Aims. An objective technological solution for tracking adherence to at-home shoulder physiotherapy is important for improving patient engagement and rehabilitation outcomes, but remains a significant challenge. The aim of this research was to evaluate performance of machine-learning (ML) methodologies for detecting and classifying inertial data collected during in-clinic and at-home shoulder physiotherapy exercise. Methods. A smartwatch was used to collect inertial data from 42 patients performing shoulder physiotherapy exercises for rotator cuff injuries in both in-clinic and at-home settings. A two-stage ML approach was used to detect out-of-distribution (OOD) data (to remove non-exercise data) and subsequently for classification of exercises. We evaluated the performance impact of grouping exercises by motion type, inclusion of non-exercise data for algorithm training, and a patient-specific approach to exercise classification. Algorithm performance was evaluated using both in-clinic and at-home data. Results. The patient-specific approach with engineered features achieved the highest in-clinic performance for differentiating physiotherapy exercise from non-exercise activity (area under the receiver operating characteristic (AUROC) = 0.924). Including non-exercise data in algorithm training further improved classifier performance (random forest, AUROC = 0.985). The highest accuracy achieved for classifying individual in-clinic exercises was 0.903, using a patient-specific method with deep neural network model extracted features. Grouping exercises by motion type improved exercise classification. For at-home data, OOD detection yielded similar performance with the non-exercise data in the algorithm training (fully convolutional network AUROC = 0.919). Conclusion. Including non-exercise data in algorithm training improves detection of exercises. A patient-specific approach leveraging data from earlier patient-supervised sessions should be considered but is highly dependent on per-patient data quality. Cite this article: Bone Joint Res 2023;12(3):165–177

Aims. To examine whether natural language processing (NLP) using a clinically based large language model (LLM) could be used to predict patient selection for total hip or total knee arthroplasty (THA/TKA) from routinely available free-text radiology reports. Methods. Data pre-processing and analyses were conducted according to the Artificial intelligence to Revolutionize the patient Care pathway in Hip and knEe aRthroplastY (ARCHERY) project protocol. This included use of de-identified Scottish regional clinical data of patients referred for consideration of THA/TKA, held in a secure data environment designed for artificial intelligence (AI) inference. Only preoperative radiology reports were included. NLP algorithms were based on the freely available GatorTron model, a LLM trained on over 82 billion words of de-identified clinical text. Two inference tasks were performed: assessment after model-fine tuning (50 Epochs and three cycles of k-fold cross validation), and external validation. Results. For THA, there were 5,558 patient radiology reports included, of which 4,137 were used for model training and testing, and 1,421 for external validation. Following training, model performance demonstrated average (mean across three folds) accuracy, F1 score, and area under the receiver operating curve (AUROC) values of 0.850 (95% confidence interval (CI) 0.833 to 0.867), 0.813 (95% CI 0.785 to 0.841), and 0.847 (95% CI 0.822 to 0.872), respectively. For TKA, 7,457 patient radiology reports were included, with 3,478 used for model training and testing, and 3,152 for external validation. Performance metrics included accuracy, F1 score, and AUROC values of 0.757 (95% CI 0.702 to 0.811), 0.543 (95% CI 0.479 to 0.607), and 0.717 (95% CI 0.657 to 0.778) respectively. There was a notable deterioration in performance on external validation in both cohorts. Conclusion. The use of routinely available preoperative radiology reports provides promising potential to help screen suitable candidates for THA, but not for TKA. The external validation results demonstrate the importance of further model testing and training when confronted with new clinical cohorts. Cite this article: Bone Joint J 2024;106-B(7):688–695

Aims. Ankle fracture fixation is commonly performed by junior trainees. Simulation training using cadavers may shorten the learning curve and result in a technically superior surgical performance. Methods. We undertook a preliminary, pragmatic, single-blinded, multicentre, randomized controlled trial of cadaveric simulation versus standard training. Primary outcome was fracture reduction on postoperative radiographs. Results. Overall, 139 ankle fractures were fixed by 28 postgraduate year three to five trainee surgeons (mean age 29.4 years; 71% males) during ten months' follow-up. Under the intention-to-treat principle, a technically superior fixation was performed by the cadaveric-trained group compared to the standard-trained group, as measured on the first postoperative radiograph against predefined acceptability thresholds. The cadaveric-trained group used a lower intraoperative dose of radiation than the standard-trained group (mean difference 0.011 Gym. 2. , 95% confidence interval 0.003 to 0.019; p = 0.009). There was no difference in procedure time. Conclusion. Trainees randomized to cadaveric training performed better ankle fracture fixations and irradiated patients less during surgery compared to standard-trained trainees. This effect, which was previously unknown, is likely to be a consequence of the intervention. Further study is required. Cite this article: Bone Jt Open 2023;4(8):594–601

Anterior cruciate ligament (ACL) injuries are among the most common and debilitating knee injuries in professional athletes with an incidence in females up to eight-times higher than their male counterparts. ACL injuries can be career-threatening and are associated with increased risk of developing knee osteoarthritis in future life. The increased risk of ACL injury in females has been attributed to various anatomical, developmental, neuromuscular, and hormonal factors. Anatomical and hormonal factors have been identified and investigated as significant contributors including osseous anatomy, ligament laxity, and hamstring muscular recruitment. Postural stability and impact absorption are associated with the stabilizing effort and stress on the ACL during sport activity, increasing the risk of noncontact pivot injury. Female patients have smaller diameter hamstring autografts than males, which may predispose to increased risk of re-rupture following ACL reconstruction and to an increased risk of chondral and meniscal injuries. The addition of an extra-articular tenodesis can reduce the risk of failure; therefore, it should routinely be considered in young elite athletes. Prevention programs target key aspects of training including plyometrics, strengthening, balance, endurance and stability, and neuromuscular training, reducing the risk of ACL injuries in female athletes by up to 90%. Sex disparities in access to training facilities may also play an important role in the risk of ACL injuries between males and females. Similarly, football boots, pitches quality, and football size and weight should be considered and tailored around females’ characteristics. Finally, high levels of personal and sport-related stress have been shown to increase the risk of ACL injury which may be related to alterations in attention and coordination, together with increased muscular tension, and compromise the return to sport after ACL injury. Further investigations are still necessary to better understand and address the risk factors involved in ACL injuries in female athletes. Cite this article: Bone Jt Open 2024;5(2):94–100

The anterior cruciate ligament (ACL) is frequently injured in elite athletes, with females up to eight times more likely to suffer an ACL tear than males. Biomechanical and hormonal factors have been thoroughly investigated; however, there remain unknown factors that need investigation. The mechanism of injury differs between males and females, and anatomical differences contribute significantly to the increased risk in females. Hormonal factors, both endogenous and exogenous, play a role in ACL laxity and may modify the risk of injury. However, data are still limited, and research involving oral contraceptives is potentially associated with methodological and ethical problems. Such characteristics can also influence the outcome after ACL reconstruction, with higher failure rates in females linked to a smaller diameter of the graft, especially in athletes aged < 21 years. The addition of a lateral extra-articular tenodesis can improve the outcomes after ACL reconstruction and reduce the risk of failure, and it should be routinely considered in young elite athletes. Sex-specific environmental differences can also contribute to the increased risk of injury, with more limited access to and availablility of advanced training facilities for female athletes. In addition, football kits are designed for male players, and increased attention should be focused on improving the quality of pitches, as female leagues usually play the day after male leagues. The kit, including boots, the length of studs, and the footballs themselves, should be tailored to the needs and body shapes of female athletes. Specific physiotherapy programmes and training protocols have yielded remarkable results in reducing the risk of injury, and these should be extended to school-age athletes. Finally, psychological factors should not be overlooked, with females’ greater fear of re-injury and lack of confidence in their knee compromising their return to sport after ACL injury. Both intrinsic and extrinsic factors should be recognized and addressed to optimize the training programmes which are designed to prevent injury, and improve our understanding of these injuries. Cite this article: Bone Joint J 2023;105-B(10):1033–1037

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

Aims. This study aims to assess the feasibility of conducting a pragmatic, multicentre randomized controlled trial (RCT) to test the clinical and cost-effectiveness of an informal caregiver training programme to support the recovery of people following hip fracture surgery. Methods. This will be a mixed-methods feasibility RCT, recruiting 60 patients following hip fracture surgery and their informal caregivers. Patients will be randomized to usual NHS care, versus usual NHS care plus a caregiver-patient dyad training programme (HIP HELPER). This programme will comprise of three, one-hour, one-to-one training sessions for the patient and caregiver, delivered by a nurse, physiotherapist, or occupational therapist. Training will be delivered in the hospital setting pre-patient discharge. It will include practical skills for rehabilitation such as: transfers and walking; recovery goal setting and expectations; pacing and stress management techniques; and introduction to the HIP HELPER Caregiver Workbook, which provides information on recovery, exercises, worksheets, and goal-setting plans to facilitate a ‘good’ recovery. After discharge, patients and caregivers will be supported in delivering rehabilitation through three telephone coaching sessions. Data, collected at baseline and four months post-randomization, will include: screening logs, intervention logs, fidelity checklists, quality assurance monitoring visit data, and clinical outcomes assessing quality of life, physical, emotional, adverse events, and resource use outcomes. The acceptability of the study intervention and RCT design will be explored through qualitative methods with 20 participants (patients and informal caregivers) and 12 health professionals. Discussion. A multicentre recruitment approach will provide greater external validity across population characteristics in England. The mixed-methods approach will permit in-depth examination of the intervention and trial design parameters. The findings will inform whether and how a definitive trial may be undertaken to test the effectiveness of this caregiver intervention for patients after hip fracture surgery. Cite this article: Bone Jt Open 2021;2(11):909–920

Aims. Trained immunity confers non-specific protection against various types of infectious diseases, including bone and joint infection. Platelets are active participants in the immune response to pathogens and foreign substances, but their role in trained immunity remains elusive. Methods. We first trained the innate immune system of C57BL/6 mice via intravenous injection of two toll-like receptor agonists (zymosan and lipopolysaccharide). Two, four, and eight weeks later, we isolated platelets from immunity-trained and control mice, and then assessed whether immunity training altered platelet releasate. To better understand the role of immunity-trained platelets in bone and joint infection development, we transfused platelets from immunity-trained mice into naïve mice, and then challenged the recipient mice with Staphylococcus aureus or Escherichia coli. Results. After immunity training, the levels of pro-inflammatory cytokines (tumour necrosis factor alpha (TNF-α), interleukin (IL)-17A) and chemokines (CCL5, CXCL4, CXCL5, CXCL7, CXCL12) increased significantly in platelet releasate, while the levels of anti-inflammatory cytokines (IL-4, IL-13) decreased. Other platelet-secreted factors (e.g. platelet-derived growth factor (PDGF)-AA, PDGF-AB, PDGF-BB, cathepsin D, serotonin, and histamine) were statistically indistinguishable between the two groups. Transfusion of platelets from trained mice into naïve mice reduced infection risk and bacterial burden after local or systemic challenge with either S. aureus or E. coli. Conclusion. Immunity training altered platelet releasate by increasing the levels of inflammatory cytokines/chemokines and decreasing the levels of anti-inflammatory cytokines. Transfusion of platelets from immunity-trained mice conferred protection against bone and joint infection, suggesting that alteration of platelet releasate might be an important mechanism underlying trained immunity and may have clinical implications. Cite this article: Bone Joint Res 2022;11(2):73–81

Aims. Periacetabular osteotomy (PAO) is widely recognized as a demanding surgical procedure for acetabular reorientation. Reports about the learning curve have primarily focused on complication rates during the initial learning phase. Therefore, our aim was to assess the PAO learning curve from an analytical perspective by determining the number of PAOs required for the duration of surgery to plateau and the accuracy to improve. Methods. The study included 118 consecutive PAOs in 106 patients. Of these, 28 were male (23.7%) and 90 were female (76.3%). The primary endpoint was surgical time. Secondary outcome measures included radiological parameters. Cumulative summation analysis was used to determine changes in surgical duration. A multivariate linear regression model was used to identify independent factors influencing surgical time. Results. The learning curve in this series was 26 PAOs in a period of six months. After 26 PAO procedures, a significant drop in surgical time was observed and a plateau was also achieved. The mean duration of surgery during the learning curve was 103.8 minutes (SD 33.2), and 69.7 minutes (SD 18.6) thereafter (p < 0.001). Radiological correction of acetabular retroversion showed a significant improvement after having performed a total of 93 PAOs, including anteverting PAOs on 35 hips with a retroverted acetabular morphology (p = 0.005). Several factors were identified as independent variables influencing duration of surgery, including patient weight (β = 0.5 (95% confidence interval (CI) 0.2 to 0.7); p < 0.001), learning curve procedure phase of 26 procedures (β = 34.0 (95% CI 24.3 to 43.8); p < 0.001), and the degree of lateral correction expressed as the change in the lateral centre-edge angle (β = 0.7 (95% CI 0.001 to 1.3); p = 0.048). Conclusion. The learning curve for PAO surgery requires extensive surgical training at a high-volume centre, with a minimum of 50 PAOs per surgeon per year. This study defined a cut-off value of 26 PAO procedures, after which a significant drop in surgical duration occurred. Furthermore, it was observed that a retroverted morphology of the acetabulum required a greater number of procedures to acquire proficiency in consistently eliminating the crossover sign. These findings are relevant for fellows and fellowship programme directors in establishing the extent of training required to impart competence in PAO. Cite this article: Bone Joint J 2024;106-B(4):336–343

Aims. The principles of evidence-based medicine (EBM) are the foundation of modern medical practice. Surgeons are familiar with the commonly used statistical techniques to test hypotheses, summarize findings, and provide answers within a specified range of probability. Based on this knowledge, they are able to critically evaluate research before deciding whether or not to adopt the findings into practice. Recently, there has been an increased use of artificial intelligence (AI) to analyze information and derive findings in orthopaedic research. These techniques use a set of statistical tools that are increasingly complex and may be unfamiliar to the orthopaedic surgeon. It is unclear if this shift towards less familiar techniques is widely accepted in the orthopaedic community. This study aimed to provide an exploration of understanding and acceptance of AI use in research among orthopaedic surgeons. Methods. Semi-structured in-depth interviews were carried out on a sample of 12 orthopaedic surgeons. Inductive thematic analysis was used to identify key themes. Results. The four intersecting themes identified were: 1) validity in traditional research, 2) confusion around the definition of AI, 3) an inability to validate AI research, and 4) cautious optimism about AI research. Underpinning these themes is the notion of a validity heuristic that is strongly rooted in traditional research teaching and embedded in medical and surgical training. Conclusion. Research involving AI sometimes challenges the accepted traditional evidence-based framework. This can give rise to confusion among orthopaedic surgeons, who may be unable to confidently validate findings. In our study, the impact of this was mediated by cautious optimism based on an ingrained validity heuristic that orthopaedic surgeons develop through their medical training. Adding to this, the integration of AI into everyday life works to reduce suspicion and aid acceptance. Cite this article: Bone Jt Open 2023;4(9):696–703

The December 2022 Research Roundup. 360. looks at: Halicin is effective against Staphylococcus aureus biofilms in vitro; Synovial fluid and serum neutrophil-to-lymphocyte ratio: useful in septic arthritis?; Transcutaneous oximetry and wound healing; Orthopaedic surgery causes gut microbiome dysbiosis and intestinal barrier dysfunction; Mortality in alcohol-related cirrhosis: a nationwide population-based cohort study; Self-reported resistance training is associated with better bone microarchitecture in vegan people

The April 2023 Children’s orthopaedics Roundup. 360. looks at: Can you treat type IIA supracondylar humerus fractures conservatively?; Bone bruising and anterior cruciate ligament injury in paediatrics; Participation and motor abilities after treatment with the Ponseti method; Does fellowship training help with paediatric supracondylar fractures?; Supracondylar elbow fracture management (Supra Man): a national trainee collaborative evaluation of practice; Magnetically controlled growing rods in early-onset scoliosis; Weightbearing restrictions and weight gain in children with Perthes’ disease?; Injuries and child abuse increase during the pandemic over 12,942 emergency admissions

Aims. The purpose of this survey study was to examine the demographic and lifestyle factors of women currently in orthopaedic surgery. Methods. An electronic survey was conducted of practising female orthopaedic surgeons based in the USA through both the Ruth Jackson Society and the online Facebook group “Women of Orthopaedics”. Results. The majority of surveyed female orthopaedic surgeons reported being married (76.4%; 285/373) and having children (67.6%; 252/373). In all, 66.5% (247/373) were collegiate athletes; 82.0% (306/373) reported having no female orthopaedic surgeon mentors in undergraduate and medical school. Their mean height is 65.8 inches and average weight is 147.3 lbs. Conclusion. The majority of female orthopaedic surgeons did not have female mentorship during their training. Additionally, biometrically, their build is similar to that of the average American woman. Cite this article: Bone Jt Open 2024;5(5):419–425

Aims. The aim of this study was to create artificial intelligence (AI) software with the purpose of providing a second opinion to physicians to support distal radius fracture (DRF) detection, and to compare the accuracy of fracture detection of physicians with and without software support. Methods. The dataset consisted of 26,121 anonymized anterior-posterior (AP) and lateral standard view radiographs of the wrist, with and without DRF. The convolutional neural network (CNN) model was trained to detect the presence of a DRF by comparing the radiographs containing a fracture to the inconspicuous ones. A total of 11 physicians (six surgeons in training and five hand surgeons) assessed 200 pairs of randomly selected digital radiographs of the wrist (AP and lateral) for the presence of a DRF. The same images were first evaluated without, and then with, the support of the CNN model, and the diagnostic accuracy of the two methods was compared. Results. At the time of the study, the CNN model showed an area under the receiver operating curve of 0.97. AI assistance improved the physician’s sensitivity (correct fracture detection) from 80% to 87%, and the specificity (correct fracture exclusion) from 91% to 95%. The overall error rate (combined false positive and false negative) was reduced from 14% without AI to 9% with AI. Conclusion. The use of a CNN model as a second opinion can improve the diagnostic accuracy of DRF detection in the study setting. Cite this article: Bone Joint Res 2024;13(10):588–595