Background: This study aimed to evaluate ChatGPT’s performance on questions about periprosthetic joint infections (PJI) of the hip and knee. Methods: Twenty-seven questions from the 2018 International Consensus Meeting on Musculoskeletal Infection were selected for response generation. The free-text responses were evaluated by three orthopedic surgeons using a five-point Likert scale. Inter-rater reliability (IRR) was assessed via Fleiss’ kappa (FK). Results: Overall, near-perfect IRR was found for disagreement on the presence of factual errors (FK: 0.880, 95% CI [0.724, 1.035], p < 0.001) and agreement on information completeness (FK: 0.848, 95% CI [0.699, 0.996], p < 0.001). Substantial IRR was observed for disagreement on misleading information (FK: 0.743, 95% CI [0.601, 0.886], p < 0.001) and agreement on suitability for patients (FK: 0.627, 95% CI [0.478, 0.776], p < 0.001). Moderate IRR was observed for agreement on “up-to-dateness” (FK: 0.584, 95% CI [0.434, 0.734], p < 0.001) and suitability for orthopedic surgeons (FK: 0.505, 95% CI [0.383, 0.628], p < 0.001). Question- and subtopic-specific analysis revealed diverse IRR levels ranging from near-perfect to poor. Conclusions: ChatGPT’s free-text responses to complex orthopedic questions were predominantly reliable and useful for orthopedic surgeons and patients. Given variations in performance by question and subtopic, consulting additional sources and exercising careful interpretation should be emphasized for reliable medical decision-making.

Increasing total hip (THA) and knee (TKA) arthroplasties inevitably lead to accumulating failed arthroplasty (FA) with periprosthetic joint infections (PJI) and definite treatment recommendations are scarce. Our aims were to evaluate patient and infection site specific risk factors, and to identify case-dependent salvage procedure recommendations. Retrospective analysis was conducted of salvage procedures for FA after PJI (amputation, Girdlestone resection arthroplasty [GRA], arthrodesis, or chronic fistulation [CF]) from 2008 to 2018. Univariable and multivariable modeling of revision and mortality rates, using cumulative incidence competing risk analysis, and Cox proportional hazards models were calculated. In total, 135 patients (THA 62%; TKA 38%) were diagnosed for FA after PJI, having undergone an average of 3 [1-4] revisions at a mean follow-up of 12.8 [7.8-20.9] years. Forty-four percent of THAs and 55% of TKAs had to be revised following FA, 44% deceased during follow-up, and 16% could be reconverted to an infection-free arthroplasty. GRA revealed significantly higher revision rates than CF (P = .015) for THA. Lower age (P = .003), higher number of revisions before FA (P = .007), more than one microorganism at infection site (P = .034), and GRA (P = .037, only THA) prevailed independent risk factors for revision. Patients' age remained an independent mortality risk factor (P = .001). High-risk patients suffering from FA after THA with poor constitution profit from controlled constitution of CF, reducing the risk for revision surgeries and hospitalization. In case of FA after TKA, data did not allow definite treatment recommendations. We believe that education concerning amputation should be considered early after multiple TKA revisions.

Currently, patients with extremity soft tissue sarcoma (eSTS) who have undergone curative resection are followed up by a heuristic approach, not covering individual patient risks. The aim of this study was to develop two flexible parametric competing risk regression models (FPCRRMs) for local recurrence (LR) and distant metastasis (DM), aiming at providing guidance on how to individually follow-up patients. Three thousand sixteen patients (1931 test, 1085 validation cohort) with high-grade eSTS were included in this retrospective, multicenter study. Histology (9 categories), grading (time-varying covariate), gender, age, tumor size, margins, (neo)adjuvant radiotherapy (RTX), and neoadjuvant chemotherapy (CTX) were used in the FPCRRMs and performance tested with Harrell-C-index. Median follow-up was 50 months (interquartile range: 23.3–95 months). Two hundred forty-two (12.5%) and 603 (31.2%) of test cohort patients developed LR and DM. Factors significantly associated with LR were gender, size, histology, neo- and adjuvant RTX, and margins. Parameters associated with DM were margins, grading, gender, size, histology, and neoadjuvant RTX. C-statistics was computed for internal (C-index for LR: 0.705, for DM: 0.723) and external cohort (C-index for LR: 0.683, for DM: 0.772). Depending on clinical, pathological, and patient-related parameters, LR- and DM-risks vary. With the present model, implemented in the updated Personalised Sarcoma Care (PERSARC)-app, more individualized prediction of LR/DM-risks is made possible.

Background: The aim of this study was to assess the outcome of total ankle replacement (TAR) regarding revision rates by comparing clinical studies of the last decade to data displayed in arthroplasty registers. The secondary aim was to evaluate whether dependent clinical studies show a superior outcome to independent publications. Additionally, revision rates of mobile bearing implants (MB-TARs) were compared to those of fixed bearing implants (FB-TARs). Methods: Clinical studies on TARs between 2010 and 2020 were systematically reviewed, with the endpoint being a revision for any reason. The parameter “revision rate per 100 observed component years (CYs)” was calculated for each publication. The pooled revision rate for clinical studies was compared to the data reported in arthroplasty registers. In a second step, revision rates were subdivided and analyzed for independent and dependent publications and for FB-TARs and MB-TARs. Results: A total of 43 publications met the inclusion criteria comprising 5806 TARs. A revision rate of 1.8 per 100 observed CYs was calculated, corresponding to a 7-year revision rate of 12.6%. The 3 arthroplasty registers included showed revision rates ranging from 8.2% to 12.3% after 7 years. No significant difference between dependent and independent publications nor between FB-TARs and MB-TARs was detected. Conclusion: Revision rates of clinical studies and arthroplasty registers are comparable. Surgeons can compare their own revision rates with those from this study. Dependent studies do not seem to be biased, and no superiority for one bearing type can be described. Level of Evidence: Level III, systematic review of level III studies

Purpose: In many cases, the diagnosis of a periprosthetic joint infection (PJI) consisting of the clinical appearance, laboratory tests, and other diagnostic tools remains a difficult task. Single serum biomarkers are easy to collect, are suitable for periodical assessment, and are a crucial tool in PJI diagnosis, but limited sensitivity or specificity is reported in literature. The aim of this study was to combine the best-performing single serum biomarkers into a multi-biomarker model aiming to improve the diagnostic properties. Methods: Within a 27-month period, 124 surgical procedures (aseptic or septic revision total knee arthroplasty (TKA) or total hip arthroplasty (THA)) were prospectively included. The serum leukocyte count, C-reactive protein (CRP), interleukin-6, procalcitonin, interferon alpha, and fibrinogen were assessed 1 day prior to surgery. Logistic regression with lasso-regularization was used for the biomarkers and all their ratios. After randomly splitting the data into a training (75%) and a test set (25%), the multi-biomarker model was calculated and validated in a cross-validation approach. Results: CRP (AUC 0.91, specificity 0.67, sensitivity 0.90, p value 0.03) and fibrinogen (AUC 0.93, specificity 0.73, sensitivity 0.94, p value 0.02) had the best single-biomarker performances. The multi-biomarker model including fibrinogen, CRP, the ratio of fibrinogen to CRP, and the ratio of serum thrombocytes to CRP showed a similar performance (AUC 0.95, specificity 0.91, sensitivity 0.72, p value 0.01). Conclusion: In this study, multiple biomarkers were tested for their diagnostic performance, with CRP and fibrinogen showing the best results regarding the AUC, accuracy, sensitivity, and specificity. It was not possible to further increase the diagnostic accuracy by combining multiple biomarkers using sophisticated statistical methods.