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. Methods. The study included 538 joints that underwent primary THA. The patients were divided into groups using unsupervised time series clustering for five-year BMD loss of Gruen zone 7 postoperatively, and a machine-learning model to predict the BMD loss was developed. Additionally, the predictor for BMD loss was extracted using SHapley Additive exPlanations (SHAP). The patient-specific efficacy of bisphosphonate, which is the most important categorical predictor for BMD loss, was examined by calculating the change in predictive probability when hypothetically switching between the inclusion and exclusion of bisphosphonate. Results. Time series clustering allowed us to divide the patients into two groups, and the predictive factors were identified including patient- and operation-related factors. The area under the receiver operating characteristic (ROC) curve (AUC) for the BMD loss prediction averaged 0.734. Virtual administration of bisphosphonate showed on average 14% efficacy in preventing BMD loss of zone 7. Additionally, stem types and preoperative triglyceride (TG), creatinine (Cr), estimated glomerular filtration rate (eGFR), and creatine kinase (CK) showed significant association with the estimated patient-specific efficacy of bisphosphonate. Conclusion. Periprosthetic BMD loss after THA is predictable based on patient- and operation-related factors, and optimal prescription of bisphosphonate based on the prediction may prevent BMD loss. Cite this article: Bone Joint Res 2024;13(4):184–192

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

As patient data continues to grow, the importance of efficient and precise analysis cannot be overstated. The employment of Generative Artificial Intelligence (AI), specifically Chat GPT-4, in the realm of medical data interpretation has been on the rise. However, its effectiveness in comparison to manual data analysis has been insufficiently investigated. This quality improvement project aimed to evaluate the accuracy and time-efficiency of Generative AI (GPT-4) against manual data interpretation within extensive datasets pertaining to patients with orthopaedic injuries. A dataset, containing details of 6,562 orthopaedic trauma patients admitted to a district general hospital over a span of two years, was reviewed. Two researchers operated independently: one utilised GPT-4 for insights via prompts, while the other manually examined the identical dataset employing Microsoft Excel and IBM® SPSS® software. Both were blinded on each other's procedures and outcomes. Each researcher answered 20 questions based on the dataset including injury details, age groups, injury specifics, activity trends and the duration taken to assess the data. Upon comparison, both GPT-4 and the manual researcher achieved consistent results for 19 out of the 20 questions (95% accuracy). After a subsequent review and refined prompts (prompt engineering) to GPT-4, the answer to the final question aligned with the manual researcher's findings. GPT-4 required just 30 minutes, a stark contrast to the manual researcher's 9-hour analytical duration. This quality improvement project emphasises the transformative potential of Generative AI in the domain of medical data analysis. GPT-4 not only paralleled the accuracy of manual analysis but also achieved this in significantly less time. For optimal accurate results, data analysis by AI can be enhanced through human oversight. Adopting AI-driven approaches, particularly in orthopaedic data interpretation, can enhance efficiency and ultimately improve patient care. We recommend future investigations on large and more varied datasets to reaffirm these outcomes

INTRODUCTION. Quality monitoring is increasingly important to support and assure sustainability of the Orthopaedic practice. Many surgeons in a non-academic setting lack the resources to accurately monitor quality of care. Widespread use of electronic medical records (EMR) provides easier access to medical information and facilitates its analysis. However, manual review of EMRs is inefficient and costly. Artificial Intelligence (AI) software has allowed for development of automated search algorithms for extracting relevant complications from EMRs. We questioned whether an AI supported algorithm could be used to provide accurate feedback on the quality of care following Total Hip Arthroplasty (THA) in a high-volume, non-academic setting. METHODS. 532 Consecutive patients underwent 613 THA between January 1. st. and December 31. st. , 2017. Patients were prospectively followed pre-op, 6 weeks, 3 months and 1 year. They were seen by the surgeon who created clinical notes and reported every adverse event. A random derivation cohort (100 patients, 115 hips) was used to determine accuracy. The algorithm was compared to manual extraction to validate performance in raw data extraction. The full cohort (532 patients, 613 hips) was used to determine its recall, precision and F-value. RESULTS. The algorithm had an accuracy value of 95.0%, compared to 94.5% for manual review (p=0.69). Recall of 96.0% was achieved with precision of 88.0% and F-measure of 0.85 for all adverse events. Recovery of 80.6% of patients was completely uneventful. Re-intervention was required in 1.3% of cases and 18.1% had a ‘transient’ event such as low back pain. The infection and dislocation rate was 0,3%. CONCLUSION. An AI supported search algorithm can analyze and interpret large quantities of EMRs at greater speed but with performance comparable to manual review. Using the program, new clinical information surfaced. 18.1% of patients can be expected to have a ‘transient’ problem following a THA procedure

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.

Background

Dislocation is a common complication following total hip arthroplasty (THA), and accounts for a high percentage of subsequent revisions. The purpose of this study was to develop a convolutional neural network (CNN) model to identify patients at high risk for dislocation based on postoperative anteroposterior (AP) pelvis radiographs.

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. Hip dysplasia (HD) leads to premature osteoarthritis. Timely detection and correction of HD has been shown to improve pain, functional status, and hip longevity. Several time-consuming radiological measurements are currently used to confirm HD. An artificial intelligence (AI) software named HIPPO automatically locates anatomical landmarks on anteroposterior pelvis radiographs and performs the needed measurements. The primary aim of this study was to assess the reliability of this tool as compared to multi-reader evaluation in clinically proven cases of adult HD. The secondary aims were to assess the time savings achieved and evaluate inter-reader assessment. Methods. A consecutive preoperative sample of 130 HD patients (256 hips) was used. This cohort included 82.3% females (n = 107) and 17.7% males (n = 23) with median patient age of 28.6 years (interquartile range (IQR) 22.5 to 37.2). Three trained readers’ measurements were compared to AI outputs of lateral centre-edge angle (LCEA), caput-collum-diaphyseal (CCD) angle, pelvic obliquity, Tönnis angle, Sharp’s angle, and femoral head coverage. Intraclass correlation coefficients (ICC) and Bland-Altman analyses were obtained. Results. Among 256 hips with AI outputs, all six hip AI measurements were successfully obtained. The AI-reader correlations were generally good (ICC 0.60 to 0.74) to excellent (ICC > 0.75). There was lower agreement for CCD angle measurement. Most widely used measurements for HD diagnosis (LCEA and Tönnis angle) demonstrated good to excellent inter-method reliability (ICC 0.71 to 0.86 and 0.82 to 0.90, respectively). The median reading time for the three readers and AI was 212 (IQR 197 to 230), 131 (IQR 126 to 147), 734 (IQR 690 to 786), and 41 (IQR 38 to 44) seconds, respectively. Conclusion. This study showed that AI-based software demonstrated reliable radiological assessment of patients with HD with significant interpretation-related time savings. Cite this article: Bone Jt Open 2022;3(11):877–884

The variables involved in a robotic THA can exceed 52: many parameters as pelvic orientation with CT scan, templating, offset, and leg-length, acetabular reaming, femoral osteotomy, mapping the anatomy; predefining safe zones, robotic execution, femoral head size, thickness of PE etc. with several variables for each parameter, with a total number of variables exceeding 52. This familiar number is the number of cards in a standard deck. The number of possible combinations (factorial 52! = 10^67) to shuffle the cards (and may be to perform a THA) is greater than the number of atoms on earth! Thinking that artificial intelligence and robotics can solve these problems, some surgeons and implant manufacturers have turned to artificial intelligence and robotics. We asked two questions:1) can robot with artificial intelligence really process 52 variables that represent 10^67 combinations? 2) the safety of the technology was ascertained by interrogating Food and Drug Administration (FDA) database about software-related recalls in computer-assisted and robotic arthroplasty [1], between 2017 and 2022. 1). The best computers can only calculate around 100 thousand billion combinations (10^14), and with difficulty: it takes more than 100 days to arrive at this number of digits (10^14) after the decimal point for the number π (pi). We can, therefore, expect the robot to be imperfect. 2). For the FDA software-related recalls, 4634 units were involved. The FDA determined root causes were: software design (66.6%), design change (22.2%), manufacturing deployment (5.6%), design manufacturing process (5.6%). Among the manufacturers’ reasons for recalls, a specific error was declared in 88.9%. a coding error in 43.8%. 94.4% software-related recalls were classified as class 2. Return of the device was the main action taken by firms (44.4%), followed by software update (38.9%). 3). In the same period, no robot complained about its surgeon!. Hip surgeon is as intelligent as a robot and almost twice as safe

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

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

Aims

It is important to analyze objectively the hammering sound in cup press-fit technique in total hip arthroplasty (THA) in order to better understand the change of the sound during impaction. We hypothesized that a specific characteristic would present in a hammering sound with successful fixation. We designed the study to quantitatively investigate the acoustic characteristics during cementless cup impaction in THA.

Aims

It is important to analyze objectively the hammering sound in cup press-fit technique in total hip arthroplasty (THA) in order to better understand the change of the sound during impaction. We hypothesized that a specific characteristic would present in a hammering sound with successful fixation. We designed the study to quantitatively investigate the acoustic characteristics during cementless cup impaction in THA.

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

Optimal exposure through the direct anterior approach (DAA) for total hip arthroplasty (THA) conducted on a regular operating theatre table is achieved with a standardized capsular releasing sequence in which the anterior capsule can be preserved or resected. We hypothesized that clinical outcomes and implant positioning would not be different in case a capsular sparing (CS) technique would be compared to capsular resection (CR).