Femoroacetabular Impingement (FAI) syndrome, characterised by abnormal hip contact causing symptoms and osteoarthritis, is measured using the International Hip Outcome Tool (iHOT). This study uses machine learning to predict patient outcomes post-treatment for FAI, focusing on achieving a minimally clinically important difference (MCID) at 52 weeks. A retrospective analysis of 6133 patients from the NAHR who underwent hip arthroscopic treatment for FAI between November 2013 and March 2022 was conducted. MCID was defined as half a standard deviation (13.61) from the mean change in iHOT score at 12 months. SKLearn Maximum Absolute Scaler and Logistic Regression were applied to predict achieving MCID, using baseline and 6-month follow-up data. The model's performance was evaluated by accuracy, area under the curve, and recall, using pre-operative and up to 6-month postoperative variables. A total of 23.1% (1422) of patients completed both baseline and 1-year follow-up iHOT surveys. The best results were obtained using both pre and postoperative variables. The machine learning model achieved 88.1% balanced accuracy, 89.6% recall, and 92.3% AUC. Sensitivity was 83.7% and specificity 93.5%. Key variables determining outcomes included MCID achievement at 6 months, baseline iHOT score, 6-month iHOT scores for pain, and difficulty in walking or using stairs. The study confirmed the utility of machine learning in predicting long-term outcomes following arthroscopic treatment for FAI. MCID, based on the iHOT 12 tools, indicates meaningful clinical changes. Machine learning demonstrated high accuracy and recall in distinguishing between patients achieving MCID and those who did not. This approach could help early identification of patients at risk of not meeting the MCID threshold one year after treatment

Arthroplasties are widely performed to improve mobility and quality of life for symptomatic knee/hip osteoarthritis patients. With increasing rates of Total Joint Replacements in the United Kingdom, predicting length of stay is vital for hospitals to control costs, manage resources, and prevent postoperative complications. A longer Length of stay has been shown to negatively affect the quality of care, outcomes and patient satisfaction. Thus, predicting LOS enables us to make full use of medical resources. Clinical characteristics were retrospectively collected from 1,303 patients who received TKA and THR. A total of 21 variables were included, to develop predictive models for LOS by multiple machine learning (ML) algorithms, including Random Forest Classifier (RFC), K-Nearest Neighbour (KNN), Extreme Gradient Boost (XgBoost), and Na¯ve Bayes (NB). These models were evaluated by the receiver operating characteristic (ROC) curve for predictive performance. A feature selection approach was used to identify optimal predictive factors. Based on the ROC of Training result, XgBoost algorithm was selected to be applied to the Test set. The areas under the ROC curve (AUCs) of the 4 models ranged from 0.730 to 0.966, where higher AUC values generally indicate better predictive performance. All the ML-based models performed better than conventional statistical methods in ROC curves. The XgBoost algorithm with 21 variables was identified as the best predictive model. The feature selection indicated the top six predictors: Age, Operation Duration, Primary Procedure, BMI, creatinine and Month of Surgery. By analysing clinical characteristics, it is feasible to develop ML-based models for the preoperative prediction of LOS for patients who received TKA and THR, and the XgBoost algorithm performed the best, in terms of accuracy of predictive performance. As this model was originally crafted at Ashford and St. Peters Hospital, we have naturally named it as THE ASHFORD OUTCOME

Aims. Failure of irrigation and debridement (I&D) for prosthetic joint infection (PJI) is influenced by numerous host, surgical, and pathogen-related factors. We aimed to develop and validate a practical, easy-to-use tool based on machine learning that may accurately predict outcome following I&D surgery taking into account the influence of numerous factors. Methods. This was an international, multicentre retrospective study of 1,174 revision total hip (THA) and knee arthroplasties (TKA) undergoing I&D for PJI between January 2005 and December 2017. PJI was defined using the Musculoskeletal Infection Society (MSIS) criteria. A total of 52 variables including demographics, comorbidities, and clinical and laboratory findings were evaluated using random forest machine learning analysis. The algorithm was then verified through cross-validation. Results. Of the 1,174 patients that were included in the study, 405 patients (34.5%) failed treatment. Using random forest analysis, an algorithm that provides the probability for failure for each specific patient was created. By order of importance, the ten most important variables associated with failure of I&D were serum CRP levels, positive blood cultures, indication for index arthroplasty other than osteoarthritis, not exchanging the modular components, use of immunosuppressive medication, late acute (haematogenous) infections, methicillin-resistant Staphylococcus aureus infection, overlying skin infection, polymicrobial infection, and older age. The algorithm had good discriminatory capability (area under the curve = 0.74). Cross-validation showed similar probabilities comparing predicted and observed failures indicating high accuracy of the model. Conclusion. This is the first study in the orthopaedic literature to use machine learning as a tool for predicting outcomes following I&D surgery. The developed algorithm provides the medical profession with a tool that can be employed in clinical decision-making and improve patient care. Future studies should aid in further validating this tool on additional cohorts. Cite this article: Bone Joint J 2020;102-B(7 Supple B):11–19

Identification of patients at risk of not achieving minimally clinically important differences (MCID) in patient reported outcome measures (PROMs) is important to ensure principled and informed pre-operative decision making. Machine learning techniques may enable the generation of a predictive model for attainment of MCID in hip arthroscopy. Aims: 1) to determine whether machine learning techniques could predict which patients will achieve MCID in the iHOT-12 PROM 6 months after arthroscopic management of femoroacetabular impingement (FAI), 2) to determine which factors contribute to their predictive power. Data from the UK Non-Arthroplasty Hip Registry database was utilised. We identified 1917 patients who had undergone hip arthroscopy for FAI with both baseline and 6 month follow up iHOT-12 and baseline EQ-5D scores. We trained three established machine learning algorithms on our dataset to predict an outcome of iHOT-12 MCID improvement at 6 months given baseline characteristics including demographic factors, disease characteristics and PROMs. Performance was assessed using area under the receiver operating characteristic (AUROC) statistics with 5-fold cross validation. The three machine learning algorithms showed quite different performance. The linear logistic regression model achieved AUROC = 0.59, the deep neural network achieved AUROC = 0.82, while a random forest model had the best predictive performance with AUROC 0.87. Of demographic factors, we found that BMI and age were key predictors for this model. We also found that removing all features except baseline responses to the iHOT-12 questionnaire had little effect on performance for the random forest model (AUROC = 0.85). Disease characteristics had little effect on model performance. Machine learning models are able to predict with good accuracy 6-month post-operative MCID attainment in patients undergoing arthroscopic management for FAI. Baseline scores from the iHOT-12 questionnaire are sufficient to predict with good accuracy whether a patient is likely to reach MCID in post-operative PROMs

Introduction. Instability remains a common complication following total hip arthroplasty (THA) and continues to account for the highest percentage of revisions in numerous registries. Many risk factors have been described, yet a patient-specific risk assessment tool remains elusive. The purpose of this study was to apply a machine learning algorithm to develop a patient-specific risk score capable of dynamic adjustment based on operative decisions. Methods. 22,086 THA performed between 1998–2018 were evaluated. 632 THA sustained a postoperative dislocation (2.9%). Patients were robustly characterized based on non-modifiable factors: demographics, THA indication, spinal disease, spine surgery, neurologic disease, connective tissue disease; and modifiable operative decisions: surgical approach, femoral head size, acetabular liner (standard/elevated/constrained/dual-mobility). Models were built with a binary outcome (event/no event) at 1-year and 5-year postoperatively. Inverse Probability Censoring Weighting accounted for censoring bias. An ensemble algorithm was created that included Generalized Linear Model, Generalized Additive Model, Lasso Penalized Regression, Kernel-Based Support Vector Machines, Random Forest and Optimized Gradient Boosting Machine. Convex combination of weights minimized the negative binomial log-likelihood loss function. Ten-fold cross-validation accounted for the rarity of dislocation events. Results. The 1-year model achieved an area under the curve (AUC)=0.63, sensitivity=70%, specificity=50%, positive predictive value (PPV)=3% and negative predictive value (NPV)=99%. The 5-year model achieved an AUC=0.62, sensitivity=69%, specificity=51%, PPV=7% and NPV=97%. All cohort-level accuracy metrics performed better than chance. The two most influential predictors in the model were surgical approach and acetabular liner. Conclusions. This machine learning algorithm demonstrates high sensitivity and NPV, suggesting screening tool utility. The model is strengthened by a multivariable dataset portending differential dislocation risk. Two modifiable variables (approach and acetabular liner) were the most influential in dislocation risk. Calculator utilization in “app” form could enable individualized risk prognostication. Furthermore, algorithm development through machine learning facilitates perpetual model performance enhancement with future data input

Periacetabular Osteotomy (PAO) has become the most important surgical procedure for patients with hip dysplasia, offering significant pain relief and improved joint function. This study focuses on recovery after PAO, specifically the return to sports (RTS) timeline, with the objective of identifying preoperative predictors to optimize patient outcomes. Our prospective, monocentric study from 2019 to 2023 included 698 hips from 606 patients undergoing PAO. Comprehensive preoperative data were collected, including demographic information, clinical assessments (Modified Harris Hip Score (mHHS), International Hip Outcome Tool-12 (iHot-12), Hip Disability and Osteoarthritis Outcome Score (HOOS), UCLA Activity Score) and psychological evaluations (Brief Symptom Inventory (BSI) and SF-36 Health Survey). Advanced logistic regression and machine learning techniques (R Core Team. (2016)) were employed to develop a predictive model. Multivariate regression analysis revealed that several preoperative factors significantly influenced the RTS timeline. These included gender, invasiveness of the surgical approach, preoperative UCLA Score, preoperative sports activity level, mHHS, and various HOOS subscales (Sport/Recreation, Symptoms, Pain) as well as psychological factors (BSI and SF-36). The subsequent model, using a decision tree approach, showed that the combination of a UCLA score greater than 3 (p<0.001), non-female gender (p=0.003), preoperative sports frequency not less than twice per week (p<0.001), participation in high-impact sports preoperatively (p=0.008), and a BSI anxiety score less than 2 (p<0.001) had the highest likelihood of early RTS with a probability of 71.4% at three months. Using a decision tree approach, this model provides a nuanced prediction of RTS after PAO, highlighting the synergy of physical, psychological, and lifestyle influences. By quantifying the impact of these variables, it provides clinicians with a valuable tool for predicting individual patient recovery trajectories, aiding in tailored rehabilitation planning and predicting postoperative satisfaction

Background. Postoperative recovery after routine total hip arthroplasty (THA) can lead to the development of prolonged opioid use but there are few tools for predicting this adverse outcome. The purpose of this study was to develop machine learning algorithms for preoperative prediction of prolonged post-operative opioid use after THA. Methods. A retrospective review of electronic health records was conducted at two academic medical centers and three community hospitals to identify adult patients who underwent THA for osteoarthritis between January 1. st. , 2000 and August 1. st. , 2018. Prolonged postoperative opioid prescriptions were defined as continuous opioid prescriptions after surgery to at least 90 days after surgery. Five machine learning algorithms were developed to predict this outcome and were assessed by discrimination, calibration, and decision curve analysis. Results. Overall, 5507 patients underwent THA, of which 345 (6.3%) had prolonged postoperative opioid prescriptions. The factors determined for prediction of prolonged postoperative opioid prescriptions were: age, duration of pre-operative opioid exposure, preoperative hemoglobin, and certain preoperative medications (anti-depressants, benzodiazepines, non-steroidal anti-inflammatory drugs, and beta-2-agonists). The elastic-net penalized logistic regression model achieved the best performance across discrimination (c-statistic = 0.77), calibration, and decision curve analysis. This model was incorporated into a digital application able to provide both predictions and explanations; available here: . https://sorg-apps.shinyapps.io/thaopioid/. Conclusion. If externally validated in independent populations, the algorithms developed in this study could improve preoperative screening and support for THA patients at high-risk for prolonged postoperative opioid use. Early identification and intervention in high-risk cases may mitigate the long-term adverse consequence of opioid dependence. For any tables or figures, please contact the authors directly

Over 8000 total hip arthroplasties (THA) in the UK were revised in 2019, half for aseptic loosening. It is believed that Artificial Intelligence (AI) could identify or predict failing THA and result in early recognition of poorly performing implants and reduce patient suffering. The aim of this study is to investigate whether Artificial Intelligence based machine learning (ML) / Deep Learning (DL) techniques can train an algorithm to identify and/or predict failing uncemented THA. Consent was sought from patients followed up in a single design, uncemented THA implant surveillance study (2010–2021). Oxford hip scores and radiographs were collected at yearly intervals. Radiographs were analysed by 3 observers for presence of markers of implant loosening/failure: periprosthetic lucency, cortical hypertrophy, and pedestal formation. DL using the RGB ResNet 18 model, with images entered chronologically, was trained according to revision status and radiographic features. Data augmentation and cross validation were used to increase the available training data, reduce bias, and improve verification of results. 184 patients consented to inclusion. 6 (3.2%) patients were revised for aseptic loosening. 2097 radiographs were analysed: 21 (11.4%) patients had three radiographic features of failure. 166 patients were used for ML algorithm testing of 3 scenarios to detect those who were revised. 1) The use of revision as an end point was associated with increased variability in accuracy. The area under the curve (AUC) was 23–97%. 2) Using 2/3 radiographic features associated with failure was associated with improved results, AUC: 75–100%. 3) Using 3/3 radiographic features, had less variability, reduced AUC of 73%, but 5/6 patients who had been revised were identified (total 66 identified). The best algorithm identified the greatest number of revised hips (5/6), predicting failure 2–8 years before revision, before all radiographic features were visible and before a significant fall in the Oxford Hip score. True-Positive: 0.77, False Positive: 0.29. ML algorithms can identify failing THA before visible features on radiographs or before PROM scores deteriorate. This is an important finding that could identify failing THA early

Cobalt chrome alloy is commonly used in joint replacement surgery. However, it is recognised that some patients develop lymphocyte mediated delayed type hypersensitivity (DTH) responses to this material, which may result in extensive bone and soft tissue destruction. Phase 1. United Kingdom: From an existing database, we identified extreme phenotype patient groups following metal on metal (MoM) hip resurfacing or THR: ALVAL with low wearing prostheses; ALVAL with high wear; no ALVAL with high wear; and asymptomatic patients with implants in situ for longer than ten years. Class I and II HLA genotype frequency distributions were compared between these patients’ groups, and in silico peptide binding studies were carried out using validated methodology. Phase 2. United Kingdom: We expanded the study to include more patients, including those with intermediary phenotypes to test whether an algorithm could be developed incorporating “risk genotypes”, patient age, sex and metal exposure. This model was trained in phase 3. Phase 3. United Kingdom, Australia, United States. Patients from other centres were invited to give DNA samples. The data set was split in two. 70% was used to develop machine learning models to predict failure secondary to DTH. The predictions were tested using the remaining blinded 30% of data, using time-dependent AUROCs, and integrated calibration index performance statistics. A total of 606 DNA samples, from 397 males and 209 female patients, were typed. This included 176 from patients with failed prostheses, and 430 from asymptomatic patients at a mean of >10 years follow up. C-index and ROC(t) scores suggested a high degree of discrimination, whilst the IBS indicated good calibration and further backed up the indication of high discriminatory ability. At ten years, the weighted mean survival probability error was < 4%. At present, there are no tests in widespread clinical use which use a patient's genetic profile to guide implant selection or inform post-operative management. The algorithm described herein may address this issue and we suggest that the application may not be restricted to the field of MoM hip arthroplasty

A total hip replacement (THR) patient's spinopelvic mobility might predispose them to an increased risk of impingement, instability and edge-loading. This risk can be minimised by considering their preoperative movement during planning of component alignment. However, the question of whether the preoperative, arthritic motion is representative of the postoperative mobility has been raised. We aimed to determine the change in functional pelvic tilt in a series of THR patients at one-year. Four-hundred and eleven patients had their pelvic tilt and lumbar lordotic angle (LLA) measured in the standing and flexed-seated (position when patients initiate rising from a seat) positions as part of routine planning for THR. All measurements were performed on lateral radiographs. At 12-months postoperatively, the same two lateral images were taken and pelvic tilt measured. Pearson correlation was used to investigate the linear relationship between pre-and post-op pelvic tilt. Furthermore, a predictive model of post-op pelvic tilt was developed using machine learning algorithms. The model incorporating four preoperative inputs – standing pelvic tilt, seated pelvic tilt, standing LLA and seated LLA. In the standing position, there was a mean 2° posterior rotation after THR, with a maximum posterior change of 13°. The Pearson correlation coefficient between pre-and post-op standing pelvic tilt was 0.84. This prediction of post-op standing tilt improved to 0.91 when the three further inputs were incorporated to the predictive model. In the flexed-seated position, there was a mean 7° anterior rotation after THR, with a maximum anterior change of 45°. The Pearson correlation coefficient between pre-and post-op seated pelvic tilt was 0.54. This prediction of post-op seated tilt improved to 0.71 when the three further inputs were incorporated to the predictive model. The best predictor of post-operative spinopelvic mobility, is the patients pre-operative spinopelvic mobility, and this should routinely be measured when planning THR. The predictive model will continue to improve in accuracy as more data and more variables (contralateral hip pathology, pelvic incidence, age and gender) are incorporated into the model

Introduction. Custom flanged acetabular components (CFAC) have been shown to be effective in treating complex acetabular reconstructions in revision total hip arthroplasty (THA). However, the specific patient factors and CFAC design characteristics that affect the overall survivorship remain unclear. Once the surgeon opts to follow this treatment pathway, numerous decisions need to be made during the pre-operative design phase and during implantation, which may influence the ultimate success of CFAC. The goal of this study was to retrospectively review the entire cohort of CFAC cases performed at a large volume institution and to identify any patient, surgeon, or design factors that may be related to the long-term survival of these prostheses. Methods. We reviewed 96 CFAC cases performed in 91 patients between 2004 and 2017, from which 36 variables were collected spanning patient demographics, pre-operative clinical and radiographic features, intraoperative information, and implant design characteristics. Patient demographics and relevant clinical features were collected from individual medical records. Radiographic review included analysis of pre-operative radiographs, computer tomographic (CT) scans, and serial post-operative radiographs. Radiographic failure was defined as loosening or gross migration as determined by a board-certified orthopedic surgeon. CFAC implant design characteristics and intra-operative features were collected from the design record, surgical record and post-operative radiograph for each case respectively. Two sets of statistical analyses were performed with this dataset. First, univariate analyses were performed for each variable, comprising of a Pearson chi-square test for categorical variables and an independent t-test for continuous variables. Second, a random forest supervised machine learning method was applied to identify the most influential variables within the dataset, which were then used to perform a bivariable logistic regression to generate odds ratios. Statistical significance for this study was set at p < 0.05. Results. Radiographic failures occurred in 22/96 (23%) of cases with 12/96 (13%) undergoing re-revision (time to revision: Mean 25.1 months; Range: 3 – 84, SD 26.5). No relationship between radiographic failure and the preoperative Paprosky grade or the presence of a discontinuity was observed. The rate of radiographic failure (loosening and/or migration) was inversely associated with age, with increased failure seen in patients who were younger at the time of surgery; (mean age: 54.4±13.0 v. 64.8±11.4 years; p=0.007). Patients whose initial diagnosis was not osteoarthritis were more likely to fail than those with primary OA (OR: 3.79, p=0.0173) and were younger at the time of surgery (p=0.013). The presence of ischial screws from previous surgery (28%) was also an independent risk factor for failure (OR: 3.11, p=0.021). Random forest analysis identified the age at index procedure and the location of the inferior-most ischial screw as the most sensitive predictors of radiographic failure. As patient age at the time of surgery increased, there was subsequent a decreased rate of failure (OR: 0.93 odds ratio per year, p =0.005). When the bottom-most ischial screw was within the top half of the obturator foramen, it was 4 times more likely to fail than when this screw was located at the bottom half of the obturator foramen (OR = 3.98, p=0.046) (p < 0.05). Discussion and Conclusion. This study was able to identify the patient and design variables predictive of survival of CFAC prostheses used in complex revision THA. Younger patients (<55years) are at increased risk for failure either due to a more active lifestyle or because they have a non-OA primary diagnosis that predisposes them to earlier THA. Compromised ischial bone stock or inadequate ischial fixation both had a significant impact on CFAC implant survivorship as both the presence of pre-CFAC ischial screw fixation and lack of inferior ischial fixation correlated with increased rate of failure. These findings highlight the importance of rigid ischial fixation sufficient to resist the high pull-out forces generated during activities of daily living

Aims

This study was designed to develop a model for predicting bone mineral density (BMD) loss of the femur after total hip arthroplasty (THA) using artificial intelligence (AI), and to identify factors that influence the prediction. Additionally, we virtually examined the efficacy of administration of bisphosphonate for cases with severe BMD loss based on the predictive model.

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.

Aims

Cemented hemiarthroplasty is an effective form of treatment for most patients with an intracapsular fracture of the hip. However, it remains unclear whether there are subgroups of patients who may benefit from the alternative operation of a modern uncemented hemiarthroplasty – the aim of this study was to investigate this issue. Knowledge about the heterogeneity of treatment effects is important for surgeons in order to target operations towards specific subgroups who would benefit the most.

The unparalleled events of the year 2020 continue to evolve and challenge the worldwide community on a daily basis. The COVID-19 pandemic has had a major impact on all aspects of our lives, and has caused major morbidity and mortality around the globe. The impact of COVID-19 on the practice of orthopedic surgery has been substantial with practice shutdowns, elective surgery restrictions, heightened utilization of telemedicine platforms and implementation of precautionary measures for in-person clinic visits. During this transition period the scholarly and educational pursuits of academic surgeons have been de-emphasized as the more immediate demands of clinical practice survivorship have been the priority. This unavoidable focus on clinical practice has heightened the importance of orthopedic subspecialty societies in maintaining an appropriate level of attention on research and educational activities. Under the outstanding presidential leadership of Robert Barrack, MD, The Hip Society adapted to the profound challenges of 2020, and maintained strong leadership in the realms of education and research. The recent 2020 summer meeting of the Hip Society was a testimonial to the resilience and dedication of the Society members to ongoing innovation in research and education. Due to travel and social distancing restrictions the 2020 summer meeting was transitioned from an in-person to a virtual meeting format. Dr Barrack and Program Chair Dr John Clohisy assisted with oversight of the meeting, while Olga Foley and Cynthia Garcia ensured the success of the meeting with remarkable planning and organization. These collaborative efforts resulted in an organized, well-attended, high level scientific meeting with engaging discussion and a remarkable virtual conference environment. The Bone & Joint Journal is very pleased to partner with The Hip Society to publish the proceedings of this very unique virtual meeting. The Hip Society is based in the United States and membership is granted to select individuals for leadership accomplishments in education and research related to hip disease. The Society is focused on the mission of advancing the knowledge and treatment of hip disorders to improve the lives of patients. The vision of the Hip Society is to lead in the discovery and dissemination of knowledge related to disorders of the hip. The annual closed meeting is one of the most important events of the society as this gathering highlights timely, controversial and novel research contributions from the membership. The top research papers from The Hip Society meeting will be published and made available to the wider orthopedic community in The Bone & Joint Journal. This partnership with The Bone & Joint Journal enhances the mission and vision of The Hip Society by international dissemination of the meeting proceedings. Given the far-reaching circulation of The Bone & Joint Journal the highest quality work is available to an expanding body of surgeons, associated healthcare providers and patients. Ultimately, this facilitates the overarching Hip Society goal of improving the lives of our patients. The 2020 virtual Hip Society meeting was characterized by outstanding member attendance, high quality paper presentations and robust discussion sessions. The meeting was held over two days and encompassed 58 open paper presentations divided into ten sessions with moderated discussions after each session. All papers will be presented in this issue in abstract form, while selected full papers passing our rigorous peer review process will be available online and in The Bone & Joint Journal in a dedicated supplement in 2021. The first session of the meeting focused on issues related to complex primary THA and osteonecrosis of the femoral head. Dr Gross presented on the conversion of hip fusion to THA in 28 patents at a mean 7 years. He reported a high clinical success rate, yet complications of heterotopic ossification and neurologic injury were relatively common. Consideration of heterotopic ossification prophylaxis and the selective use of a constrained liner were recommended. Dr Pagnano summarized the use of various contemporary porous acetabular components in 38 hips in the setting of prior pelvic radiation. The mean follow-up was 5 years and 10 year survivorship was 100% with all implants radiographically fixed. Dr Bolognesi's study demonstrated that THA in solid organ transplant patients is associated with higher risk for facility placement, transfusions and readmissions. This patient population also has increased mortality risk (4.3% risk at 1 year) especially lung transplant patients. The second group of papers focused on femoral head osteonecrosis. Dr Iorio presented single center data demonstrating that CT scan was a useful adjunct for diagnosis in the staging work-up for cancer, yet was not useful for ARCO staging and treatment decision-making. On the basic science side, Dr Goodman utilized a rabbit model of steroid-induced femoral head osteonecrosis to determine that immunomodulation with IL-4 has the potential to improve bone healing after core decompression. The session was concluded by Dr Nelson's study of ceramic-on-ceramic THA in 108 osteonecrosis patients. The median 12 year results were outstanding with marked increases in PROs, maintenance of high activity levels, and a 3.7% revision rate. In the second session attention was directed to THA instability and spinopelvic mobility. Dr Sierra presented a machine learning algorithm for THA dislocation risk. Two modifiable variables (anterior/lateral approach, elevated liner) were most influential in minimizing dislocation risk. Dr Taunton's study demonstrated a deep learning artificial intelligence model derived from postoperative radiographs to predict THA dislocation risk. High sensitivity and negative predictive value suggest that this model may be helpful in assessing postoperative dislocation risk. In reviewing a large single-center, multiple surgeon cohort of 2,831 DAA procedures, Dr Moskal noted a very low dislocation rate (0.45%) at minimum 2 years. Importantly, spinopelvic pathology or prior spinal instrumentation was not associated with an increased dislocation risk (0.30%). Dr Huo and colleagues analyzed pelvic tilt during functional gait in patients with acetabular dysplasia. They detected variable pelvic tilt on different surfaces with the data suggesting that patients with more anterior pelvic tilt while standing tend to have greater compensatory posterior pelvic tilt during gait. Dr Lamontagne reported on the sagittal and axial spinomobility in patients with hip OA, and highlighted reductions in pelvic tilt, pelvic-femoral-angle, lumbar lordosis and seated maximal trunk rotation when compared to controls. Dr Dennis showed that differences in spinopelvic mobility may explain the variable accuracy of acetabular version measurements on the cross-table lateral radiographs. Dr Gwo-Chin presented on a comprehensive functional analysis of 1,592 patients undergoing THA and observed that spinopelvic abnormalities are not infrequent (14%) in THA patients. Consistent with these findings Dr Murphy and collaborators identified a low prevalence of previous spinal instrumentation (1.5%), yet a high prevalence of spine stiffness (27.6%) in 149 patients undergoing THA. Session three highlighted various aspects of treating hip disease in young patients. Dr Peters investigated the need for subsequent hip arthroscopy in 272 patients treated with an isolated PAO. Only 4.8% of these patients required subsequent arthroscopy calling into question the routine use of combined arthroscopy and PAO. Three papers addressed questions related to THA in young patients. Dr Berend's study of 2532 hips demonstrated that high activity level was not associated with an increased risk of midterm aseptic or all cause failure. Dr Nunley presented on 43 young patients with an average age of 52 years treated with a cementless stem and modular dual mobility articulation. Stress shielding was minimal and no concerning metal ion release detected. Dr Garvin summarized minimum 15 year data of THA with highly cross-linked polyethylene in patient less than 50 years. These hips performed exceptionally well with no mechanical loosening or radiographic osteolysis. Dr Engh examined 10 year results of the Birmingham Hip Resurfacing implant and reported a 92.9 % overall survivorship, with males less than 55 years achieving a 98.3% survivorship. The session was concluded by long-term data on the Conserve Plus hip resurfacing arthroplasty. Dr Amstutz presented an impressive dataset depicting an 83.1% 20 year survivorship for this early resurfacing cohort. Direct anterior approach total hip arthroplasty was the focus of session four. Dr Meneghini reported on the anesthesia and surgical times of direct anterior and posterior approaches from a large healthcare system database. These data suggested longer OR and surgical times for the DAA both in the inpatient and ASC environments. Dr Clohisy introduced the technique and early outcomes of lateral decubitus position DAA. In a learning curve experience of 257 hips. 96% of acetabular components were in the Lewinneck safe zone, the aseptic revision rate was 0.9% and there were no dislocations. Dr Beaule analyzed femoral stem cement mantle with the DAA and posterior approaches by comparing two matched cohorts. Stem alignment and cement mantle quality were equivalent with both approaches. Similarly, Dr Emerson demonstrated technical feasibility and fewer cemented femoral stem failures when compared to cementless stems in a series of 360 DAAs THAs. The final paper of the session presented by Dr Hamilton examined the impact of surgical approach on dislocation after isolated head and liner exchange. Neither the posterior nor the anterior approach was superior in reducing the dislocation rate for these high dislocation risk procedures. The fifth session explored contemporary topics related to anesthesia and pain management. Dr Byrd opened the session with a comparative study evaluating general versus spinal anesthesia for hip arthroscopy. This preliminary study was provoked by the desire to minimize aerosolized exposure early in the COVID-19 pandemic by transitioning to spinal anesthesia. Both anesthetic methods were effective. Dr Austin presented a randomized, double-blind controlled trial comparing spinal anesthetic with mepivacaine, hyperbaric bupivacaine and isobaric bupivacaine. Mepivacaine patients ambulated earlier and were more likely to be discharged the same day. Dr Mont provided a very timely study on the effects of “cannabis use disorder” and THA outcomes. This administrative database study of 44,154 patients revealed this disorder to be associated with longer hospital stays, increased complications rates and higher costs. Dr Bedair investigated whether a highly porous acetabular component submerged in an analgesic solution could enhance perioperative pain management. Interestingly, this novel strategy was associated with a reduction of postoperative pain scores and opioid consumption in 100 experimental patients compared to 100 controls. The concluding paper of the session by Dr Della Valle examined whether decreased discharge opioids led to increased postoperative opioid refills. A large single-center study of 19,428 patients detected a slight increase (5%) in opioid refills but a reduction in total refill morphine milligram equivalents. The final, sixth session of day one considered various challenging aspects of revision hip arthroplasty. Dr Nam started the session with review of preliminary results from a randomized control trial comparing closed incision negative-pressure therapy with a silver-impregnated dressing for wound management in 113 hips undergoing revision arthroplasty. Unlike previous reports, the negative pressure therapy was associated with a higher reoperation rate for wound-related complications. Dr Bostrom highlighted the potential clinical impact of basic biological interventions by establishing the presence of Neutrophil Extracellular Traps (NETS) in fibrotic tissue from human aseptic loosening specimens and in a murine model of unstable tibial implantation. NET inhibition in the murine model prevented the expected tibial implant osseointegration failure. Dr Lombardi presented early 3.3 year clinical results of a highly porous Ti6al4v acetabular component in complex primary and revision arthroplasty. Survivorship for aseptic loosening was 96.6 % and 95.3% for the primary and revision cases, respectively. Dr Schwarzkopf and colleagues explored the impact of time to revision arthroplasty on clinical outcomes. Analysis of 188 revision cases revealed early revisions (less than 2 years from primary) were associated with worse outcomes, longer hospitalizations and higher reoperation rates. Mid-term results for modular dual mobility implants in revision arthroplasty were reviewed by Dr Lachiewicz who reported on 126 hips at a mean 5.5 years. 11% of hips dislocated and the 6 year survival was 91%. An outer head diameter of 48mm or greater was associated with a lower risk of dislocation. Dr Berry concluded the session by discussing the outcomes of treating the challenging problem of interprosthetic femur fractures. A single-center study of 77 cases treated over 32 years demonstrated a 79% success rate free of reoperation at 2 years with 95% of patients being ambulatory. The second day commenced with the seventh session evaluating recent strategies to improve short-term THA outcomes. Dr Bozic and colleagues investigated the association of quality measure public reporting with hip/knee replacement outcomes. Annual trend data from 2010–2011 and 2016–2017 indicate that hospital-level complication and readmission rates decease after the start of public reporting, yet it is difficult to prove a direct effect. Dr Slover reviewed his institutions experience with the Comprehensive Care for Joint Replacement (CJR) model and emphasized that lower CJR target prices make it increasingly difficult for programs to meet target price thresholds. Cost saving strategies including same day discharge and reduction of home health services may result in smaller losses of positive margins. Dr Barsoum reported on the influence of patient and procedure-related risk factors of length of stay after THA. Patient-related risk factors provided substantial predictive value yet procedure-related risk factors (hospital site and surgical approach) remain the main drivers of predicting length of stay. Dr Hozack reviewed an impressive, single surgeon cohort of 3,977 DAA THAs and analyzed adverse events and 90 day perioperative outcomes. Simultaneous bilateral DAA THA was comparable with unilateral or staged bilateral procedures in regards to complications, readmission rate and home discharge rate but with an increased risk of transfusion. To examine the risk of complications with outpatient joint arthroplasty, Dr Della Valle performed a single-surgeon matched cohort analysis comparing outpatient and inpatient hip and knee arthroplasties. Outpatient procedures were not associated with an increased risk of any postoperative complications and actually experienced fewer emergency department visits. The eighth session covered various contemporary challenges in hip arthroplasty care. Dr Griffin began the session with an analysis of the timing of complications associated with two-stage exchange procedures for periprosthetic joint infection (PJI). Of the 189 hips included, 41.6% had a complication and the mortality was 14.1% at 2.5 years, highlighting the morbidity of this treatment method. Dr Fehring provided data assessing the fate of two-stage reimplantation after failed debridement, antibiotics and implant retention (DAIR) for a prosthetic hip infection. This analysis of 114 hips yielded concerning results demonstrating a 42.9% treatment failure of patients treated with a previous DAIR compared to a 12.3% failure rate in patients treated with an initial 2-stage procedure. Dr Jacobs reviewed the analysis of 106 femoral heads with severe corrosion and identified a chemically dominated etching process termed “column damage” to be a detrimental damage mode within CoCr femoral heads that is directly linked to banding within its microstructure. These data indicate that implant alloy microstructure must be optimized to minimize the release of fretting-corrosion products. Simon Mears presented retrospective data from 184 THAs with a dual modular femoral stem. A subgroup of hips with a modular, cobalt chromium femoral neck had a pseudotumor visualized in 15% with only 55% of these having elevated CoCr levels. These findings may support the use of routine follow-up MARS MRI for modular CoCr femoral neck prostheses. The final two studies explored timely issues related to viral illness and hip surgery. Dr Browne analyzed three large administrative databases to elucidate whether patients are at increased risk for viral illnesses following total joint replacement. The incidence of postoperative influenza after total joint replacement was not increased compared to patients not undergoing total joint replacement surgery suggesting that arthroplasty procedures may not heighten the risk of viral illness. In the final paper of the session Dr Haddad presented important data regarding perioperative complications in coronavirus positive patients undergoing surgical treatment of femoral neck fractures. In this multicenter cohort study from the United Kingdom 82 coronavirus positive patients were shown to have longer hospital stays, more critical care unit admissions, higher risk of perioperative complications and an increased mortality compared to 340 coronavirus negative patients. The eighth session had two papers on alternative femoral stem designs and three presentations more focused on femoral fracture treatments. Dr Mihalko focused on the European and US experiences with the Metha femoral neck retaining stem. The US experience mirrored the encouraging results from Europe with a 94% all cause femoral survivorship and a 99.1% femoral aseptic loosening survivorship at 5 years. Dr Kraay summarized dual energy x-ray absorptiometry (DEXA) evaluation of 16 low modulus composite femoral components at long-term follow-up of a mean 22 years. The bone mineral density associated with the implant increased in Gruen zones 2–6 and showed limited decreases in zones 1 and 7. These data support the concept that a low modulus femoral stem may more effectively load the proximal femur. Dr Springer provided data from the American Joint Replacement Registry (AJRR) and by evaluating outcomes of exact matched cohorts of 17,138 patients treated with cementless or cemented femoral implants for femoral neck fractures. Cemented implants were associated with marked reduction in early revision and periprosthetic fractures. However, cemented fixation was associated with an increased mortality at 90 days and 1 year. Additional data from the AJRR was presented by Dr Huddleston who investigated the risk factors for revision surgery after arthroplasty in a cohort of 75,333 femoral neck fractures. THA when compared to hemiarthroplasty was associated with higher early and overall revision rates. Cementless femoral fixation and increased age were also associated with higher rates of any revision. Both of these studies from the AJRR suggest that further consideration should be given to femoral fixation preferences in the femoral neck fracture population. Dr Vail summarized his institution's experience with an interdisciplinary hip fracture protocol for patients undergoing arthroplasty for acute femoral neck fractures. His study compared 157 cases prior to protocol implementation with 114 patients treated after the protocol was established. The impact of the interdisciplinary protocol was impressive as evidenced by a reduced time to operative treatment, length of stay, complication rate and one-year mortality. All being achieved without an increase in readmissions or facility discharges. The final session of the meeting addressed innovations in perioperative care of THA patients. Dr Barrack started the session with an interesting study examining the feasibility and patient preferences regarding telemedicine. A cross-sectional telephone survey of 163 arthroplasty patients indicated that 88% of patients use the internet and 94% own a device capable of videoconferencing. Nevertheless, only 18% of patients preferred a video visit over an in-person clinic visit due to concerns of inferior care. Dr Barnes quantified preoperative optimization work in 100 arthroplasty patients by using EMR activity logs and determined the surgical team spends an average 75 minutes per case on preoperative work activities. Dr Duwelius reported the early outcomes of primary THA with a smartphone-based exercise and educational platform compared to standard of care controls. A randomized control trial design with 365 patients demonstrated similar outcomes and non-inferiority of the smartphone platform relative to complications, readmissions, emergency room/urgent care visits. The association of controlled substance use with THA outcomes was assessed by Dr Higuera Rueda. A quantitative assessment using the NarxCare score identified 300 and above as a score associated with adverse outcomes after THA. Dr Macaulay reviewed data from a large retrospective study of 1,825 THAs indicating that discontinuation of intermittent pneumatic compression devices does not increase the risk of venous thromboembolism in standard risk patients being treated with 81mg ASA BID as prophylaxis. Dr Antoniou presented the final paper of the meeting investigating potential changes in patient health status as an indication for surgery over time. Data from this large systematic review of the literature found patients undergoing THA at similar health status to the past with no influence form patient age, gender, year of enrollment or geographic region. As summarized above, the 2020 virtual Hip Society Summer Meeting was rich in scientific content, productive discussion and a collaborative spirit. This collective body of work will result in impactful scientific contributions and will serve as a foundation for future innovation and advancements in the treatment of hip disease

Aims

Natural Language Processing (NLP) offers an automated method to extract data from unstructured free text fields for arthroplasty registry participation. Our objective was to investigate how accurately NLP can be used to extract structured clinical data from unstructured clinical notes when compared with manual data extraction.

Aims

The primary aim of this paper was to outline the processes involved in building the Partners Arthroplasty Registry (PAR), established in April 2016 to capture baseline and outcome data for patients undergoing arthroplasty in a regional healthcare system. A secondary aim was to determine the quality of PAR’s data. A tertiary aim was to report preliminary findings from the registry and contributions to quality improvement initiatives and research up to March 2019.

Aims

Custom flange acetabular components (CFACs) are a patient-specific option for addressing large acetabular defects at revision total hip arthroplasty (THA), but patient and implant characteristics that affect survivorship remain unknown. This study aimed to identify patient and design factors related to survivorship.