Periprosthetic joint infection (PJI) is a serious complication that can occur after joint arthroplasty, such as hip or knee replacement surgeries. It involves the invasion of the periprosthetic space by pathogens, leading to severe inflammation and often requiring complex medical intervention. PJI is associated with significant morbidity, increased healthcare costs, and a reduced quality of life for patients. This study aims to evaluate the performance of multiple supervised machine learning models in predicting PJI using clinical and demographic data collected from patients who underwent joint arthroplasty. Eight supervised machine learning models—Logistic Regression, Random Forest, XGBoost, Artificial Neural Network (ANN), k-Nearest Neighbors (KNN), AdaBoost, Gaussian Naive Bayes (GNB), and Stochastic Gradient Descent (SGD)—were trained and tested on a dataset of 27,854 patients. Models were evaluated using accuracy, precision, recall, specificity, F1 score, and area under the ROC curve (AUC). Random Forest and XGBoost showed the best overall performance, with high accuracy and balanced metrics across all evaluation criteria. KNN also performed strongly, particularly in minimizing misclassifications. GNB and SGD yielded weaker results, with higher error rates. Random Forest, XGBoost, and KNN are the most promising models for clinical implementation in PJI prediction. Their robust performance may support earlier diagnosis and improved patient outcomes in orthopedic care. This study demonstrates that machine learning models—particularly Random Forest and XGBoost—can accurately predict periprosthetic joint infection (PJI) using structured electronic health record data. By integrating these models into preoperative assessment workflows, clinicians may be able to identify high-risk patients earlier, personalize prophylactic strategies, and reduce infection-related morbidity. The implementation of these predictive tools has the potential to enhance clinical decision-making, improve surgical outcomes, and optimize the use of healthcare resources in orthopedic practice.

Preoperative radiological planning is a key factor in the prediction of implant size and positioning that influences surgical time, the risk of complications, and functional outcomes. We have tested the accuracy of the digital templating performed in our hospital for a sample of 215 patients that underwent total hip arthroplasty. We assessed the accuracy of correctly predicting implant size for the femoral and acetabular components, as well as the stem neck length. We found that our method of templating proved accurate (within one size) in 95.8% of cases for the stem and 94.9% for the cup when using the anteroposterior view only, while the lateral view was accurate in 95.8% of cases for the stem and 97.2% for the cup. Exact prediction of the stem size was obtained in 77.7% of cases using the anteroposterior view and 67.0% of cases on the lateral view, and 73.0% and 74.4% of cases for the cup on the AP and LL views, respectively. Stem neck size was predicted exactly in 75.35% of cases and within one size in 93.49% of cases. We concluded that our method of digital templating using dedicated software is highly effective in accurately predicting implant size.

Large Language Models (LLMs) are increasingly used for rubric-based assessment, yet reliability is limited by instability, bias, and weak diagnostics. We present EvalCouncil, a committee-and-chief framework for rubric-guided grading with auditable traces and a human adjudication baseline. Our objectives are to (i) characterize domain structure in Human–LLM alignment, (ii) assess robustness to concordance tolerance and panel composition, and (iii) derive a domain-adaptive audit policy grounded in dispersion and chief–panel differences. Authentic student responses from two domains–Computer Networks (CNs) and Machine Learning (ML)–are graded by multiple heterogeneous LLM evaluators using identical rubric prompts. A designated chief arbitrator operates within a tolerance band and issues the final grade. We quantify within-panel dispersion via MPAD (mean pairwise absolute deviation), measure chief–panel concordance (e.g., absolute error and bias), and compute Human–LLM deviation. Robustness is examined by sweeping the tolerance and performing leave-one-out perturbations of panel composition. All outputs and reasoning traces are stored in a graph database for full provenance. Human–LLM alignment exhibits systematic domain dependence: ML shows tighter central tendency and shorter upper tails, whereas CN displays broader dispersion with heavier upper tails and larger extreme spreads. Disagreement increases with item difficulty as captured by MPAD, concentrating misalignment on a relatively small subset of items. These patterns are stable to tolerance variation and single-grader removals. The signals support a practical triage policy: accept low-dispersion, small-gap items; apply a brief check to borderline cases; and adjudicate high-dispersion or large-gap items with targeted rubric clarification. EvalCouncil instantiates a committee-and-chief, rubric-guided grading workflow with committee arbitration, a human adjudication baseline, and graph-based auditability in a real classroom deployment. By linking domain-aware dispersion (MPAD), a policy tolerance dial, and chief–panel discrepancy, the study shows how these elements can be combined into a replicable, auditable, and capacity-aware approach for organizing LLM-assisted grading and identifying instability and systematic misalignment, while maintaining pedagogical interpretability.

Objectives: Spondylodiscitis can be caused by various microorganisms and has shown a continuous rise in incidence and mortality. The purpose of our study was to analyze the demographic and laboratory data, as well as comorbidities of patients that were surgically treated for spondylodiscitis in our hospital. The causative pathogens involved in the etiology of spinal infections were also assessed. Methods: The study included 92 patients who underwent clinical, radiological, and microbiological analyses including bacterial isolation. According to their culture results, patients were divided into three groups: negative results (n = 29), positive results with Mycobacterium tuberculosis (M. tb.) (n = 26), and positive results with other pathological agents (n = 37). Results: Patients with M. tb. had a significantly lower body mass index (p = 0.022) and were significantly younger (p = 0.024) than the others. The analysis of the complete blood work showed significant differences between the groups regarding fibrinogen levels (p = 0.023), C-reactive protein (p = 0.009), and erythrocyte sedimentation rates (p = 0.042). Results also showed significant differences (p = 0.023) for patients with diabetes mellitus who were more prone to a tuberculosis etiology for their spondylodiscitis compared with patients without the disease. Conclusions: These findings have important implications for adopting individualized treatment strategies underlining the need for identification of patients at high risk for specific causative pathogens.

Spinal infections in general, and infectious spondylodiscitis in particular, are increasingly diagnosed in the Western world, in recent decades. This rise in incidence is associated with an ageing population and with an increased availability of accurate diagnostic modalities. Even so, due to the non-specific nature of clinical manifestations, and of the implicated blood and serum markers, there is a risk of underdiagnosis or misdiagnosis of the disease in its initial stages. Ionizing radiation methods, such as plain radiography (X-ray) and computed tomography (CT), are also not reliable in the early stages of the diseases, and the golden standard of imagistic diagnosis, magnetic resonance imaging (MRI), is not always available or requested. Still, MRI remains the most reliable method in most cases where there is a need for differential diagnosis with other pathologies, namely Andersson lesions, destructive spondyloarthropathy, erosive osteochondritis, micro-crystalline spondylitis, Modic 1 lesion, Charcot spinal arthropathy, osteoporotic fractures, SAPHO syndrome with spinal involvement, and Schmorl’s nodes. Infectious spondylodiscitis is caused by bacteria, and, less frequently, by fungi. Rare cases of parasitic causes have also been reported in the literature. Infectious spondylodiscitis of bacterial causes may be pyogenic, more frequently caused by Staphylococcus spp. or Streptococcus spp., or granulomatous, usually caused by Mycobacterium tuberculosis complex (MTBC) or from classical brucellosis. In all these cases, therapy may be conservative, with antibiotics, or surgical, when the former fails or in patients with significant spinal instability or other neurological manifestations. There are various surgical approaches, each with its own drawbacks, and usually used according to the preference of the attending physician. Even in cases of surgical treatment, antibiotic administration is prolonged, and it is important for a proper scheme to be selected based on antimicrobial susceptibility testing. However, given that in many cases, the causative agent cannot be identified, empirical treatment must be initiated. Finally, newer approaches, including the incorporation of antimicrobial substances, may offer better solutions for improving treatment and rehabilitation outcomes.

We present the case of a 66 year-old male patient who developed severe postoperative thrombocytopenia after revision total hip arthroplasty. The patient underwent surgery in a dedicated orthopedics hospital and was initially managed in the intensive care unit. Upon the development of thrombocytopenia, he was referred to a dedicated hematology clinic for investigation and advanced management. A thorough diagnostic algorithm was employed in order to rule out the main causes of thrombocytopenia. By exclusion, we diagnosed the patient as suffering from a rare and severe form of postoperative thrombocytopenia through an immune mechanism. Although postoperative thrombocytopenia is relatively frequent but transitory and no treatment is required, this condition was refractory to corticosteroids and substitution therapy; however, it quickly responded to treatment with thrombopoietin receptor agonists. The patient recovered and was successfully discharged with normal platelet values. While rare occurrences, alternative causes of thrombocytopenia such as infection, drug-induced, or immune should be considered in patients developing postoperative thrombocytopenia.