, and the outcomes that were measured, add to the literature greatly in comparison with other large database studies involving TSA. These findings allow orthopaedic surgeons practising in under-served or low-volume areas to identify patients who may be at greater risk of developing complications. Cite this article: Bone Joint J 2024;106-B(2):174–181

Aims. The purpose of this study was to develop a convolutional neural network (CNN) for fracture detection, classification, and identification of greater tuberosity displacement ≥ 1 cm, neck-shaft angle (NSA) ≤ 100°, shaft translation, and articular fracture involvement, on plain radiographs. Methods. The CNN was trained and tested on radiographs sourced from 11 hospitals in Australia and externally validated on radiographs from the Netherlands. Each radiograph was paired with corresponding CT scans to serve as the reference standard based on dual independent evaluation by trained researchers and attending orthopaedic surgeons. Presence of a fracture, classification (non- to minimally displaced; two-part, multipart, and glenohumeral dislocation), and four characteristics were determined on 2D and 3D CT scans and subsequently allocated to each series of radiographs. Fracture characteristics included greater tuberosity displacement ≥ 1 cm, NSA ≤ 100°, shaft translation (0% to < 75%, 75% to 95%, > 95%), and the extent of articular involvement (0% to < 15%, 15% to 35%, or > 35%). Results. For detection and classification, the algorithm was trained on 1,709 radiographs (n = 803), tested on 567 radiographs (n = 244), and subsequently externally validated on 535 radiographs (n = 227). For characterization, healthy shoulders and glenohumeral dislocation were excluded. The overall accuracy for fracture detection was 94% (area under the receiver operating characteristic curve (AUC) = 0.98) and for classification 78% (AUC 0.68 to 0.93). Accuracy to detect greater tuberosity fracture displacement ≥ 1 cm was 35.0% (AUC 0.57). The CNN did not recognize NSAs ≤ 100° (AUC 0.42), nor fractures with ≥ 75% shaft translation (AUC 0.51 to 0.53), or with ≥ 15% articular involvement (AUC 0.48 to 0.49). For all objectives, the model’s performance on the external dataset showed similar accuracy levels. Conclusion. CNNs proficiently rule out proximal humerus fractures on plain radiographs. Despite rigorous training methodology based on CT imaging with multi-rater consensus to serve as the reference standard, artificial intelligence-driven classification is insufficient for clinical implementation. The CNN exhibited poor diagnostic ability to detect greater tuberosity displacement ≥ 1 cm and failed to identify NSAs ≤ 100°, shaft translations, or articular fractures. Cite this article: Bone Joint J 2024;106-B(11):1348–1360

Aims. This study aimed to compare the performance of survival prediction models for bone metastases of the extremities (BM-E) with pathological fractures in an Asian cohort, and investigate patient characteristics associated with survival. Methods. This retrospective cohort study included 469 patients, who underwent surgery for BM-E between January 2009 and March 2022 at a tertiary hospital in South Korea. Postoperative survival was calculated using the PATHFx3.0, SPRING13, OPTIModel, SORG, and IOR models. Model performance was assessed with area under the curve (AUC), calibration curve, Brier score, and decision curve analysis. Cox regression analyses were performed to evaluate the factors contributing to survival. Results. The SORG model demonstrated the highest discriminatory accuracy with AUC (0.80 (95% confidence interval (CI) 0.76 to 0.85)) at 12 months. In calibration analysis, the PATHfx3.0 and OPTIModel models underestimated survival, while the SPRING13 and IOR models overestimated survival. The SORG model exhibited excellent calibration with intercepts of 0.10 (95% CI -0.13 to 0.33) at 12 months. The SORG model also had lower Brier scores than the null score at three and 12 months, indicating good overall performance. Decision curve analysis showed that all five survival prediction models provided greater net benefit than the default strategy of operating on either all or no patients. Rapid growth cancer and low serum albumin levels were associated with three-, six-, and 12-month survival. Conclusion. State-of-art survival prediction models for BM-E (PATHFx3.0, SPRING13, OPTIModel, SORG, and IOR models) are useful clinical tools for orthopaedic surgeons in the decision-making process for the treatment in Asian patients, with SORG models offering the best predictive performance. Rapid growth cancer and serum albumin level are independent, statistically significant factors contributing to survival following surgery of BM-E. Further refinement of survival prediction models will bring about informed and patient-specific treatment of BM-E. Cite this article: Bone Joint J 2024;106-B(2):203–211

Aims. This study aimed to evaluate the relationship between hip shape and mid-term function in Perthes’ disease. It also explored whether the modified three-group Stulberg classification can offer similar prognostic information to the five-group system. Methods. A total of 136 individuals aged 12 years or older who had Perthes’ disease in childhood completed the Patient-Reported Outcomes Measurement Information System (PROMIS) Mobility score (function), Nonarthritic Hip Score (NAHS) (function), EuroQol five-dimension five-level questionnaire (EQ-5D-5L) score (quality of life), and the numeric rating scale for pain (NRS). The Stulberg class of the participants’ hip radiographs were evaluated by three fellowship-trained paediatric orthopaedic surgeons. Hip shape and Stulberg class were compared to PROM scores. Results. A spherical hip was associated with the highest function and quality of life, and lowest pain. Conversely, aspherical hips exhibited the lowest functional scores and highest pain. The association between worsening Stulberg class (i.e. greater deviation from sphericity) and worse outcome persisted after adjustment for age and sex in relation to PROMIS (predicted mean difference -1.77 (95% confidence interval (CI) -2.70 to -0.83)), NAHS (-5.68 (95% CI -8.45 to -2.90)), and NRS (0.61 (95% CI 0.14 to 1.08)), but not EQ-5D-5L (-0.03 (95% CI -0.72 to 0.11)). Conclusion. Patient-reported outcomes identify lower function, quality of life, and higher pain in aspherical hips. The magnitude of symptoms deteriorated with time. Hip sphericity (i.e. the modified three-group classification of spherical, oval, and aspherical) appeared to offer similar levels of detail to the five-group Stulberg classification. Cite this article: Bone Joint J 2023;105-B(6):711–716

Orthopaedic surgeons are currently faced with an overwhelming number of choices surrounding total knee arthroplasty (TKA), not only with the latest technologies and prostheses, but also fundamental decisions on alignment philosophies. From ‘mechanical’ to ‘adjusted mechanical’ to ‘restricted kinematic’ to ‘unrestricted kinematic’ — and how constitutional alignment relates to these — there is potential for ambiguity when thinking about and discussing such concepts. This annotation summarizes the various alignment strategies currently employed in TKA. It provides a clear framework and consistent language that will assist surgeons to compare confidently and contrast the concepts, while also discussing the latest opinions about alignment in TKA. Finally, it provides suggestions for applying consistent nomenclature to future research, especially as we explore the implications of 3D alignment patterns on patient outcomes. Cite this article: Bone Joint J 2023;105-B(2):102–108

Paediatric bone sarcomas are a dual challenge for orthopaedic surgeons in terms of tumour resection and reconstruction, as it is important to minimize functional and growth problems without compromising survival rates. Cañadell’s technique consists of a Type I epiphysiolysis performed using continuous distraction by an external fixator prior to resection. It was designed to achieve a safe margin due to the ability of the physeal cartilage to be a barrier to tumour spread in some situations, avoiding the need for articular reconstruction, and preserving the growth capacity most of the times. Despite initial doubts raised in the scientific community, this technique is now widely used in many countries for the treatment of metaphyseal paediatric bone sarcomas. This annotation highlights the importance of Cañadell’s work and reviews the experience of applying it to bone sarcoma patients over the last 40 years. Cite this article: Bone Joint J 2023;105-B(1):11–16

Aims. The Open-Fracture Patient Evaluation Nationwide (OPEN) study was performed to provide clarity in open fracture management previously skewed by small, specialist centre studies and large, unfocused registry investigations. We report the current management metrics of open fractures across the UK. Method. Patients admitted to hospital with an open fracture (excluding phalanges or isolated hand injuries) between 1 June 2021 and 30 September 2021 were included. Institutional information governance approval was obtained at the lead site and all data entered using Research Electronic Data Capture software. All domains of the British Orthopaedic Association Standard for Open Fracture Management were recorded. Results. Across 51 centres, 1,175 patients were analyzed. Antibiotics were given to 754 (69.0%) in the emergency department, 240 (22.0%) pre-hospital, and 99 (9.1%) as inpatients. Wounds were photographed in 848 (72.7%) cases. Median time to first surgery was 16 hrs 14 mins (interquartile range (IQR) 8 hrs 29 mins to 23 hrs 19 mins). Complex injuries were operated on sooner (median 12 hrs 51 mins (IQR 4 hrs 36 mins to 21 hrs 14 mins)). Of initial procedures, 1,053 (90.3%) occurred between 8am and 8pm. A consultant orthopaedic surgeon was present at 1,039 (89.2%) first procedures. In orthoplastic centres, a consultant plastic surgeon was present at 465 (45.1%) first procedures. Overall, 706 (60.8%) patients required a single operation. At primary debridement, 798 (65.0%) fractures were definitively fixed, while 734 (59.8%) fractures had fixation and coverage in one operation through direct closure or soft-tissue coverage. Negative pressure wound therapy was used in 235 (67.7%) staged procedures. Following wound closure or soft-tissue cover, 509 (47.0%) patients received antibiotics for a median of three days (IQR 1 to 7). Conclusion. OPEN provides an insight into care across the UK and different levels of hospital for open fractures. Patients are predominantly operated on promptly, in working hours, and at specialist centres. Areas for improvement include combined patient review and follow-up, scheduled operating, earlier definitive soft-tissue cover, and more robust antibiotic husbandry. Cite this article: Bone Joint J 2022;104-B(9):1073–1080

Aims. Total hip arthroplasty (THA) and total knee arthroplasty (TKA) are common orthopaedic procedures requiring postoperative radiographs to confirm implant positioning and identify complications. Artificial intelligence (AI)-based image analysis has the potential to automate this postoperative surveillance. The aim of this study was to prepare a scoping review to investigate how AI is being used in the analysis of radiographs following THA and TKA, and how accurate these tools are. Methods. The Embase, MEDLINE, and PubMed libraries were systematically searched to identify relevant articles. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for scoping reviews and Arksey and O’Malley framework were followed. Study quality was assessed using a modified Methodological Index for Non-Randomized Studies tool. AI performance was reported using either the area under the curve (AUC) or accuracy. Results. Of the 455 studies identified, only 12 were suitable for inclusion. Nine reported implant identification and three described predicting risk of implant failure. Of the 12, three studies compared AI performance with orthopaedic surgeons. AI-based implant identification achieved AUC 0.992 to 1, and most algorithms reported an accuracy > 90%, using 550 to 320,000 training radiographs. AI prediction of dislocation risk post-THA, determined after five-year follow-up, was satisfactory (AUC 76.67; 8,500 training radiographs). Diagnosis of hip implant loosening was good (accuracy 88.3%; 420 training radiographs) and measurement of postoperative acetabular angles was comparable to humans (mean absolute difference 1.35° to 1.39°). However, 11 of the 12 studies had several methodological limitations introducing a high risk of bias. None of the studies were externally validated. Conclusion. These studies show that AI is promising. While it already has the ability to analyze images with significant precision, there is currently insufficient high-level evidence to support its widespread clinical use. Further research to design robust studies that follow standard reporting guidelines should be encouraged to develop AI models that could be easily translated into real-world conditions. Cite this article: Bone Joint J 2022;104-B(8):929–937