Search Results (10,239)

Background: Thymic epithelial tumors (TETs) are rare mediastinal malignancies whose prognosis is largely determined by histology. Current predictive models rely on clinical variables and subjective imaging interpretation, with unsatisfied performance. Non-invasive pre-treatment risk stratification could guide surgical planning and perioperative management in patients with TETs. The role of fluorine-18 (¹⁸F) fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (CT) in identifying aggressive disease is increasingly recognized. In this bicentric study, we aimed to evaluate a machine learning-based radiomics model using PET and CT images to differentiate between low-risk and high-risk TETs. Methods: Seventy-five patients who underwent PET/CT to evaluate the suspected anterior mediastinal mass and histopathologically diagnosed with TETs were included. On PET/CT images, the tumor was manually segmented by two experienced clinicians. First-order, shape, and texture features were extracted using the PyRadiomics library, resulting in 200 radiomics features (186 intensity/texture features and 14 shape features). In addition, rPET (i.e., tumor SUVmax/Liver SUVmax) parameter was included, yielding a grand total of 201 features. The feature set was reduced to 20 variables using ANOVA, with both selection and model evaluation performed via stratified 5-fold cross-validation. Results: The proposed approach achieved an average balanced accuracy of 0.58 ± 0.07 and an average AUC of 0.71 ± 0.04. Average sensitivity and specificity were 0.48 and 0.68, respectively. The model obtained an average Gmean of 0.57, indicating balanced and stable classification performance. Conclusions: Our ML models trained on PET/CT radiomic features showed moderate discriminatory performance for TET risk stratification. Full article

Background/Objectives: Dysphagia is common in tracheostomized patients with traumatic brain injury (TBI) and may be influenced by airway pathology and tracheostomy-related factors. This study investigated whether tracheostomy cannula type is independently associated with swallowing function and pharyngeal residue after accounting for airway stenosis and clinical variables. Methods: This retrospective observational study included 80 tracheostomized TBI patients using a speaking valve. Participants were grouped according to cannula type (non-fenestrated vs. fenestrated). Swallowing function was evaluated using Fiberoptic Endoscopic Evaluation of Swallowing (FEES), and pharyngeal residue severity was assessed using the Yale Pharyngeal Residue Severity Rating Scale (YPRSRS). Airway stenosis severity was graded using the Cotton–Meyer classification. Multivariable ordinal logistic regression analyses were performed to identify independent predictors of pharyngeal residue. Results: Higher pharyngeal residue scores were observed in the fenestrated cannula group under selected conditions, particularly for 5 mL liquid (p = 0.039) and 5 mL semi-solid boluses (p = 0.004) in the vallecular region, and for 5 mL semi-solid boluses in the pyriform sinuses (p < 0.001). Airway stenosis grade was strongly associated with increased pharyngeal residue and reduced SpO₂ levels (p < 0.001). In multivariable analyses, airway stenosis emerged as the factor most consistently associated with pharyngeal residue severity (e.g., OR = 4.909, 95% CI: 1.646–14.646, p = 0.004), whereas cannula type was not independently associated with most outcomes. Condition-specific associations were identified between fenestrated cannula use and pharyngeal residue in two models (vallecular residue for 5 mL semi-solid: OR = 0.354, 95% CI: 0.143–0.876, p = 0.025; pyriform sinus residue for 10 mL liquid: OR = 0.190, 95% CI: 0.073–0.495, p = 0.001); however, the direction of these associations differed from unadjusted comparisons, indicating prominent confounding by stenosis severity. Conclusions: FEES-estimated airway stenosis appeared to be the factor most consistently associated with pharyngeal residue severity in tracheostomized TBI patients, whereas the effect of cannula type appeared to be limited. Comprehensive airway assessment may therefore be important in dysphagia management. Full article

Background/Objectives: Prediabetes significantly increases the risk of type 2 diabetes and related complications. Limited data exist for prediabetes among minority groups in Israel, particularly Bedouins. In the Negev region, Jewish and Bedouin populations differ markedly in culture and socioeconomic status. This study aimed to identify gender- and ethnicity-specific predictors of prediabetes. Methods: This retrospective, population-based observational exploratory study used data from 28,754 adults aged 20–65 years insured by Clalit Health Services in Southern Israel (2010–2020). Individuals with prediabetes were matched 1:1 with controls by age, gender, ethnicity, and year of diagnosis. Multivariate logistic regression models stratified by gender and ethnicity identified independent predictors. Results: Prediabetes was identified at significantly younger ages among Bedouins than Jews (6.8 years in men, 11.3 in women). The strongest predictor across all subgroups was metabolic syndrome (OR 2.0–4.0). Gestational diabetes was a major risk factor in women, particularly Jewish (OR 3.6). Cardiovascular disease and the use of statins or thiazide diuretics were independently associated with increased odds of prediabetes. Triglyceride-to-HDL cholesterol ratio was consistently elevated among prediabetes patients. Conclusions: Metabolic and medication-related factors contribute significantly to prediabetes-associated risk, with distinct gender and ethnic patterns. Culturally tailored early interventions and individualized risk profiling may enhance diabetes prevention in Southern Israel. Full article

Background/Objectives: Artificial intelligence (AI) offers a promising approach for detecting and classifying symptom severity in patients with Parkinson’s disease (PD). The objective was to provide an overview of AI methods performance used for this classification through a systematic review and meta-analysis conducted in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Methods: The Google Scholar, IEEE Xplore, PubMed/MedLine, and ScienceDirect databases were searched for the period 2015–2025. The studies included were original, peer-reviewed studies written in English that addressed an AI method based on machine learning (ML) or deep learning (DL) for the classification of PD patients. The dataset used had to be “Gait in Parkinson’s Disease,” in which the severity of disease symptoms was assessed using the Hoehn and Yahr (H&Y) scale. Studies had to report at least one of the five performance metrics: accuracy, sensitivity, specificity, precision, and F1 score. Two reviewers independently selected articles, assessed the risk of bias using PROBAST (Prediction Model Study Risk of Bias Assessment Tool), and extracted data. The logit-transformed values were pooled separately by performance metrics and by severity level using a random-effects model. Cochran’s Q test, the I² statistic, and inter-study variability (τ²), computed using the generalized inverse variance method with the restricted maximum likelihood model, were used to assess heterogeneity. Forest plots with 95% confidence intervals were used to present the results. Possible causes of heterogeneity were explored using a subgroup analysis (ML vs. DL) and a sensitivity analysis. Finally, publication bias (Egger’s test) and the certainty of the evidence (using GRADE—Grading of Recommendations Assessment, Development, and Evaluation) were assessed to verify the generalizability of the results. Results: Among the 257 unique records, 12 studies were included. The methods demonstrated very high overall performance (>92%): accuracy (96.4%, 95% CI: 95.9–96.9%), specificity (97.7%, 95% CI: 97.3–98.1%), sensitivity (94.0%, 95% CI: 92.7–95.2%), precision (93.4%, 95% CI: 92.0–94.6%), F1 score (92.1%, 95% CI: 90.6–93.4%). Accuracy, specificity, and precision were high for all H&Y levels. However, the more advanced the symptoms, the lower the sensitivity (97.3% for H&Y0 vs. 92.1% for H&Y3). ML models achieved the best results for classifying healthy patients (H&Y0: 95.7% to 98.2%), while DL approaches performed better for classifying higher severity levels (>92%). Heterogeneity and inter-study variability were moderate (I²: 40–50% and τ²: 0.3–0.4) for precision and F1 score, and high (I² > 90% and τ² > 0.6) for accuracy, specificity, and sensitivity. The GRADE analysis revealed low-quality evidence for precision and F1 score and very-low quality for accuracy, specificity, and sensitivity. Conclusions: Thus, AI-based wearable gait assessment devices show great promise in terms of aiding clinical decision-making and treatment personalization. However, further research using a rigorous methodology (PROBAST) is needed to ensure the generalizability of the results and the clinical viability of the proposed solutions. Full article

Background/Objectives: The accuracy and reliability of automated clinical analyzers are fundamental to patient safety and effective medical decision-making. Traditional quality control (QC) methods, which rely on periodic manual calibration and reactive maintenance, are inherently limited by high latency and labor costs; furthermore, they fail to provide continuous, real-time monitoring. This paper introduces a novel hybrid ensemble learning framework for the automated quality inspection of medical devices through the analysis of time-series reaction curves. Methods: Our system integrates three heterogeneous anomaly detection paradigms: an Enhanced Dynamic Time Warping (DTW) detector for robust non-linear pattern matching, a Shape Template Matching (STM) detector that mimics expert clinical logic by analyzing morphological features in a normalized shape space, and a specialized Time-series Variational Autoencoder (TimeVAE) for deep representation learning. The outputs of these detectors are fused using a weighted ensemble strategy, which is specifically designed to prioritize the minimization of false negatives—a critical requirement in medical diagnostics. Results: We evaluate our framework on a comprehensive, multi-center real-world dataset comprising seven distinct biochemical assays. Experimental results demonstrate that our proposed method achieves superior performance, attaining a $0\%$ false negative rate on CRE and DBIL assays and outperforming all baseline methods on the other five datasets. An ablation study confirms the model’s robustness even with limited training data, and a comparative analysis against eight state-of-the-art baseline methods further validates the effectiveness of our domain-optimized ensemble approach. Conclusions: The system provides a robust, interpretable, and highly automated solution for transitioning from reactive maintenance to proactive, real-time quality assurance in clinical laboratories. Full article

Background: Artificial intelligence (AI) is increasingly being integrated into implant dentistry, where clinical decision-making depends on the interpretation of complex radiographic and patient-specific data. Although multiple applications have been proposed across diagnostic imaging, treatment planning, intraoperative support and outcome prediction, their clinical validity and real-world applicability remain incompletely defined and their use raises relevant medico-legal considerations. Methods: A narrative review was conducted through a structured search of PubMed/MEDLINE, Scopus, and Web of Science, including English-language studies published between 2010 and February 2026. Clinical and experimental studies, as well as relevant reviews addressing AI applications in implant dentistry, were included. A qualitative thematic synthesis was performed due to methodological heterogeneity. Results: AI applications are mainly concentrated in diagnostic imaging, particularly CBCT analysis, where high levels of performance are consistently reported. In treatment planning, systems support specific decision-making tasks rather than comprehensive strategies, while intraoperative applications are integrated into navigation and robotic systems to improve procedural accuracy. Predictive models for implant outcomes have been developed, although their reliability remains influenced by dataset variability and study design. Conclusions: AI currently represents a supportive tool in implant dentistry, with greater applicability in standardized tasks. Its integration into complex clinical decision-making remains limited, highlighting the need for clinically oriented validation and cautious implementation in practice. Full article

Cardiovascular disease and cancer remain the leading causes of death worldwide. Although numerous cancer therapies have improved survival rates, they also increase the risk of cardiomyopathy, heart failure, and arrhythmias. These cardiovascular complications can limit treatment options and adversely affect the long-term quality of life of cancer survivors. Ca_V1.3, an L-type calcium channel encoded by CACNA1D, emerges as a central molecular mediator linking cardiovascular disease and cancer. It regulates calcium entry into cardiomyocytes and contributes to sinoatrial pacemaking and atrioventricular conduction. It also contributes to proliferation, migration, and therapy resistance in several cancers. Chemotherapy-induced oxidative stress, inflammatory signaling, hypoxia, and transcriptional changes can modulate the expression, gating, splicing, and trafficking of Ca_V1.3 channels. All these changes destabilize diastolic depolarization and impair conduction, thereby promoting arrhythmias in cancer patients. This review focuses on Ca_V1.3 biology in cardio-oncology, along with the mechanisms of chemotherapy-induced cardiotoxicity. It outlines the role of Ca_V1.3 as a key mediator linking cancer therapies to subsequent nodal dysfunction and increased arrhythmia susceptibility. It also expands on how patient-specific induced pluripotent stem cell-derived cardiomyocytes can model Ca_V1.3 dysregulation as well as support the development of targeted therapies. We propose that Ca_V1.3 represents a mechanistic bridge linking cancer therapy, calcium signaling, and cardiac electrophysiology, and that elucidating its pathophysiology may guide the design of targeted strategies in cardio-oncology. Full article

Bone defects from trauma, tumour resection, infection, and degenerative disease remain a major clinical burden, and autografts face limitations of supply and donor-site morbidity. Three-dimensional (3D) printing offers a route to patient-specific, architecturally defined bone scaffolds, while biopolymers from natural sources provide biodegradability, biocompatibility, and extracellular matrix-mimicking cues consistent with sustainable, green biomaterials science. This review synthesises recent progress in 3D printing of biopolymer-based scaffolds for bone tissue engineering. We first examine the principal feedstocks—alginate, gelatin and gelatin methacryloyl, collagen, chitosan, silk fibroin, cellulose, and microbial polyesters—and their preparation, crosslinking chemistry, and printability. We then compare extrusion, light-based, and indirect printing technologies and the process–property relationships governing resolution, mechanical competence, and cell viability. Composite and functionalisation strategies, including biopolymer–bioceramic hybrids and controlled delivery of growth factors and antimicrobial agents, are analysed as routes to osteoinduction, vascularisation, and infection control. Finally, we evaluate translational performance in preclinical models and outline central challenges of vascularisation, mechanical–degradation matching, scalability, and regulatory standardisation. Biopolymer 3D printing is positioned as a ve rsatile, sustainable platform whose clinical maturation depends on integrated material, structural, and biological design. Full article

Background/Objectives: Preoperative differentiation among benign thyroid nodules, follicular variant papillary thyroid carcinoma (FV-PTC), and classical papillary thyroid carcinoma (C-PTC) remains clinically challenging. FV-PTC is particularly difficult to identify due to its substantial sonographic and cytological overlap with both benign nodules and other malignant subtypes, frequently resulting in overtreatment or delayed diagnosis. This study aimed to develop and validate an interpretable multimodal model for accurate three-class discrimination using routine ultrasound images, with a specific focus on improving the preoperative identification of FV-PTC. Methods: This retrospective study included 479 pathologically confirmed thyroid nodules from 462 patients. Conventional ultrasound features and radiomics features extracted from grayscale ultrasound and color Doppler flow imaging were used to construct three predictive models: a Conventional Ultrasound model (conventional ultrasound features only), a Radiomics model (radiomics features only), and an Integrated model (combined features). Each model was trained using four machine learning classifiers. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score. Model interpretability was assessed using SHapley Additive exPlanations (SHAP) analysis, and clinical usefulness was evaluated using decision curve analysis (DCA). Results: The support vector machine (SVM)-based Integrated Model achieved the best overall performance. In the independent testing cohort, the AUCs were 0.853 for FV-PTC, 0.882 for C-PTC and 0.928 for benign nodules. The Integrated Model showed the greatest improvement for FV-PTC, with a ΔAUC of 0.141 compared with the Conventional Ultrasound Model. SHAP (SHapley Additive exPlanations) analysis identified wavelet-HL_gldm_Dependence and wavelet-HH_glcm_InverseVariance as the two most important radiomics predictors in both the Radiomics Model and the Integrated Model, demonstrating robust cross-model stability and high discriminative power. Conclusions: The SVM-based Integrated Model demonstrated promising performance for three-class classification of thyroid nodules and enhanced the preoperative identification of FV-PTC. This approach may provide an interpretable and noninvasive decision-support tool for refining subtype-specific risk stratification and supporting individualized clinical management. Full article

Human digital twins (HDTs) are patient-specific computational models that combine medical imaging, physiological measurements and predictive algorithms. They are moving from an exciting concept to a realistic clinical opportunity. The key question is no longer whether HDTs can be built. The key question is which methods are mature enough to support clinical decisions and what is still missing for routine use. This systematic review maps the methodological landscape of HDTs and highlights practical bottlenecks that limit clinical translation. A PRISMA 2020 guided search of PubMed, Scopus, IEEE Xplore, and the Cochrane Library, covering publications from 2016 to 2026, identified 151 eligible studies. Bibliometric mapping and thematic synthesis were used to characterize research clusters, computational paradigms, and collaboration patterns. Three dominant application streams were identified: cardiovascular HDTs for hemodynamic simulation and procedural planning, musculoskeletal HDTs for biomechanics-driven orthopedic innovation, and neurological HDTs integrating neuroimaging with computational neuroscience. Across domains, the strongest technical trend is the rise in hybrid pipelines that combine physics-based simulation, including finite element and computational fluid dynamics models, with machine learning for segmentation, parameter identification, reduced-order modeling, and faster inference. However, reporting of verification, validation, uncertainty quantification, and explicit context of use remains uneven and prospective clinical evidence is still limited. Overall, the literature shows rapid progress toward clinically credible HDTs, while highlighting the need for scalable computation, standardized credibility pipelines, and workflow-integrated platforms to support safe and reproducible clinical adoption. Full article

Background/Objectives: This preliminary, single-centre study evaluated infectious diseases consultation (IDC) patterns as indicators of hospital workflow and care complexity, aiming to characterise routinely available variables that may inform future organisational research and EHR-based clinical decision support development. Methods: In this retrospective study, 39,275 IDC requests from 16,430 patients were analysed using hospital information management system records. Paediatric patients and specialised immunosuppressed patient units were excluded. Request volumes, diagnostic categories, consultation purposes, and factors associated with in-hospital mortality were evaluated. Multivariable logistic regression models were constructed separately for two hospital blocks. Results: A total of 39,275 IDC records for 16,430 unique patients were reviewed. Mean consultation access time was 82.2 ± 64.3 min. Requests originated from surgical clinics (43.8%), followed by intensive care units (37.6%) and medical/internal clinics (18.6%). Pneumonia was the most common indication (30.5%), followed by unspecified infections (25.4%) and skin/soft tissue infections (17.2%). Consultation objectives included treatment, diagnostic assessment, and clinical guidance as non-mutually exclusive components. Significant block-level differences were observed in consultation timing, ICU-related consultation, diagnostic profiles, consultation purposes, and mortality. Age and ICU-related consultation were independently associated with mortality in both blocks, whereas consultation access time and COVID-19 diagnosis showed block-specific associations. Conclusions: IDC patterns may reflect not only diagnostic demand but also case severity, ICU-related care, consultation timing, and hospital location. As a preliminary single-centre study, these hypothesis-generating findings highlight the importance of integrating clinical, organisational, and contextual variables in future prospective, multi-centre studies aimed at developing EHR-based decision-support models. External validation, incorporation of comorbidity indices and microbiological data, and assessment of explainability are required before clinical implementation. Full article

Background: The management of diabetic foot disease and knee osteoarthritis (OA) with smart orthotics holds significant importance during the early stages of these conditions, given their potential consequences, including functional impairment, chronic pain, and economic burden. Real-time monitoring of plantar foot pressure enables early detection of abnormal force distribution and gait biomechanics, allowing for the redirection of forces away from affected ulcers or arthritic joints. This is the first systematic review to synthesise clinical evidence for smart orthotics technology with real-time plantar pressure sensor biofeedback across both diabetic foot ulcer prevention and knee osteoarthritis management simultaneously. A search of the PROSPERO register confirmed no existing registration covers this specific combination. Objectives: To examine the clinical evidence for the use of standard and smart orthotics in the prevention and management of diabetic foot ulcers (DFUs) and knee OA, and to evaluate their impact on plantar pressure redistribution, ulcer recurrence, pain, biomechanics, and economic burden. Eligibility criteria: Studies published in English involving human adult participants (≥18 years) with a clinical diagnosis of diabetes mellitus (at risk of DFU or with peripheral neuropathy) or knee OA, where the intervention involved any orthotic device or smart/intelligent insole with clinical outcomes reported, were included. Studies on healthy individuals only, those not reporting participant age, and non-weight-bearing protocols not differentiated from weight-bearing were excluded. Information sources: Five databases were searched: CINAHL (EBSCO Information Services, Ipswich, MA, USA), PubMed Advanced (National Library of Medicine, Bethesda, MD, USA), Wiley Online Library (John Wiley & Sons, Hoboken, NJ, USA), Cochrane Library (Cochrane Collaboration, London, UK), and Google Scholar (Google LLC, Mountain View, CA, USA). Searches were completed in May 2026. Methods: We conducted a comprehensive literature review. This review was structured and reported with reference to the PRISMA 2020 statement (Preferred Reporting Items for Systematic Reviews and Meta-Analysis; University of Ottawa, Ottawa, ON, Canada) to guide transparency of reporting. It does not constitute a full Cochrane-style systematic review; risk of bias assessment was applied to key included studies and GRADE (Grading of Recommendations Assessment, Development and Evaluation; McMaster University, Hamilton, ON, Canada) certainty ratings were applied informally and narratively rather than as formal per-outcome evidence profiles. Five databases were searched yielding 92,637 records. After removal of 398 duplicates by Rayyan, 92,239 records remained. A subsequent automated keyword-based relevance filter applied within Rayyan (Rayyan AI, Doha, Qatar), prior to human screening, excluded 84,572 records that did not contain any terms related to orthotics, diabetic foot, or knee osteoarthritis, yielding 7667 records for human title/abstract screening. A narrative synthesis approach was adopted owing to the heterogeneity of study designs and outcome measures across included studies, which precluded meta-analysis. This review was not prospectively registered. A complete list of all 78 included studies, including those not individually discussed in the results and discussion. Results: The available clinical studies report promising findings for orthotics and smart orthotics in pain reduction, ulcer prevention, and potential reduction in economic burden, though conclusions are limited by small sample sizes, heterogeneity, and predominantly open-label designs. Recent research found that orthotics can be used to alter the gait pattern that influences knee OA by reducing excessive force on the affected joint. A randomised controlled trial demonstrated an 80% relative risk reduction in DFU recurrence (RR = 0.20; 95% CI: 0.06–0.79; p = 0.022), with absolute event rates of 6.3% in the intervention group versus 30.8% in controls (ARR = 24.5%); a second trial reported a 71% reduction in ulcer incidence over 18 months; and a third randomised controlled trial demonstrated statistically significant plantar pressure reduction (p < 0.01) in patients with diabetic neuropathy. Conclusions: The available evidence suggests that orthotics may be associated with improved pressure redistribution, reduced ulcer incidence, and benefit in the management of knee OA. Although the number of studies directly comparing smart orthotics with standard orthotics remains limited, the limited comparative studies suggested that smart orthotics showed promising results in reducing ulcer incidence, providing the patient with real-time feedback to offload via their electronic devices. These findings, while preliminary, highlight the potential of smart orthotic technology as an adjunct to standard orthotic care in reducing the overall burden of diabetic foot disease and knee osteoarthritis. Limitations: The primary methodological limitation of this review is the open-label design of all included smart orthotic trials, which precludes participant blinding and introduces performance bias. However, this limitation is structural and inherent to the wearable technology field—analogous to surgical trials—and is substantially mitigated by the use of objective primary outcome measures (plantar pressure and ulcer recurrence) across the three included RCTs, the consistency of effect direction across independent RCTs conducted in different countries, and a narrative sensitivity analysis confirming robustness of findings (Risk of Bias Across Studies Section). Formal per-outcome GRADE evidence profiles were not produced; overall certainty of evidence was assessed narratively with reference to GRADE domains and is judged to be low to moderate for smart orthotics in DFU prevention and low for knee OA management, consistent with the Level 2–3 evidence base and open-label study designs. Future adequately powered, multi-site RCTs with standardised outcome reporting, minimum 24-month follow-up, and integrated health economic modelling are the highest priority to extend these preliminary findings. Registration: This review was not prospectively registered. Full article

Dual antiplatelet therapy (DAPT) with aspirin and a P2Y12 inhibitor remains the cornerstone of antithrombotic management after myocardial revascularization. However, the traditional “one-size-fits-all” approach to DAPT duration and intensity fails to account for marked interindividual variability in drug response—driven by genetic polymorphisms, notably CYP2C19 variants like CYP2C19*2, which reach a frequency of up to 75% in specific groups like the Melanesian population—comorbidities such as diabetes and chronic kidney disease, and dynamic clinical factors including age and concomitant medications. We examine the current landscape of precision medicine tools for individualizing DAPT, including platelet function testing, point-of-care genotyping, validated clinical risk scores, and emerging artificial intelligence (AI)–based predictive models. Evidence from landmark trials is synthesized to evaluate escalation, de-escalation, and duration-tailoring strategies within the ischemic–bleeding trade-off framework. Special populations requiring individualized approaches are reviewed, including patients with atrial fibrillation, the elderly, and those requiring urgent noncardiac surgery with perioperative bridging. Future directions, including multi-omics integration, novel antiplatelet agents, and AI-driven clinical decision support systems, are also explored. As a narrative review, conclusions should be interpreted as reflective of current evidence synthesis rather than systematic-review-grade evidence, given the absence of formal risk-of-bias scoring or meta-analytic pooling. Personalized DAPT guided by complementary genetic and phenotypic testing, integrated with dynamic risk stratification, offers a paradigm shift from empiric therapy toward precision-guided antithrombotic management with the potential to simultaneously reduce ischemic and bleeding complications. Full article

Background/Objectives: Early recurrence after curative-intent resection is a major determinant of poor prognosis in hepatocellular carcinoma (HCC). Artificial intelligence (AI)-driven predictive models have emerged to identify patients at high risk of recurrence but remain incompletely synthesized for early recurrence specifically. This review aimed to identify and appraise AI-driven models predicting early recurrence after surgical resection. Methods: PubMed/MEDLINE, Scopus and Web of Science were searched from inception to November 2025. Eligible studies developed and evaluated AI-driven models predicting early recurrence (≤24 months) after curative-intent hepatectomy as first-line treatment for HCC. Risk of bias and applicability were assessed using PROBAST+AI, and findings were synthesized narratively due to methodological heterogeneity. The review was registered in PROSPERO. Results: Thirty-six studies involving 14,716 patients were included. Most studies originated from China (33/36, 91.7%), were single-center (27/36, 75%), and retrospective (35/36, 97.2%). Magnetic resonance imaging (MRI) was the predominant imaging modality (15/36, 41.7%), followed by computed tomography (CT) (11/36, 30.6%) and ultrasound (US)/contrast-enhanced ultrasound (CEUS) (6/36, 16.7%). Three studies developed non-imaging models, and one combined CT and MRI. In within-study comparisons, multimodal models generally showed better discrimination than unimodal approaches. Peritumoral, habitat-based, and multiphasic strategies appeared promising. However, external validation was reported in only 6/36 studies (16.7%), calibration and decision-curve analysis were inconsistently reported, and most studies had high risk of bias. Conclusions: AI-driven models show potential to predict early recurrence of HCC after curative-intent resection. Nevertheless, evidence remains limited by methodological heterogeneity and restricted geographical diversity, while clinical utility remains inconsistently evaluated, and no model has yet been generalized in clinical practice. Prospective multicenter studies with standardized outcomes, transparent reporting, and external validation are needed for clinical implementation. Full article

Background/Objectives: Parathyroid hormone (PTH) has emerged as a novel biomarker in heart failure (HF), reflecting neurohormonal, renal, and metabolic dysregulation within the cardiorenal–mineral axis. However, its independent prognostic value and incremental contribution remain unclear when evaluated through formal nested structures Therefore, this study aimed to evaluate the association between PTH and all-cause mortality in patients with heart failure with reduced ejection fraction (HFrEF) and to determine whether PTH provides additional prognostic information beyond NT-proBNP. Methods: In this retrospective cohort study, 1594 patients with HFrEF (LVEF ≤ 40%) were analyzed. Serum PTH and NT-proBNP levels were log-transformed and evaluated as predictors of all-cause mortality. Patients were stratified according to PTH levels, and survival analysis was performed. Incremental model fit was evaluated using nested likelihood ratio tests. Stratified multivariable Cox models and formal interaction tests were executed across predefined clinical strata (age, renal function, and heart failure etiology). Results: During a median follow-up of 36 months, 525 deaths occurred. Elevated PTH levels were associated with worse survival outcomes. In multivariable Cox regression analysis, both LnPTH (HR: 1.233, p = 0.0147) and LnNT-proBNP (HR: 1.374, p < 0.0001) were independent predictors of mortality. Combined elevation of PTH and NT-proBNP identified patients at the highest risk. The addition of LnPTH to the baseline model significantly improved global model fit (χ² = 4.242, p = 0.0394). Importantly, the prognostic value of LnPTH was significantly modified by age (P_interaction = 0.026) and renal function (P_interaction = 0.038), demonstrating independent predictive power specifically in patients aged < 65 years (HR: 1.402) and those with eGFR ≥ 60 mL/min/1.73 m² (HR: 1.454), but not in older or advanced renal impairment strata. Conclusions: PTH is independently associated with mortality in patients with HFrEF and provides incremental prognostic value beyond NT-proBNP by optimizing global model fit. These findings support its role as a complementary biomarker within a multimarker strategy for improved risk stratification of the cumulative metabolic and cardiovascular burden. Full article