Aims. Our aim was to develop and validate nomograms that would predict the cumulative incidence of sarcoma-specific death (CISSD) and disease progression (CIDP) in patients with localized high-grade primary central and dedifferentiated chondrosarcoma. Methods. The study population consisted of 391 patients from two international sarcoma centres (development cohort) who had undergone definitive surgery for a localized high-grade (histological grade II or III) conventional primary central chondrosarcoma or dedifferentiated chondrosarcoma. Disease progression captured the first event of either metastasis or local recurrence. An independent cohort of 221 patients from three additional hospitals was used for external validation. Two nomograms were internally and externally validated for discrimination (c-index) and calibration plot. Results. In the development cohort, the CISSD at ten years was 32.9% (95% confidence interval (CI) 19.8% to 38.4%). Age at diagnosis, grade, and surgical margin were found to have significant effects on CISSD and CIDP in multivariate analyses. Maximum tumour diameter was also significantly associated with CISSD. In the development cohort, the c-indices for CISSD and CIDP at five years were 0.743 (95% CI 0.700 to 0.819) and 0.761 (95% CI 0.713 to 0.800), respectively. When applied to the validation cohort, the c-indices for CISSD and CIDP at five years were 0.839 (95% CI 0.763 to 0.916) and 0.749 (95% CI 0.672 to 0.825), respectively. The calibration plots for these two nomograms demonstrated good fit. Conclusion. Our nomograms performed well on internal and external validation and can be used to predict CISSD and CIDP after resection of localized high-grade conventional primary central and dedifferentiated chondrosarcomas. They provide a new tool with which clinicians can assess and advise individual patients about their prognosis. Cite this article: Bone Joint J 2020;102-B(12):1752–1759

Aims. The number of convolutional neural networks (CNN) available for fracture detection and classification is rapidly increasing. External validation of a CNN on a temporally separate (separated by time) or geographically separate (separated by location) dataset is crucial to assess generalizability of the CNN before application to clinical practice in other institutions. We aimed to answer the following questions: are current CNNs for fracture recognition externally valid?; which methods are applied for external validation (EV)?; and, what are reported performances of the EV sets compared to the internal validation (IV) sets of these CNNs?. Methods. The PubMed and Embase databases were systematically searched from January 2010 to October 2020 according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. The type of EV, characteristics of the external dataset, and diagnostic performance characteristics on the IV and EV datasets were collected and compared. Quality assessment was conducted using a seven-item checklist based on a modified Methodologic Index for NOn-Randomized Studies instrument (MINORS). Results. Out of 1,349 studies, 36 reported development of a CNN for fracture detection and/or classification. Of these, only four (11%) reported a form of EV. One study used temporal EV, one conducted both temporal and geographical EV, and two used geographical EV. When comparing the CNN’s performance on the IV set versus the EV set, the following were found: AUCs of 0.967 (IV) versus 0.975 (EV), 0.976 (IV) versus 0.985 to 0.992 (EV), 0.93 to 0.96 (IV) versus 0.80 to 0.89 (EV), and F1-scores of 0.856 to 0.863 (IV) versus 0.757 to 0.840 (EV). Conclusion. The number of externally validated CNNs in orthopaedic trauma for fracture recognition is still scarce. This greatly limits the potential for transfer of these CNNs from the developing institute to another hospital to achieve similar diagnostic performance. We recommend the use of geographical EV and statements such as the Consolidated Standards of Reporting Trials–Artificial Intelligence (CONSORT-AI), the Standard Protocol Items: Recommendations for Interventional Trials–Artificial Intelligence (SPIRIT-AI) and the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis–Machine Learning (TRIPOD-ML) to critically appraise performance of CNNs and improve methodological rigor, quality of future models, and facilitate eventual implementation in clinical practice. Cite this article: Bone Jt Open 2021;2(10):879–885

Aims. To develop and externally validate a parsimonious statistical prediction model of 90-day mortality after elective total hip arthroplasty (THA), and to provide a web calculator for clinical usage. Methods. We included 53,099 patients with cemented THA due to osteoarthritis from the Swedish Hip Arthroplasty Registry for model derivation and internal validation, as well as 125,428 patients from England and Wales recorded in the National Joint Register for England, Wales, Northern Ireland, the Isle of Man, and the States of Guernsey (NJR) for external model validation. A model was developed using a bootstrap ranking procedure with a least absolute shrinkage and selection operator (LASSO) logistic regression model combined with piecewise linear regression. Discriminative ability was evaluated by the area under the receiver operating characteristic curve (AUC). Calibration belt plots were used to assess model calibration. Results. A main effects model combining age, sex, American Society for Anesthesiologists (ASA) class, the presence of cancer, diseases of the central nervous system, kidney disease, and diagnosed obesity had good discrimination, both internally (AUC = 0.78, 95% confidence interval (CI) 0.75 to 0.81) and externally (AUC = 0.75, 95% CI 0.73 to 0.76). This model was superior to traditional models based on the Charlson (AUC = 0.66, 95% CI 0.62 to 0.70) and Elixhauser (AUC = 0.64, 95% CI 0.59 to 0.68) comorbidity indices. The model was well calibrated for predicted probabilities up to 5%. Conclusion. We developed a parsimonious model that may facilitate individualized risk assessment prior to one of the most common surgical interventions. We have published a web calculator to aid clinical decision-making. Cite this article: Bone Joint J 2021;103-B(3):469–478

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.

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. 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. Methods. A systematic search screening 3,252 studies identified 45 ML-based prediction models in orthopaedic trauma up to January 2023. The TRIPOD statement assessed transparent reporting and the PROBAST tool the risk of bias. Results. A total of 40 studies reported on training and internal validation; four studies performed both development and external validation, and one study performed only external validation. The most commonly reported outcomes were mortality (33%, 15/45) and length of hospital stay (9%, 4/45), and the majority of prediction models were developed in the hip fracture population (60%, 27/45). The overall median completeness for the TRIPOD statement was 62% (interquartile range 30 to 81%). The overall risk of bias in the PROBAST tool was low in 24% (11/45), high in 69% (31/45), and unclear in 7% (3/45) of the studies. High risk of bias was mainly due to analysis domain concerns including small datasets with low number of outcomes, complete-case analysis in case of missing data, and no reporting of performance measures. Conclusion. The results of this study showed that despite a myriad of potential clinically useful applications, a substantial part of ML studies in orthopaedic trauma lack transparent reporting, and are at high risk of bias. These problems must be resolved by following established guidelines to instil confidence in ML models among patients and clinicians. Otherwise, there will remain a sizeable gap between the development of ML prediction models and their clinical application in our day-to-day orthopaedic trauma practice. Cite this article: Bone Jt Open 2024;5(1):9–19

Aims. The aim of this study was to identify factors associated with five-year cancer-related mortality in patients with limb and trunk soft-tissue sarcoma (STS) and develop and validate machine learning algorithms in order to predict five-year cancer-related mortality in these patients. Methods. Demographic, clinicopathological, and treatment variables of limb and trunk STS patients in the Surveillance, Epidemiology, and End Results Program (SEER) database from 2004 to 2017 were analyzed. Multivariable logistic regression was used to determine factors significantly associated with five-year cancer-related mortality. Various machine learning models were developed and compared using area under the curve (AUC), calibration, and decision curve analysis. The model that performed best on the SEER testing data was further assessed to determine the variables most important in its predictive capacity. This model was externally validated using our institutional dataset. Results. A total of 13,646 patients with STS from the SEER database were included, of whom 35.9% experienced five-year cancer-related mortality. The random forest model performed the best overall and identified tumour size as the most important variable when predicting mortality in patients with STS, followed by M stage, histological subtype, age, and surgical excision. Each variable was significant in logistic regression. External validation yielded an AUC of 0.752. Conclusion. This study identified clinically important variables associated with five-year cancer-related mortality in patients with limb and trunk STS, and developed a predictive model that demonstrated good accuracy and predictability. Orthopaedic oncologists may use these findings to further risk-stratify their patients and recommend an optimal course of treatment. Cite this article: Bone Joint J 2023;105-B(6):702–710

Aims. This study aimed to explore the biological and clinical importance of dysregulated key genes in osteoarthritis (OA) patients at the cartilage level to find potential biomarkers and targets for diagnosing and treating OA. Methods. Six sets of gene expression profiles were obtained from the Gene Expression Omnibus database. Differential expression analysis, weighted gene coexpression network analysis (WGCNA), and multiple machine-learning algorithms were used to screen crucial genes in osteoarthritic cartilage, and genome enrichment and functional annotation analyses were used to decipher the related categories of gene function. Single-sample gene set enrichment analysis was performed to analyze immune cell infiltration. Correlation analysis was used to explore the relationship among the hub genes and immune cells, as well as markers related to articular cartilage degradation and bone mineralization. Results. A total of 46 genes were obtained from the intersection of significantly upregulated genes in osteoarthritic cartilage and the key module genes screened by WGCNA. Functional annotation analysis revealed that these genes were closely related to pathological responses associated with OA, such as inflammation and immunity. Four key dysregulated genes (cartilage acidic protein 1 (CRTAC1), iodothyronine deiodinase 2 (DIO2), angiopoietin-related protein 2 (ANGPTL2), and MAGE family member D1 (MAGED1)) were identified after using machine-learning algorithms. These genes had high diagnostic value in both the training cohort and external validation cohort (receiver operating characteristic > 0.8). The upregulated expression of these hub genes in osteoarthritic cartilage signified higher levels of immune infiltration as well as the expression of metalloproteinases and mineralization markers, suggesting harmful biological alterations and indicating that these hub genes play an important role in the pathogenesis of OA. A competing endogenous RNA network was constructed to reveal the underlying post-transcriptional regulatory mechanisms. Conclusion. The current study explores and validates a dysregulated key gene set in osteoarthritic cartilage that is capable of accurately diagnosing OA and characterizing the biological alterations in osteoarthritic cartilage; this may become a promising indicator in clinical decision-making. This study indicates that dysregulated key genes play an important role in the development and progression of OA, and may be potential therapeutic targets. Cite this article: Bone Joint Res 2024;13(2):66–82

Aims. Machine learning (ML), a branch of artificial intelligence that uses algorithms to learn from data and make predictions, offers a pathway towards more personalized and tailored surgical treatments. This approach is particularly relevant to prevalent joint diseases such as osteoarthritis (OA). In contrast to end-stage disease, where joint arthroplasty provides excellent results, early stages of OA currently lack effective therapies to halt or reverse progression. Accurate prediction of OA progression is crucial if timely interventions are to be developed, to enhance patient care and optimize the design of clinical trials. Methods. A systematic review was conducted in accordance with PRISMA guidelines. We searched MEDLINE and Embase on 5 May 2024 for studies utilizing ML to predict OA progression. Titles and abstracts were independently screened, followed by full-text reviews for studies that met the eligibility criteria. Key information was extracted and synthesized for analysis, including types of data (such as clinical, radiological, or biochemical), definitions of OA progression, ML algorithms, validation methods, and outcome measures. Results. Out of 1,160 studies initially identified, 39 were included. Most studies (85%) were published between 2020 and 2024, with 82% using publicly available datasets, primarily the Osteoarthritis Initiative. ML methods were predominantly supervised, with significant variability in the definitions of OA progression: most studies focused on structural changes (59%), while fewer addressed pain progression or both. Deep learning was used in 44% of studies, while automated ML was used in 5%. There was a lack of standardization in evaluation metrics and limited external validation. Interpretability was explored in 54% of studies, primarily using SHapley Additive exPlanations. Conclusion. Our systematic review demonstrates the feasibility of ML models in predicting OA progression, but also uncovers critical limitations that currently restrict their clinical applicability. Future priorities should include diversifying data sources, standardizing outcome measures, enforcing rigorous validation, and integrating more sophisticated algorithms. This paradigm shift from predictive modelling to actionable clinical tools has the potential to transform patient care and disease management in orthopaedic practice. Cite this article: Bone Joint J 2024;106-B(11):1216–1222

Aims. Precise implant positioning, tailored to individual spinopelvic biomechanics and phenotype, is paramount for stability in total hip arthroplasty (THA). Despite a few studies on instability prediction, there is a notable gap in research utilizing artificial intelligence (AI). The objective of our pilot study was to evaluate the feasibility of developing an AI algorithm tailored to individual spinopelvic mechanics and patient phenotype for predicting impingement. Methods. This international, multicentre prospective cohort study across two centres encompassed 157 adults undergoing primary robotic arm-assisted THA. Impingement during specific flexion and extension stances was identified using the virtual range of motion (ROM) tool of the robotic software. The primary AI model, the Light Gradient-Boosting Machine (LGBM), used tabular data to predict impingement presence, direction (flexion or extension), and type. A secondary model integrating tabular data with plain anteroposterior pelvis radiographs was evaluated to assess for any potential enhancement in prediction accuracy. Results. We identified nine predictors from an analysis of baseline spinopelvic characteristics and surgical planning parameters. Using fivefold cross-validation, the LGBM achieved 70.2% impingement prediction accuracy. With impingement data, the LGBM estimated direction with 85% accuracy, while the support vector machine (SVM) determined impingement type with 72.9% accuracy. After integrating imaging data with a multilayer perceptron (tabular) and a convolutional neural network (radiograph), the LGBM’s prediction was 68.1%. Both combined and LGBM-only had similar impingement direction prediction rates (around 84.5%). Conclusion. This study is a pioneering effort in leveraging AI for impingement prediction in THA, utilizing a comprehensive, real-world clinical dataset. Our machine-learning algorithm demonstrated promising accuracy in predicting impingement, its type, and direction. While the addition of imaging data to our deep-learning algorithm did not boost accuracy, the potential for refined annotations, such as landmark markings, offers avenues for future enhancement. Prior to clinical integration, external validation and larger-scale testing of this algorithm are essential. Cite this article: Bone Jt Open 2024;5(8):671–680

Aims. The primary aim of this study was to develop a reliable, effective radiological score to assess the healing of humeral shaft fractures, the Radiographic Union Score for HUmeral fractures (RUSHU). The secondary aim was to assess whether the six-week RUSHU was predictive of nonunion at six months after the injury. Patients and Methods. Initially, 20 patients with radiographs six weeks following a humeral shaft fracture were selected at random from a trauma database and scored by three observers, based on the Radiographic Union Scale for Tibial fractures system. After refinement of the RUSHU criteria, a second group of 60 patients with radiographs six weeks after injury, 40 with fractures that united and 20 with fractures that developed nonunion, were scored by two blinded observers. Results. After refinement, the interobserver intraclass correlation coefficient (ICC) was 0.79 (95% confidence interval (CI) 0.67 to 0.87), indicating substantial agreement. At six weeks after injury, patients whose fractures united had a significantly higher median score than those who developed nonunion (10 vs 7; p < 0.001). A receiver operating characteristic curve determined that a RUSHU cut-off of < 8 was predictive of nonunion (area under the curve = 0.84, 95% CI 0.74 to 0.94). The sensitivity was 75% and specificity 80% with a positive predictive value (PPV) of 65% and a negative predictive value of 86%. Patients with a RUSHU < 8 (n = 23) were more likely to develop nonunion than those with a RUSHU ≥ 8 (n = 37, odds ratio 12.0, 95% CI 3.4 to 42.9). Based on a PPV of 65%, if all patients with a RUSHU < 8 underwent fixation, the number of procedures needed to avoid one nonunion would be 1.5. Conclusion. The RUSHU is reliable and effective in identifying patients at risk of nonunion of a humeral shaft fracture at six weeks after injury. This tool requires external validation but could potentially reduce the morbidity associated with delayed treatment of an established nonunion. Cite this article: Bone Joint J 2019;101-B:1300–1306

Despite the vast quantities of published artificial intelligence (AI) algorithms that target trauma and orthopaedic applications, very few progress to inform clinical practice. One key reason for this is the lack of a clear pathway from development to deployment. In order to assist with this process, we have developed the Clinical Practice Integration of Artificial Intelligence (CPI-AI) framework – a five-stage approach to the clinical practice adoption of AI in the setting of trauma and orthopaedics, based on the IDEAL principles (https://www.ideal-collaboration.net/). Adherence to the framework would provide a robust evidence-based mechanism for developing trust in AI applications, where the underlying algorithms are unlikely to be fully understood by clinical teams.

Cite this article: Bone Joint Res 2024;13(9):507–512.

Aims

This study aimed to develop and validate a fully automated system that quantifies proximal femoral bone mineral density (BMD) from CT images.

Objectives. To define Patient Acceptable Symptom State (PASS) thresholds for the Oxford hip score (OHS) and Oxford knee score (OKS) at mid-term follow-up. Methods. In a prospective multicentre cohort study, OHS and OKS were collected at a mean follow-up of three years (1.5 to 6.0), combined with a numeric rating scale (NRS) for satisfaction and an external validation question assessing the patient’s willingness to undergo surgery again. A total of 550 patients underwent total hip replacement (THR) and 367 underwent total knee replacement (TKR). Results. Receiver operating characteristic (ROC) curves identified a PASS threshold of 42 for the OHS after THR and 37 for the OKS after TKR. THR patients with an OHS ≥ 42 and TKR patients with an OKS ≥ 37 had a higher NRS for satisfaction and a greater likelihood of being willing to undergo surgery again. Conclusions. PASS thresholds appear larger at mid-term follow-up than at six months after surgery. With- out external validation, we would advise against using these PASS thresholds as absolute thresholds in defining whether or not a patient has attained an acceptable symptom state after THR or TKR. Cite this article: Bone Joint Res 2014;3:7–13

Aims

To develop prediction models using machine-learning (ML) algorithms for 90-day and one-year mortality prediction in femoral neck fracture (FNF) patients aged 50 years or older based on the Hip fracture Evaluation with Alternatives of Total Hip arthroplasty versus Hemiarthroplasty (HEALTH) and Fixation using Alternative Implants for the Treatment of Hip fractures (FAITH) trials.

Literature surrounding artificial intelligence (AI)-related applications for hip and knee arthroplasty has proliferated. However, meaningful advances that fundamentally transform the practice and delivery of joint arthroplasty are yet to be realized, despite the broad range of applications as we continue to search for meaningful and appropriate use of AI. AI literature in hip and knee arthroplasty between 2018 and 2021 regarding image-based analyses, value-based care, remote patient monitoring, and augmented reality was reviewed. Concerns surrounding meaningful use and appropriate methodological approaches of AI in joint arthroplasty research are summarized. Of the 233 AI-related orthopaedics articles published, 178 (76%) constituted original research, while the rest consisted of editorials or reviews. A total of 52% of original AI-related research concerns hip and knee arthroplasty (n = 92), and a narrative review is described. Three studies were externally validated. Pitfalls surrounding present-day research include conflating vernacular (“AI/machine learning”), repackaging limited registry data, prematurely releasing internally validated prediction models, appraising model architecture instead of inputted data, withholding code, and evaluating studies using antiquated regression-based guidelines. While AI has been applied to a variety of hip and knee arthroplasty applications with limited clinical impact, the future remains promising if the question is meaningful, the methodology is rigorous and transparent, the data are rich, and the model is externally validated. Simple checkpoints for meaningful AI adoption include ensuring applications focus on: administrative support over clinical evaluation and management; necessity of the advanced model; and the novelty of the question being answered.

Cite this article: Bone Joint J 2022;104-B(12):1292–1303.

Aims

To determine the major risk factors for unplanned reoperations (UROs) following corrective surgery for adult spinal deformity (ASD) and their interactions, using machine learning-based prediction algorithms and game theory.

Prediction tools are instruments which are commonly used to estimate the prognosis in oncology and facilitate clinical decision-making in a more personalized manner. Their popularity is shown by the increasing numbers of prediction tools, which have been described in the medical literature. Many of these tools have been shown to be useful in the field of soft-tissue sarcoma of the extremities (eSTS). In this annotation, we aim to provide an overview of the available prediction tools for eSTS, provide an approach for clinicians to evaluate the performance and usefulness of the available tools for their own patients, and discuss their possible applications in the management of patients with an eSTS.

Cite this article: Bone Joint J 2022;104-B(9):1011–1016.

The October 2023 Hip & Pelvis Roundup³⁶⁰ looks at: Femoroacetabular impingement syndrome at ten years – how do athletes do?; Venous thromboembolism in patients following total joint replacement: are transfusions to blame?; What changes in pelvic sagittal tilt occur 20 years after total hip arthroplasty?; Can stratified care in hip arthroscopy predict successful and unsuccessful outcomes?; Hip replacement into your nineties; Can large language models help with follow-up?; The most taxing of revisions – proximal femoral replacement for periprosthetic joint infection – what’s the benefit of dual mobility?

Aims

The risk factors for recurrent instability (RI) following a primary traumatic anterior shoulder dislocation (PTASD) remain unclear. In this study, we aimed to determine the rate of RI in a large cohort of patients managed nonoperatively after PTASD and to develop a clinical prediction model.