To examine whether Natural Language Processing (NLP) using a state-of-the-art clinically based Large Language Model (LLM) could predict patient selection for Total Hip Arthroplasty (THA), across a range of routinely available clinical text sources. Data pre-processing and analyses were conducted according to the Ai to Revolutionise the patient Care pathway in Hip and Knee arthroplasty (ARCHERY) project protocol (. https://www.researchprotocols.org/2022/5/e37092/. ). Three types of deidentified Scottish regional clinical free text data were assessed: Referral letters, radiology reports and clinic letters. NLP algorithms were based on the GatorTron model, a Bidirectional Encoder Representations from Transformers (BERT) based LLM trained on 82 billion words of de-identified clinical text. Three specific inference tasks were performed: assessment of the base GatorTron model, assessment after model-fine tuning, and external validation. There were 3911, 1621 and 1503 patient text documents included from the sources of referral letters, radiology reports and clinic letters respectively. All letter sources displayed significant class imbalance, with only 15.8%, 24.9%, and 5.9% of patients linked to the respective text source documentation having undergone surgery. Untrained model performance was poor, with F1 scores (harmonic mean of precision and recall) of 0.02, 0.38 and 0.09 respectively. This did however improve with model training, with mean scores (range) of 0.39 (0.31–0.47), 0.57 (0.48–0.63) and 0.32 (0.28–0.39) across the 5 folds of cross-validation. Performance deteriorated on external validation across all three groups but remained highest for the radiology report cohort. Even with further training on a large cohort of routinely collected free-text data a clinical LLM fails to adequately perform clinical inference in NLP tasks regarding identification of those selected to undergo THA. This likely relates to the complexity and heterogeneity of free-text information and the way that patients are determined to be surgical candidates

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

Aims. Cementing in arthroplasty for hip fracture is associated with improved postoperative function, but may have an increased risk of early mortality compared to uncemented fixation. Quantifying this mortality risk is important in providing safe patient care. This study investigated the association between cement use in arthroplasty and mortality at 30 days and one year in patients aged 50 years and over with hip fracture. Methods. This retrospective cohort study used linked data from the Australian Hip Fracture Registry and the National Death Index. Descriptive analysis and Kaplan-Meier survival curves tested the unadjusted association of mortality between cemented and uncemented procedures. Multilevel logistic regression, adjusted for covariates, tested the association between cement use and 30-day mortality following arthroplasty. Given the known institutional variation in preference for cemented fixation, an instrumental variable analysis was also performed to minimize the effect of unknown confounders. Adjusted Cox modelling analyzed the association between cement use and mortality at 30 days and one year following surgery. Results. The 30-day mortality was 6.9% for cemented and 4.9% for uncemented groups (p = 0.003). Cement use was significantly associated with 30-day mortality in the Kaplan-Meier survival curve (p = 0.003). After adjusting for covariates, no significant association between cement use and 30-day mortality was shown in the adjusted multilevel logistic regression (odd rati0 (OR) 1.1, 95% confidence interval (CI) 0.9 to 1.5; p = 0.366), or in the instrumental variable analysis (OR 1.0, 95% CI 0.9 to 1.0, p=0.524). There was no significant between-group difference in mortality within 30days (hazard ratio (HR) 0.9, 95% CI 0.7to 1.1; p = 0.355) or one year (HR 0.9 95% CI 0.8 to 1.1; p = 0.328) in the Cox modelling. Conclusion. No statistically significant difference in patient mortality with cement use in arthroplasty was demonstrated in this population, once adjusted for covariates. This study concludes that cementing in arthroplasty for hip fracture is a safe means of surgical fixation. Cite this article: Bone Jt Open 2023;4(3):198–204

Aims. Delirium is associated with adverse outcomes following hip fracture, but the prevalence and significance of delirium for the prognosis and ongoing rehabilitation needs of patients admitted from home is less well studied. Here, we analyzed relationships between delirium in patients admitted from home with 1) mortality; 2) total length of hospital stay; 3) need for post-acute inpatient rehabilitation; and 4) hospital readmission within 180 days. Methods. This observational study used routine clinical data in a consecutive sample of hip fracture patients aged ≥ 50 years admitted to a single large trauma centre during the COVID-19 pandemic between 1 March 2020 and 30 November 2021. Delirium was prospectively assessed as part of routine care by the 4 A’s Test (4AT), with most assessments performed in the emergency department. Associations were determined using logistic regression adjusted for age, sex, Scottish Index of Multiple Deprivation quintile, COVID-19 infection within 30 days, and American Society of Anesthesiologists grade. Results. A total of 1,821 patients were admitted, with 1,383 (mean age 79.5 years; 72.1% female) directly from home. Overall, 87 patients (4.8%) were excluded due to missing 4AT scores. Delirium prevalence in the whole cohort was 26.5% (460/1,734): 14.1% (189/1,340) in the subgroup of patients admitted from home, and 68.8% (271/394) in the remaining patients (comprising care home residents and inpatients when fracture occurred). In patients admitted from home, delirium was associated with a 20-day longer total length of stay (p < 0.001). In multivariable analyses, delirium was associated with higher mortality at 180 days (odds ratio (OR) 1.69 (95% confidence interval (CI) 1.13 to 2.54); p = 0.013), requirement for post-acute inpatient rehabilitation (OR 2.80 (95% CI 1.97 to 3.96); p < 0.001), and readmission to hospital within 180 days (OR 1.79 (95% CI 1.02 to 3.15); p = 0.041). Conclusion. Delirium affects one in seven patients with a hip fracture admitted directly from home, and is associated with adverse outcomes in these patients. Delirium assessment and effective management should be a mandatory part of standard hip fracture care. Cite this article: Bone Jt Open 2023;4(6):447–456

Introduction. Previous studies have reported an increased risk for postoperative complications in the Medicaid population undergoing total hip arthroplasty (THA). These studies have focused on payer type and have not controlled for the surgeon's practice or patient care setting. This study aims to evaluate whether patient point of entry plays a role in quality outcomes and discharge disposition following THA. Methods. The electronic medical record at our institution was retrospectively reviewed for all primary, elective, unilateral THA between January 2016 and June 2018. THA recipients were categorized as either Hospital Ambulatory Clinic Centers (HACC) with Medicaid as the primary payer or private office patients with a non-Medicaid primary payer based on a previous visit to our institution's HACC within the 6-months prior to surgery. Only patients who had been operated on by a surgeon with at least 10 HACC and 10 private office patients were included. Results. A total of 426 patients were included in this study, with 114 HACC and 312 private office patients. HACC patients were significantly younger (p<0.01), more likely to be black or “other” race (p<0.01), and more likely to be a current smoker (p<0.01). In the unadjusted model, length of stay (p=0.15) and surgical time (p=0.03) were greater in HACC patients. There was no difference in discharge disposition (p=1). After adjusting for patient risk factors, LOS was greater for HACC patients, whereas surgical time and facility discharge were lower. Conclusion. There was a significant difference in surgical time between HACC and private clinic patients. After controlling for patient risk factors, LOS, surgical time, and facility discharge were similar between the two groups. These results indicate that similar outcomes can be achieved for Medicaid patients as compared to non-Medicaid patients as long as the surgeon and patient care setting are similar. For any tables or figures, please contact the authors directly

Aims. Previous studies have reported an increased risk for postoperative complications in the Medicaid population undergoing total hip arthroplasty (THA). These studies have not controlled for the surgeon’s practice or patient care setting. This study aims to evaluate whether patient point of entry and Medicaid status plays a role in quality outcomes and discharge disposition following THA. Methods. The electronic medical record at our institution was retrospectively reviewed for all primary, unilateral THA between January 2016 and January 2018. THA recipients were categorized as either Medicaid or non-Medicaid patients based on a visit to our institution’s Hospital Ambulatory Care Center (HACC) within the six months prior to surgery. Only patients who had been operated on by surgeons (CML, JV, JDS, RS) with at least ten Medicaid and ten non-Medicaid patients were included in the study. The patients included in this study were 56.33% female, had a mean age of 60.85 years, and had a mean BMI of 29.14. The average length of follow-up was 343.73 days. Results. A total of 426 hips in 403 patients were included in this study, with 114 Medicaid patients and 312 non-Medicaid patients. Medicaid patients had a significantly lower mean age (54.68 years (SD 12.33) vs 63.10 years (SD 12.38); p < 0.001), more likely to be black or ‘other’ race (27.19% vs 13.46% black; 26.32% vs 12.82% other; p < 0.001), and more likely to be a current smoker (19.30% vs 9.29%; p = 0.001). After adjusting for patient risk factors, there was a significant Medicaid effect on length of stay (LOS) (rate ratio 1.129, 95% confidence interval (CI) 1.048 to 1.216; p = 0.001) and facility discharge (odds ratio 2.010, 95% CI 1.398 to 2.890; p < 0.001). There was no Medicaid effect on surgical time (exponentiated β coefficient 1.015, 95% CI 0.995 to 1.036; p = 0.136). There was no difference in 30-day readmission, 90-day readmission, 30-day infections, 90-day infections, and 90-day mortality between the two groups. Conclusion. After controlling for patient variables, there was a statistically significant Medicaid effect on LOS and facility discharge. These results indicate that clinically similar outcomes can be achieved for Medicaid patients; however, further work is needed on maximizing social support and preoperative patient education with a focus on successful home discharge. Cite this article: Bone Joint J 2020;102-B(7 Supple B):78–84

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

Aims

The burden of revision total hip arthroplasty (rTHA) continues to grow. The surgery is complex and associated with significant costs. Regional rTHA networks have been proposed to improve outcomes and to reduce re-revisions, and therefore costs. The aim of this study was to accurately quantify the cost and reimbursement for a rTHA service, and to assess the financial impact of case complexity at a tertiary referral centre within the NHS.

Aims

Total hip arthroplasty (THA) is a common procedure to address pain and enhance function in hip disorders such as osteoarthritis. Despite its success, postoperative patient recovery exhibits considerable heterogeneity. This study aimed to investigate whether patients follow distinct pain trajectories following THA and identify the patient characteristics linked to suboptimal trajectories.

Aims

The aims of this study were to evaluate the incidence of reoperation (all cause and specifically for periprosthetic femoral fracture (PFF)) and mortality, and associated risk factors, following a hemiarthroplasty incorporating a cemented collarless polished taper slip stem (PTS) for management of an intracapsular hip fracture.

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.

Introduction. The number of hip fracture admissions is rising; with reduced hospital bed capacity and increasing patient numbers, care pathways must be optimised to maximise inpatient bed efficiency. There is currently significant interest in improving healthcare services across all 7 days in the United Kingdom. It is unclear whether lack of allied healthcare professional review at the weekend is detrimental to hip fracture patient care. This study aims to examine whether providing 7-day physiotherapy and occupational therapy (7DPOT) service improves outcomes for fractured neck of femur patients compared to a 5-day service (5DPOT). Methods. All patients admitted with an acute neck of femur fracture were grouped into three cohorts, depending on provision of 7DPOT services: the initial cohort received 5DPOT between December 2012 and March 2013. Seven-day physiotherapy and occupational therapy was introduced for one year from October 2014 until September 2015 (2. nd. cohort). The service then reverted to 5DPOT between January to June 2016 (3. rd. cohort). The third cohort was utilised to nullify changes in the overall service which had occurred which were not attributable to 7DPOT. Data was collected prospectively using a specially designed audit tool. Results. 580 patients were included, with 533 patients followed out to 120 days. Introduction of 7DPOT saw improvement of documented first mobilisation with a physiotherapist from mean 1.38 days to 0.98 days (p<0.05). No significant differences were seen in inpatient length of stay between the three groups or when comparing all 5DPOT to 7DPOT. Use of 7DPOT did not lead to significant differences in initial discharge location. Mortality at 120-day follow up was observed to improve over time but was not attributable to 7DPOT. Conclusion. This study has not shown any significant improvement in outcomes for hip fracture patients receiving 7DPOT compared 5DPOT. Given the current financial constraints on healthcare services, widespread adoption cannot be recommended

Aims

The primary aim of this study was to determine the ten-year outcome following surgical treatment for femoroacetabular impingement (FAI). We assessed whether the evolution of practice from open to arthroscopic techniques influenced outcomes and tested whether any patient, radiological, or surgical factors were associated with outcome.

Aims. To determine mortality risk after first revision total hip arthroplasty (THA) for periprosthetic femoral fracture (PFF), and to compare this to mortality risk after primary and first revision THA for other common indications. Methods. The study cohort consisted of THAs recorded in the National Joint Registry between 2003 and 2015, linked to national mortality data. First revision THAs for PFF, infection, dislocation, and aseptic loosening were identified. We used a flexible parametric model to estimate the cumulative incidence function of death at 90 days, one year, and five years following first revision THA and primary THA, in the presence of further revision as a competing risk. Analysis covariates were age, sex, and American Society of Anesthesiologists (ASA) grade. Results. A total of 675,078 primary and 74,223 first revision THAs were included (of which 6,131 were performed for PFF). Following revision for PFF, mortality ranged from 9% at 90 days, 21% at one year, and 60% at five years in the highest risk group (males, ≥ 75 years, ASA ≥ 3) to 0.6%, 1.4%, and 5.5%, respectively, for the lowest risk group (females, < 75 years, ASA ≤ 2). Mortality was greater in all groups following first revision THA for PFF than for primary THA. Compared to mortality risk after first revision THA for infection, dislocation, or aseptic loosening, revision for PFF was associated with higher five-year mortality in all groups except males < 75 years with an ASA ≤ 2. Conclusion. Mortality risk after revision THA for PFF is high, reaching 60% at five years in the highest risk patient group. In comparison to other common indications for revision, PFF demonstrated the highest overall risk of mortality at five years. These estimates can be used in the surgical decision-making process and when counselling patients and carers regarding surgical risk. Cite this article: Bone Joint J 2020;102-B(12):1670–1674

Aims

The aim of this study was to estimate the clinical and economic burden of dislocation following primary total hip arthroplasty (THA) in England.

Aims

The aim of this modified Delphi process was to create a structured Revision Hip Complexity Classification (RHCC) which can be used as a tool to help direct multidisciplinary team (MDT) discussions of complex cases in local or regional revision networks.

Aims

A recent report from France suggested an association between the use of cobalt-chrome (CoCr) femoral heads in total hip arthroplasties (THAs) and an increased risk of dilated cardiomyopathy and heart failure. CoCr is a commonly used material in orthopaedic implants. If the reported association is causal, the consequences would be significant given the millions of joint arthroplasties and other orthopaedic procedures in which CoCr is used annually. We examined whether CoCr-containing THAs were associated with an increased risk of all-cause mortality, heart outcomes, cancer, and neurodegenerative disorders in a large national database.

Aims

This study aimed to describe preoperative waiting times for surgery in hip fracture patients in Norway, and analyze factors affecting waiting time and potential negative consequences of prolonged waiting time.

Introduction. Alternative payment models for total hip arthroplasty (THA) were initiated by the Center for Medicare and Medicaid Services (CMS) to decrease overall healthcare cost by optimizing healthcare delivery. The associated shift of financial risk to participating institutions has been criticized to introduce patient selection in order to avoid potentially high cost of care. This study aimed to evaluate the impact of the Comprehensive Care for Joint Replacement (CJR) model on patient selection, care delivery and hospital costs at a single care center. Methods. This is a retrospective review of THA patient from July 2015-December 2017 was performed. Patient were stratified by insurance type (Medicare and commercial insurance) and whether care was provided before or after implementation of the CJR bundle. Patient age, gender, and BMI, as well as Elixhauser comorbidities and ASA scores were analyzed. Delivery of care variables including surgery duration, discharge disposition, length of stay, and direct hospital costs were compared before and after CJR implementation. Results. 751 THA patients (273 Medicare and 478 Commercial Insurance) were evaluated before (29%) and after (71%) CJR bundle implementation. There was no difference in patient demographics (age, gender, or BMI); however, commercially insured patients had less Elxihauser comorbidies pre-bundle (p=0.033). After CJR implementation length of stay (p=0.010) for Medicare patients was reduced with a trend toward discharge to home (p=0.019). However, surgical time and OR service time as well as direct hospital costs were similar before and after the CJR bundle initiation. Conclusions. There was no differential patient selection after CJR bundle implementation, and value-based metrics (surgical time, OR service time) were not affected. Patients were discharged sooner and more often to home. However, overall direct hospital expenses remained unchanged revealing that any cost savings were for insurance providers, not participating hospitals. For any tables or figures, please contact the authors directly

Aims

To achieve the functional benefits of the direct anterior (DA) approach and the fixation benefits of cemented replacement, this study combined the two techniques posing the following questions: does the limited access of the DA approach adversely affect the cement technique?; and does such a cementing technique reduce the incidence of cementless complications?