Search Results (163)

Background: Cervicogenic headache (CEH) is a secondary headache disorder originating from dysfunction in the cervical spine. In addition to pain, individuals with CEH frequently experience disturbances in postural control and sensorimotor integration, which may compromise functional capacity and quality of life. Conventional clinical assessments typically focus on pain intensity and cervical range of motion; however, these measures often fail to capture the multifactorial mechanisms underlying balance impairments in this population. Machine learning (ML) methods offer the ability to integrate multidimensional clinical data and may provide a more comprehensive approach for identifying patterns of postural stability and the factors influencing balance regulation in CEH. Methods: A secondary analysis was conducted using baseline data pooled from three registered randomized controlled trials, comprising 68 independent participants diagnosed by a neurologist according to the International Classification of Headache Disorders, 3rd edition (ICHD-3). Postural Stability Class served as the primary outcome and was derived from quantitative stability scores categorized as High, Moderate, or Low. Predictor variables included demographic characteristics (age, gender), clinical measures (pain intensity, headache frequency, symptom duration, cervical range of motion), and sensorimotor parameters (center-of-pressure sway and gaze accuracy). Five machine learning algorithms—Random Forest, XGBoost, Support Vector Machine, Logistic Regression, and Gradient Boosting—were trained and evaluated using 10-fold cross-validation with procedures implemented to reduce overfitting. Results: The Gradient Boosting classifier demonstrated the best performance, achieving an accuracy of 0.857 and an F1 score of 0.857, with a cross-validated accuracy of 0.802 ± 0.063. Random Forest and XGBoost achieved accuracies of 0.786. Feature importance analysis identified center-of-pressure sway and pain intensity as the most influential predictors of stability classification, followed by cervical flexion range of motion and gaze accuracy. Demographic variables showed minimal contribution to model performance. Conclusions: Machine learning models were able to distinguish different levels of postural stability in individuals with CEH. The findings highlight the central role of pain and sensorimotor control in balance regulation and suggest that predictive analytics may support precision physiotherapy by enabling rehabilitation strategies tailored to individual sensorimotor profiles. Full article

As global populations grow and technology advances, daily life is increasingly shaped by digital systems such as computers and smart devices. However, prolonged device use has contributed to increasing physical and mental health concerns, particularly those associated with poor sitting posture. Posture-related strain is frequently overlooked and contributes to musculoskeletal discomfort, including back, neck, shoulder, and wrist pain, and may also be associated with sleep disturbances and elevated stress levels. To the best of our knowledge and based on the existing literature, this is the first study to introduce a machine learning-based framework for advanced muscle strain severity classification using Internet of Things (IoT) devices that integrates posture monitoring and muscle strain detection into a unified low-cost framework ($23 hardware cost). The primary objective of this work is accurate classification of muscle strain severity, while real-time alerts serve as a secondary ergonomic feedback mechanism. Specifically, this study makes four major contributions. First, we created a novel dataset through real-time acquisition of electromyography (EMG) and posture signals from participants in hospital and industrial environments, capturing diverse muscle strain patterns validated against clinical assessment procedures. Second, we designed a two-part hardware architecture consisting of posture detection (PD) and strain detection (SD) modules using a NodeMCU ESP8266, HC-SR04 ultrasonic sensor, EMG sensor, and buzzer for real-time physiological monitoring, incorporating EMG-specific preprocessing including band-pass filtering, rectification, and RMS smoothing. Third, we proposed and evaluated a hybrid machine learning framework integrating Vision Transformer (ViT) and XGBoost to classify strain severity into three study-specific categories: baseline (EMG RMS < 40 µV), compensatory strain (40–59 µV), and overload (≥60 µV). These categories were used as reproducible severity proxies for machine learning annotation and should not be interpreted as universal biomarkers of structural tissue damage. Finally, the proposed framework achieved a classification accuracy of 99.0% (95% CI: 98.5–99.5%) with an inference latency of 15.2 ms. Full article

Objectives: The diagnosis of pediatric acute appendicitis remains challenging due to clinical findings that overlap with nonspecific abdominal pain (NSAP). In this study, the value of fibrinogen in the diagnosis of pediatric acute appendicitis and in the classification of disease severity was investigated. Methods: In a single-center, retrospective cohort study, 145 patients aged 1 month to 18 years who underwent contrast-enhanced abdominal computed tomography were divided into three groups: NSAP (n = 62), uncomplicated appendicitis (n = 44), and complicated appendicitis (n = 39). Hemogram parameters, CRP, procalcitonin, albumin, and fibrinogen levels were compared. Diagnostic performance was assessed using ROC analysis, and independent predictors were evaluated via multivariate logistic regression. Results: Fibrinogen levels showed a gradual and statistically significant increase from NSAP to uncomplicated appendicitis and then to complicated appendicitis (p < 0.001 for all pairwise comparisons). In distinguishing appendicitis from NSAP, fibrinogen achieved the highest diagnostic accuracy among the biomarkers examined (AUC = 0.95); CRP, WBC, ANC, and NLR demonstrated lower discriminatory performance. In multivariate logistic regression analysis, fibrinogen was validated as an independent predictor of appendicitis (p < 0.001). Conclusions: Fibrinogen demonstrates high discriminatory performance in the diagnosis of pediatric acute appendicitis and shows a graded relationship with disease severity. These findings suggest that fibrinogen may be a promising biomarker for the evaluation of pediatric acute appendicitis. However, larger prospective multicenter studies are required before its routine integration into diagnostic algorithms can be recommended. Full article

[¹⁸F]-PSMA PET/CT is a high-impact modality for the staging and restaging of prostate cancer, but its wide anatomic coverage and tracer biology generate frequent incidental findings on both PET and the accompanying low-dose CT (LDCT). This narrative review is restricted in scope to fluorine-18 PSMA tracers because tracer-specific biodistribution and pitfall profiles shape what is perceived as incidentaloma: how confidently lesions can be categorized, and how often borderline findings trigger downstream testing, particularly for skeletal foci with [¹⁸F]-PSMA-1007. Specifically, [¹⁸F]-PSMA-1007 shows substantially higher rates of focal unspecific bone uptake than [⁶⁸Ga]-PSMA-11—reported in multicenter studies as affecting up to 40–50% of patients—which directly inflates the pool of potential incidentalomas and creates a tracer-specific false-positive problem with no parallel in gallium-68 practice. Additionally, [¹⁸F]-DCFPyL has different urinary clearance kinetics that affect bladder and ureteral uptake patterns, altering what qualifies as physiologic versus incidental in the pelvis. These differences mean that the threshold for Category B versus C classification—and the appropriate cascade-resistant language—must be tuned to the specific tracer in use. A framework built on [⁶⁸Ga]-PSMA-11 data would systematically underestimate bone pitfall frequency in [¹⁸F]-PSMA-1007 practice and could therefore paradoxically increase rather than reduce cascades if applied uncritically across tracers. These biodistribution differences have direct and concrete consequences for reporting behaviour and downstream management. In [¹⁸F]-PSMA-1007 practice, a focal bone uptake without a CT correlate in a mechanically plausible location—such as an anterior rib or vertebral endplate—should trigger Category B language in the report conclusion: the finding is documented in the body with explicit safety netting (“most consistent with unspecific uptake; no routine workup unless interval growth, new pain, or aggressive CT morphology”), and no referral to bone scintigraphy or MRI is generated. Without tracer-specific awareness, the same finding would typically prompt a reflex bone scan or whole-body MRI referral, delaying definitive prostate cancer management by weeks and adding imaging costs without diagnostic gain. By contrast, in [⁶⁸Ga]-PSMA-11 practice, an equivalent focal bone uptake without a CT correlate carries a higher prior probability of true metastatic disease given the lower background rate of unspecific uptake and should more often be reported at Category B with a lower threshold for escalation or more cautious language. For [¹⁸F]-DCFPyL, the higher urinary activity in the pelvis means that ureteral segments can mimic lymph node disease; recognizing this as a physiologic variant (Category C) rather than an equivocal nodal finding (Category B) avoids unnecessary pelvic MRI referrals that would otherwise be triggered by an uncontextualized report. In practical terms, the tracer-specific calibration of the overlay therefore changes not only the category assigned but also the specific safety-netting language and the escalation trigger, which directly modifies the downstream management pathway for each affected finding type. The scanned population—predominantly older men with a high prevalence of degenerative, inflammatory, and vascular abnormalities—creates substantial background noise that can drive low-value diagnostic cascades if incidental findings are communicated without actionability context. We integrate society-endorsed frameworks (EANM/SNMMI procedure guideline 2.0; E-PSMA; PSMA-RADS; and PROMISE/miTNM with miPSMA score) and propose a cascade-aware overlay for incidental findings that can be appended to existing PSMA reporting standards rather than replacing them. The A/B/C actionability overlay is a structured expert-consensus framework informed by existing evidence-based guidelines for specific finding types and by tracer-specific cohort data; it has not yet been prospectively validated as a standalone tool, and its current level of evidence is therefore analogous to a structured expert recommendation rather than an evidence-based clinical guideline. We operationalize a three-tier actionability scheme across PET- and CT-dominant findings, provide cascade-resistant language for conclusions, and clarify why SUVmax-only “probability scales” for lymph nodes are not recommended in routine reports. Three practical tables summarize PET incidental findings, lymph node reporting frameworks, and LDCT incidental findings, and two structured report templates are provided (concise and extended), with the extended version explicitly labelling actionability tiers and escalation triggers. Finally, we outline concrete AI use cases for standardization and triage while emphasizing governance to avoid the amplification of false positives and paradoxical growth of cascades. Full article

Background: Despite stable fixation, aseptic tibial shaft nonunion represents a severe orthopedic complication. Teriparatide and adipose-derived stem-cell augmentation have been proposed as biological supports, but comparative clinical evidence remains limited. This study explored whether adding adjuvant therapies to reamed intramedullary nailing was associated with faster healing than nailing alone. Methods: We retrospectively reviewed 43 adults with aseptic tibial shaft nonunion treated at three level I trauma centers between 2017 and 2020. Patients underwent reamed intramedullary nailing alone (n = 15), nailing plus teriparatide (n = 15), or nailing plus adipose-derived stem-cell augmentation (n = 13). Group allocation was nonrandom and based on contraindications and patient acceptance; results were therefore interpreted as exploratory. Outcomes included time to tricortical radiographic healing, pain, radiographic healing scores over time, complications, ASAMI classification, and SF-12. Results: Baseline demographic and fracture characteristics were comparable across groups. Time to tricortical radiographic healing was shorter in the teriparatide group (87.46 ± 6.34 days) and the adipose-derived stem-cell group (86.41 ± 5.67 days) than in the nailing-alone group (99.71 ± 4.29 days; p = 0.034). Pain, complication rates, ASAMI outcomes, and quality-of-life recovery did not differ significantly among groups at final follow-up. Conclusions: In this exploratory multicenter retrospective cohort, teriparatide and adipose-derived stem-cell augmentation were associated with shorter radiographic healing time after reamed intramedullary nailing for aseptic tibial shaft nonunion, but not with superior long-term functional outcomes. Because no comparator group treated with standard graft-based biological augmentation was included, the findings should be interpreted cautiously. Larger prospective studies or randomized controlled trials comparing these strategies with established graft-based approaches are needed to validate the present data. Full article

Endometriosis (EM) is a chronic, estrogen-dependent inflammatory disorder affecting approximately 6–10% of women of reproductive age in the general population and remains a major cause of chronic pelvic pain and infertility. High recurrence rates and enduring symptoms despite current treatments underscore the need for a more thorough understanding of its intricate biology. There is growing evidence that the interaction among oxidative stress (OS), microbiome dysbiosis, and epigenetic dysregulation contributes to immunological activation, hormonal imbalance, and the persistence of ectopic lesions. Important disease mechanisms, such as progesterone resistance, inflammatory signaling, and aberrant cellular proliferation, are influenced by epigenetic changes, which include aberrant DNA methylation, histone modifications, and dysregulated non-coding RNAs. Simultaneously, high levels of reactive oxygen species (ROS) reinforce lesion survival and chronic inflammation by promoting angiogenesis, fibrosis, and tissue damage. Changes in the microbiome also affect immunological responses, oxidative balance, estrogen metabolism, and epigenetic control, indicating the existence of interrelated pathogenic loops. This narrative review presents an integrated mechanistic framework for endometriosis, summarizing the available data that connect these pathways. Furthermore, the growing implications of non-invasive biomarkers and precision medicine techniques highlight the potential for improved diagnosis, disease classification, and targeted treatment approaches. Full article

Background/Objectives: This paper aims to design an explainable and accurate ML framework to support the automatic classification of Carpal Tunnel Syndrome (CTS) severity from structured patient data. Methods: For the experiment, an open-source dataset of 1037 samples was used. Following stratified partitioning, 305 samples were held out as the test set; the remaining training set (n = 732) was augmented to 1216 balanced samples via ADASYN, yielding an 80/20 train/test ratio relative to the final dataset (n = 1521). In order to solve the problem of imbalance associated with CTS cases of moderate and severe severity, the Adaptive Synthetic Sampling (ADASYN) technique was employed. The model’s predictive capacity was increased by means of feature engineering methods, such as polynomial transformations and clinically relevant interactions. Specifically, four ensemble learning models (XGBoost, Random Forest, LightGBM, and CatBoost) were optimized and ensembled with the use of a stacking approach with a base algorithm of LightGBM. The explainability of the model was ensured through SHAP and LIME analysis. Results: As a result, the stacking ensemble was able to reach a test accuracy of 91.15%, an F1-score of 91.13%, and an ROC-AUC of 0.9708. The proposed ensemble performed superiorly compared to any other individual algorithm while having stable performance across all severity categories. Conclusions: Through the explainability analysis, it was observed that such a classification model relies on important clinically relevant predictors, including cross-sectional area (CSA), duration of symptoms, pain level measured by the numeric rating scale of pain (NRS), and palmar bowing (PB). Full article

Background: Rheumatic heart disease (RHD) remains a significant public health problem in low- and middle-income countries. Beyond its clinical consequences, RHD adversely affects the health-related quality of life (HRQoL) of affected children and adolescents, their families, and healthcare systems. Addressing the HRQoL of children and adolescents with RHD will contribute to strengthening patient-centered care and policy development. Objective: To determine the health-related quality of life of children and adolescents with rheumatic heart disease attending follow-up at the pediatric cardiology clinic of Moi Teaching and Referral Hospital (MTRH), Kenya. Methods: This was a hospital-based cross-sectional study conducted between January and July 2024. A total of 171 children and adolescents aged 5–18 years were consecutively enrolled while attending follow-up at the pediatric cardiology clinic of MTRH. The EuroQol EQ-5D-Y and EQ-5D-L questionnaires were used to assess HRQoL across five domains: mobility, self-care, usual activities, pain/discomfort, and anxiety/depression. Overall HRQoL was evaluated using the EQ visual analog scale (EQ-VAS) and categorized as optimal (≥80%), suboptimal (70–79%), or poor (≤70%). Results: Overall HRQoL was optimal in 70.8% (n = 121) of participants, suboptimal in 8.2% (n = 14), and poor in 21.1% (n = 36). Impaired HRQoL was significantly associated with poor self-care (95% CI: 0.066–0.853; p = 0.028), anxiety/depression (95% CI: 0.111–0.678; p = 0.005), pain/discomfort (95% CI: 0.142–0.758; p = 0.009) and missing more than five school days (95% CI: 0.109–0.584; p = 0.001). Caregiver characteristics (age, education level, and income), surgical correction, RHD-related hospital admissions, comorbidities, and Ross classification were not significantly associated with HRQoL. Conclusion: Health-related quality of life among children and adolescents with RHD was most adversely affected in the mental health and mobility domains. Routine assessment of HRQoL should be incorporated into the clinical care of children and adolescents with RHD to reduce disease-related morbidity and support holistic management. Full article

Background and Objectives: Diabetes mellitus (DM) is a major global health concern, with diabetes-related foot disease (DFD) representing one of its most severe complications, often resulting in chronic infection, osteomyelitis, and limb amputation. Conventional therapies frequently fail in refractory cases, necessitating novel adjunctive strategies. Ozone therapy (OT) possesses antimicrobial, immunomodulatory, and oxygen-enhancing properties, while negative pressure wound therapy (NPWT) facilitates granulation, exudate removal, and tissue perfusion. This study explored the combined efficacy of OT and NPWT in advanced DFD. Materials and Methods: An exploratory, retrospective, observational cohort study was conducted at a specialized wound care center in Gdańsk, Poland, between 2019 and 2022. The study included 30 patients (n = 30) with refractory DFD involving both soft tissue and bone infection who had not responded to previous conventional treatment. The analyzed treatment approach consisted of surgical debridement, application of topical ozonated preparations, and (NPWT) with instillation of ozonated saline administered over a six-week period. Clinical outcomes included wound healing assessed using the Wagner classification and wound volume reduction, pain intensity measured using the Numeric Rating Scale (NRS), inflammatory biomarkers (C-reactive protein [CRP] and procalcitonin [PCT]), and microbiological characteristics of wound cultures. Statistical analyses were performed using the Wilcoxon signed-rank test and the chi-square test, and regression modeling was applied to identify potential predictors of therapeutic response. Statistical significance was defined as p < 0.05. Results: By week six, 100% of ulcers improved to Wagner stage ≤1, with 26.7% achieving stage 0. Median wound volume decreased from 5.5 cm³ to 0 cm³ (p < 0.001). Pain scores declined from 7.2 ± 0.96 points to 0.2 ± 0.5 points (p < 0.001). CRP and PCT levels decreased significantly (p < 0.001), and microbiological clearance was observed in all cases. Higher body mass index (BMI) was associated with poorer pain reduction. Conclusions: The combination of standard wound care with OT and NPWT was associated with clinically relevant improvements in wound healing, infection control, systemic inflammation, and pain reduction in patients with refractory DFD. Although limited by a non-controlled design and small cohort size, these findings support further randomized controlled trials to define the role of this combined approach in integrated diabetic foot care. Full article

Background/Objectives: Platelet-rich plasma (PRP) is an autologous blood-derived biologic enriched in platelets and bioactive mediators. In urology and sexual medicine, PRP has been promoted for erectile dysfunction (ED) and a growing range of urogenital disorders on the premise that it may support angiogenesis, neuroregeneration, immune modulation, and tissue remodeling. However, clinical uptake has outpaced high-quality evidence, while heterogeneity in PRP preparation, characterization, and delivery limits interpretability and reproducibility. This structured narrative review aims to critically integrate mechanistic, preclinical, and clinical evidence regarding PRP use in ED, Peyronie’s disease (PD), stress urinary incontinence (SUI), interstitial cystitis/bladder pain syndrome (IC/BPS), and selected emerging indications. We further aim to identify sources of heterogeneity and propose an actionable minimum reporting framework (PRP-Uro Checklist) to guide future research. Methods: A structured search of PubMed/MEDLINE was conducted for studies published between 2021 and 2025. The relevant literature on PRP use in ED, PD, SUI, IC/BPS, and related indications was included for critical narrative synthesis. Emphasis was placed on PRP classification and preparation variables, outcome measure validity, and sources of heterogeneity across studies. Results: Mechanistic and preclinical evidence supports PRP’s potential to modulate nerve repair, angiogenesis, extracellular matrix remodeling, and immune polarization through a complex secretome of growth factors, cytokines, and extracellular vesicles (EVs). Clinical evidence suggests that intracavernosal PRP may improve erectile function in selected populations, but effect size, durability, and superiority over placebo remain uncertain due to small trials, substantial placebo effects, short follow-up, and incomplete biologic characterization. Evidence for PRP in PD, SUI, and IC/BPS remains preliminary and is derived largely from small cohorts, proof-of-concept studies, or uncontrolled designs, although early findings suggest potential symptom benefit and acceptable short-term tolerability. Across indications, inconsistent PRP reporting, particularly the absence of absolute platelet dose, leukocyte quantification, activation method, and standardized treatment protocols, represents a major barrier to reproducibility and evidence synthesis. Conclusions: PRP is biologically plausible and appears broadly safe, but its role in urology and sexual medicine remains investigational and is not yet supported by guideline-level evidence. To enhance reproducibility and interpretation, we propose a Minimum PRP Reporting Checklist for Urology and Sexual Medicine Trials (PRP-Uro Checklist). Future progress requires rigorous standardized reporting, indication-specific biologic characterization, rigorously designed sham-controlled trials, clinically meaningful endpoints, and longer-term follow-up. Full article

Background: Women with endometriosis frequently experience mobility limitations that affect daily functioning. A specific tool to assess these restrictions would help clinicians to better understand patients’ functional challenges, facilitating more effective communication and shared decision making. Addressing this gap is essential for strengthening patient–professional dialogue and improving individualized care. Objective: To develop the new instrument MobEndo and to perform initial psychometric testing of the tool. Methods: The initial domains and items were generated through semi-structured interviews with patients and based on experts’ advice. Guided by the International Classification of Functioning, Disability, and Health (ICF) framework, exploratory factor analysis was conducted on data from patients diagnosed with endometriosis. Internal consistency was assessed using Cronbach’s alpha, considering values ≥ 0.70 as acceptable. Test–retest reliability was examined using intraclass correlation coefficients (ICCs), and ICC values were judged as excellent if >0.75. Construct validity was evaluated through concurrent, discriminant, and known-groups validity. For the known-groups validity hypothesis, participants were categorized by baseline pain levels. Results: The final questionnaire included 18 items, developed from responses from 301 women (mean age 38.96 ± 6.85). Factor analysis revealed two components—transitioning between body positions and performing movements requiring stabilization and executing load-bearing tasks involving the upper limbs—with the model explaining 71.78% of the total variance. Reliability was excellent, with a Cronbach’s alpha of 0.977. The ICC for the total score was 0.976 (95% CI 0.949–0.988), with similarly high values for each component. Concurrent validity correlations were significant, while discriminant validity showed no relevant associations. Known-groups analyses showed clear differences across pain-level groups. Conclusions: The questionnaire is a valid and reliable tool for capturing women’s perceived mobility limitations in endometriosis. Full article

Low back pain is common in road cyclists and has been associated with prolonged lumbar flexion during cycling. The flexion–relaxation (FR) phenomenon reflects neuromuscular control of the lumbar spine, but its response to prolonged cycling under physiologically individualized conditions remains unclear. Thirty-one pain-free road cyclists completed a laboratory protocol in which exercise intensity was prescribed at 50% of the range between the first and second ventilatory thresholds (VT1 and VT2). Surface electromyography (sEMG) was recorded during trunk flexion extension tasks performed before and after a 60 min cycling trial. FR responses were characterized at both the individual and group levels using the flexion–relaxation ratio (FRR), descriptive classification of altered patterns, and exploratory estimates of mean change, effect size, and 95% confidence intervals. Four cyclists (12.9%; 95% CI: 3.6–29.8%) exhibited altered FR responses: three showed persistent alterations already present before cycling, and one showed an exercise-associated alteration. Group-level changes were minimal (effect sizes: −0.20 to 0.04). These findings suggest that prolonged cycling under controlled physiological load primarily reveals heterogeneous subject-specific neuromuscular patterns rather than a uniform average response. FR assessment using sEMG may therefore be useful as a complementary tool for identifying individual neuromuscular behavior in pain-free cyclists. Full article

Objective: The objective of this study was to choose the optimal anesthesia method for gastric cancer patients undergoing surgery with lymph node dissection. Materials and Methods: The study included 53 patients with stage T1-4aN0-3M0 gastric cancer, who underwent radical surgery with xenon and dexmedetomidine (DMM) anesthesia in combination with epidural analgesia (main group, 27 patients) or with sevorflurane anesthesia in combination with epidural analgesia (comparison group, 26 patients). All patients underwent monitoring of hemodynamic parameters, blood coagulation system, thromboelastometry, and inflammation and metabolic parameters (interleukins, hormones and glucose levels), with an assessment of complications according to the Clavien-Dindo classification and the intensity of postoperative pain. Results: Awakening and extubation times, narcotic analgesic consumption, and Numeric Rating Scale pain scores were lower in the xenon + DMM group than in the sevoflurane group (p < 0.05). The overall number of patients experiencing complications did not differ significantly between anesthesia types; however, significant differences were found in the total number of complications (p = 0.003), the number of complications according to Clavien-Dindo I (p = 0.043) and II (p = 0.019), and the incidence of postoperative nausea and vomiting (p = 0.042). Conclusions: The BIS monitoring data obtained showed a sufficient level of anesthesia depth during surgery in both groups; however, post-anesthesia depression persisted longer in patients in sevoflurane group. Mathematical models for predicting Clavien-Dindo IIIb-V complications and severe postoperative pain syndrome are characterized by high sensitivity and specificity. They include simple clinical and laboratory parameters as well as type of anesthesia as predictors. The limitations of predictive models are also discussed in the article. Full article

Horses presenting with temporomandibular joint (TMJ) dysfunctions are often clinically evaluated for TMJ osteoarthritis (OA). Due to the unique characteristic of TMJ-related pain, the clinical diagnosis of equine TMJ OA is challenging; however, it may be supported by computer-aided tools incorporating biomarker data. This study aims to evaluate a machine learning-based approach to address a binary classification distinguishing healthy TMJs from TMJ OA. Among 50 equine cadaver heads, 82 TMJs were included and annotated as healthy or OA based on histological and computed tomography (CT) findings. For each TMJ, nine CT findings were assessed, and synovial fluid was collected for the evaluation of twelve biomarkers. Using a biomarker dataset, correlations among biomarkers were calculated and supported with a mixed-effects logistic regression model. Using a combined dataset, twelve machine learning models, incorporating two feature selection methods and six classification algorithms, were evaluated. Specific biomarker levels showed predominately positive correlations with TMJ OA, age, and with each other; however, only age had a significant effect on OA assignment in the mixed model. The best-performing machine learning model achieved an accuracy of 0.82 and an area under the curve (AUC) of 0.85 for binary TMJ classification. The proposed classification model outperforms conventional diagnostic methods and may therefore be considered beneficial in aiding the diagnosis of equine TMJ OA. Full article

Background/Objectives: Childhood-onset Sjögren disease (cSjD) is a rare autoimmune disorder with heterogeneous manifestations and ongoing diagnostic challenges, as there are no validated paediatric criteria. Our study aims to characterise the clinical, laboratory, and imaging features of children diagnosed with cSjD at a single Romanian paediatric rheumatology centre between 2015 and 2025 and contextualise these findings within the most recent literature. Methods: A retrospective review of 15 consecutive cSjD patients was conducted, including clinical features, autoantibodies, imaging, biopsy findings, treatment, and outcomes. Results: Our cohort showed a significant female predominance (80%) and a broad age range at disease onset (3–15 years). Extraglandular manifestations were more common at presentation than glandular phenotypes (53.3% vs. 40%). Lupus-like extraglandular presentations frequently led to initial misdiagnosis as childhood-onset systemic lupus erythematosus (SLE) in our cohort. Sicca symptoms were present at diagnosis in only 3 of 15 patients (20%) and developed later during follow-up in an additional 4 patients (26.7%). Notably, the cohort included novel findings, such as an unprecedented presentation with acute exudative pericarditis complicated by cardiac tamponade. Anti-SSA antibodies and salivary gland ultrasound abnormalities were highly prevalent (86.7% and 100%, respectively). Anti-SSB antibodies were detected in seven patients (46.7%), with titres showing more variability than those of anti-SSA, ranging from just above the positivity threshold to mildly elevated levels. The association with macro-creatine kinase type I was another distinctive feature of this series. Chronic musculoskeletal pain and dryness were our patients’ most frequently reported symptoms at the last assessment, affecting up to 5/15 (33.3%) in each domain. One patient showed irreversible ocular damage during our study. Conclusions: Extraglandular presentations of cSjD are highly heterogeneous and diagnostically challenging, often occurring without glandular symptoms. Lupus-like systemic features—including facial vasculitic purpura, with or without arthralgia, and occasional pericarditis, as observed in our cohort—may contribute to frequent initial diagnostic misattribution to SLE. Early salivary gland ultrasonography, targeted autoantibody testing, and selective biopsy are essential for timely diagnosis, underscoring the urgent need for paediatric-specific validated classification criteria. Full article