Search Results (13,450)

Background: PRKAG2 cardiac syndrome is a rare autosomal dominant glycogen-storage cardiomyopathy that mimics sarcomeric hypertrophic cardiomyopathy (HCM) but features ventricular pre-excitation, progressive conduction disease and concentric hypertrophy due to intracellular glycogen accumulation. The c.905G>A (p.Arg302Gln) variant is one of the most frequently reported pathogenic substitutions. Case summary: We describe a three-generation family carrying the heterozygous PRKAG2 p.Arg302Gln variant. The proband, a 41-year-old man, presented with paroxysmal atrial fibrillation, short PR interval and abnormal intraventricular conduction associated with concentric left ventricular hypertrophy and preserved ejection fraction. Holter monitoring disclosed episodes of high-grade atrioventricular block, prompting implantation of a primary-prevention dual-chamber ICD. Two gene-positive brothers exhibited milder hypertrophy but shared sinus bradycardia, ventricular pre-excitation and supraventricular arrhythmias; one underwent catheter ablation of a posteroseptal accessory pathway. The affected mother displayed a hypertrophic phenotype complicated by sick sinus syndrome and permanent atypical atrial flutter requiring pacemaker implantation. No relevant extracardiac involvement was detected in any family member. Review and novelty: Using this family as a starting point, we provide a concise narrative review of PRKAG2 syndrome with emphasis on the Arg302Gln genotype, molecular mechanisms and emerging treatment strategies. We highlight key multimodality imaging and tissue-characterization features that help distinguish diffuse, concentric glycogen-storage hypertrophy from the often-asymmetric pattern of sarcomeric HCM. Integration of our findings with published Arg302Gln cohorts illustrates the broad phenotypic variability in conduction disease, pre-excitation and atrial arrhythmias. Conclusions: PRKAG2 p.Arg302Gln-related cardiomyopathy should be suspected in patients with otherwise unexplained left ventricular hypertrophy associated with short PR interval, pre-excitation or early brady–tachy arrhythmias. Early recognition of red-flag features, systematic genetic testing, family screening and tailored arrhythmia/device management are crucial, while emerging gene- and pathway-targeted therapies may offer future disease-modifying potential. Full article

This paper discusses a multimodal AI system applied to legal reasoning for tax law. The results given here are very general and apply to systems developed for other areas besides tax law. A central goal of this work is to gain a better understanding of the relationships between LLMs (Large Language Models) and automated theorem-proving methodologies. To do this, we suppose (1) two cases for the theorem-proving system: one where it has a countable number of total meanings for its countable number of atoms and the other is where it has an uncountable number of total meanings for its countable number of atoms, and (2) LLMs can have an uncountable number of token meanings. With this in mind, the results given in this paper use the downward and upward Löwenheim–Skolem theorems and logical model theory to contrast these two AI modalities. One modality focuses on syntactic proofs and the other focuses on logical semantics based on LLMs. Particularly, one modality uses a rule-based first-order logic theorem-proving system to perform legal reasoning. The objective of this theorem-proving system is to provide proofs as evidence of valid legal reasoning when enacted laws are applied to particular situations. These proofs are syntactic structures that can be presented in the form of narrative explanations of how the answer to the legal question was determined. The second modality uses LLMs to analyze and transform a user’s tax query so this query can be sent to a first-order logic theorem-proving system to perform its legal reasoning function. The main goal of our application of LLMs is to enhance and simplify user input and output for the theorem-proving system. Using logical model theory, we show how there can exist an equivalence between laws represented in logic of the theorem-proving system, fixed in time when the theorem-proving system was set up, and new semantics given by LLMs. These results are based on logical model theory and Löwenheim–Skolem theorems. Full article

Background and Objectives: Sarcopenia is a common yet underrecognized condition in cancer patients and is associated with increased treatment-related toxicity, functional decline, and poor clinical outcomes. Practical, rapid, and bedside-applicable tools are needed to detect sarcopenia early in routine oncology practice. This study aimed to evaluate the diagnostic value of rectus femoris muscle ultrasonography within an integrated clinical assessment combining handgrip strength and bioelectrical impedance analysis for the detection of sarcopenia in cancer patients. Materials and Methods: In this prospective cross-sectional study, 147 adult patients with malignancy were evaluated using a multimodal sarcopenia assessment framework. Muscle strength was assessed by handgrip dynamometry, muscle mass was estimated using bioelectrical impedance analysis (BIA)-derived appendicular skeletal muscle mass index (ASMI), and muscle morphology was evaluated using ultrasonographic measurements of the rectus femoris and biceps brachii muscles. Sarcopenia was defined and classified according to the EWGSOP2 criteria. Associations between clinical variables, BIA parameters, and ultrasonographic measurements were analyzed. Receiver operating characteristic (ROC) curve analyses were performed to assess the diagnostic performance of muscle ultrasonography for sarcopenia detection. Results: The mean age of the study population was 60.2 ± 11.2 years, and 51% of participants were male. Confirmed sarcopenia was identified in 12.2% of patients, while 27.2% were classified as having probable sarcopenia. Sarcopenic patients were significantly older (68.5 ± 7.6 vs. 59.0 ± 11.2 years, p = 0.001) and had lower handgrip strength (15.8 ± 6.0 vs. 24.3 ± 8.4 kg, p < 0.001) and ASMI values (5.96 ± 0.64 vs. 7.23 ± 1.18 kg/m², p < 0.001). Rectus femoris muscle thickness was significantly reduced in patients with sarcopenia (6.40 ± 1.42 vs. 8.19 ± 2.21 mm, p = 0.001). Rectus femoris muscle thickness demonstrated good diagnostic performance for sarcopenia detection (AUC = 0.752; 95% CI: 0.650–0.853; p = 0.001), with an optimal cut-off value of ≤ 7.59 mm (sensitivity 83.3%, specificity 61.2%). Conclusion: Rectus femoris muscle ultrasonography is a practical, rapid bedside assessment for detecting sarcopenia in cancer patients. When integrated with handgrip strength and BIA, this multimodal approach provides a feasible, radiation-free strategy for early sarcopenia screening in routine oncology practice. Full article

Traditional ergonomic considerations in human–machine and human–swarm systems have primarily relied on static diagnostic snapshots, which often fail to capture the temporal accumulation and non-linear dissipation of musculoskeletal fatigue. As Industry 5.0 transitions toward immersive, human-centric cyber-physical systems, redefining ergonomic load as an endogenous state variable allows for real-time control of musculoskeletal integrity. This work proposes the Dynamic Integrity Governor (DIG) framework, which treats ergonomic load as a normalized, dimensionless state variable $\xi \left(t\right)$ that evolves according to a stochastic proxy of recursive Newton–Euler dynamics. Leveraging a machine-perception-aware Adaptive Event-Triggered Mechanism (AETM) and the Multi-modal Flamingo Search Algorithm (MMFSA), we develop a decentralized architecture that redistributes ergonomic demands in real-time. The framework utilizes a 7-DOF kinematic model and Control Barrier Functions (CBF) to maintain human–swarm interaction within safe biomechanical boundaries, effectively filtering stochastic sensor noise through Girard-based stability buffers. Computational validation via N = 1000 Monte Carlo runs demonstrates that the proposed strategy achieves a 79.97% reduction in control updates (SD = 0.19%; p < 0.0001; Cohen’s d = 2.41), ensuring a positive minimum inter-event time (MIET) to prevent the Zeno phenomenon and supporting carbon-aware AI operations. The integration of variable prediction horizons yields an 80.69% improvement in solving time, while ensuring a minimal computational footprint suitable for real-time edge deployment. The identification of optimal postural niches maintains peak ergonomic load at 41.42%, representing a significant safety margin relative to the integrity barrier. While validated against a 50th percentile male profile, the DIG framework establishes a modular foundation for personalized ergonomic governors in inclusive Industry 5.0 applications. Full article

Accurate fault diagnosis of mining hoisting head sheave systems is critical for ensuring operational safety in harsh underground environments. This study proposes a multi-source fault diagnosis framework that fuses vibration and acoustic information using a Convolutional Neural Network and Random Forest (CNN-RF). To support mechanism understanding and validate the experimental platform, finite element and multi-body dynamics simulations (ANSYS/ADAMS) are employed for physical verification and fault signature analysis, while the CNN-RF model is trained and tested exclusively using experimentally acquired vibration and acoustic data. For feature construction, vibration signals are transformed into time–frequency representations (including STFT, CWT, and generalized S-Transform (GST)), and acoustic signals are characterized using Mel-Frequency Cepstral Coefficients (MFCCs). Experimental results demonstrate that vibration–acoustic fusion improves diagnostic performance compared with single-modality baselines; the best performance is achieved by GST+MFCC with the proposed CNN-RF classifier, reaching an accuracy of 98.96%. Future work will conduct cross-condition validation under varying speeds and loads and investigate missing-modality robustness to further assess generalization and deployment reliability. Full article

Magnetocardiography has received regulatory recognition as a contactless, sensitive aid for physicians to diagnose or exclude myocardial ischemia in chest pain patients, with or without coronary obstruction. Such success, however, might not equate to guideline endorsement or proven clinical effectiveness. Moreover, despite its intrinsic advantages, including unrivalled contactless functional imaging of cardiac electrophysiology and a strong potential for multimodal integration with other imaging methods, its clinical adoption remains limited by the lack of internationally recognized standards and guidelines. This Perspective Review article, highlighting the viewpoints of clinical end users, is a call for urgent action to establish an interdisciplinary expert commission. This is essential for defining consensus-based standards and recommendations for the clinical use of MCG. Full article

Background: Obesity is traditionally defined by excess fat mass; however, the preservation of fat-free mass (FFM), particularly skeletal muscle, has gained increasing relevance due to its metabolic, endocrine, and functional roles. Weight loss interventions, including hypocaloric diets, pharmacological treatments, and bariatric surgery, are frequently associated with unintended loss of skeletal mass, increasing the risk of sarcopenic obesity and related complications. Objective: This study aimed to systematically evaluate the effectiveness of whey protein supplementation in preserving fat-free mass and muscle-related outcomes in adults with obesity undergoing weight loss interventions. Methods: A systematic review was conducted in accordance with PRISMA guidelines. Randomized controlled trials published in English were identified through searches of PubMed/MEDLINE, CENTRAL, Embase, Scopus, ClinicalTrials.gov, and WHO ICTRP, searched up to September 2025. Eligible studies included adults (>18 years) with obesity receiving whey protein supplementation as part of a hypocaloric diet, compared with placebo or standard interventions. Primary outcomes were changes in fat-free mass assessed by validated methods (DXA, BIA, MRI), while secondary outcomes included body weight, fat mass, metabolic parameters, adherence, and safety. Risk of bias was assessed using the Cochrane RoB 2.0 tool, and certainty of evidence was evaluated with GRADE. The abstract was registered in PROSPERO with code CRD420251069996. There was no funding and no conflicts of interest. Results: Fourteen randomized controlled trials were included. Whey protein supplementation generally supported the maintenance or modest improvement of fat-free mass, particularly when combined with resistance exercise or anabolic-enriched formulations such as leucine or vitamin D. Several trials, however, reported neutral effects, especially in the absence of structured physical activity. Overall, effect estimates ranged from small gains to null or uncertain differences, and the certainty of evidence was frequently downgraded due to limited sample sizes, wide confidence intervals, heterogeneity across interventions and assessment methods, short follow-up periods, and methodological limitations including open-label designs and inconsistent adherence monitoring. Conclusions: Whey protein supplementation may support fat-free mass preservation during weight loss in adults with obesity, particularly as part of a multimodal intervention. Further high-quality trials are needed to define optimal dosing strategies and target populations. Full article

The rise of toxic content, particularly in the form of hateful memes, poses a significant challenge to social media platforms. This paper presents an empirical comparative study of unimodal and multimodal architectures for toxic content detection. Rather than proposing a novel architecture, the study evaluates the efficacy of a modular Late Fusion framework (RoBERViT) against specialized unimodal baselines (RoBERTa and ViT) and a generalist Large Multimodal (LLaVA). Both unimodal and multimodal configurations across two distinct benchmarks—the imbalanced Innopolis Hateful Memes dataset and the confounder-driven Facebook Hateful Meme dataset—were explored. Beyond quantitative metrics, this study conducts a qualitative analysis using Explainable AI (LIME) and a Large Multimodal Model (LLaVA) to investigate model reasoning. Results demonstrate that the multimodal fusion model consistently outperformed its unimodal counterparts on the Innopolis Hateful Meme dataset, achieving a toxic class F1-score of 0.6439 compared to the text-only score of 0.5794. However, on the Facebook Hateful Meme dataset, text-only models remain competitive, highlighting the “benign confounder” challenge. The qualitative analysis reveals that text remains the dominant modality, with models often relying on surface-level keywords. Notably, the Vision Transformer frequently uses text overlays as a visual proxy for hate, while the LLaVA model struggles with hallucinated toxicity in benign confounder contexts. These findings underscore the persistent challenge of achieving true multimodal understanding in hate speech detection. Full article

Objectives: Global infertility rates are rapidly increasing. Assisted reproductive technologies combined with artificial intelligence are the next hope for overcoming infertility. In vitro fertilization (IVF) is gaining popularity owing to its increasing success rates. The success rate of IVF essentially depends on the assessment and inspection of blastocysts. Blastocysts can be segmented into several important compartments, and advanced and precise assessment of these compartments is strongly associated with successful pregnancies. However, currently, embryologists must manually analyze blastocysts, which is a time-consuming, subjective, and error-prone process. Several AI-based techniques, including segmentation, have been recently proposed to fill this gap. However, most existing methods rely only on raw grayscale intensity and do not perform well under challenging blastocyst image conditions, such as low contrast, similarity in textures, shape variability, and class imbalance. Methods: To overcome this limitation, we developed a novel and lightweight architecture, the microscopic multimodal interaction segmentation network (MiMics-Net), to accurately segment blastocyst components. MiMics-Net employs a multimodal blastocyst stem to decompose and process each frame into three modalities (photometric intensity, local textures, and directional orientation), followed by feature fusion to enhance segmentation performance. Moreover, MiMic dual-path grouped blocks have been designed, in which parallel-grouped convolutional paths are fused through point-wise convolutional layers to increase diverse learning. A lightweight refinement decoder is employed to refine and restore the spatial features while maintaining computational efficiency. Finally, semantic skip pathways are induced to transfer low- and mid-level spatial features after passing through the grouped and point-wise convolutional layers. Results/Conclusions: MiMics-Net was evaluated using a publicly available human blastocyst dataset and achieved a Jaccard index score of 87.9% while requiring only 0.65 million trainable parameters. Full article

To predict the output power of integrated energy systems (IES) under zero-carbon conditions, this research presents a Multi Data Fusion-based iTransformer prediction network (MDF-iTransformer). The network uses Multivariate Singular Spectrum Analysis (MSSA) to identify nonlinear relationships among variables and extract dynamic features from multi-modal data. It integrates an embedding block and multivariate attention module into the iTransformer network to capture complex patterns and long-term temporal dependencies in multi-dimensional data, thereby extracting dynamic features across different time scales and spatial dimensions. Subsequently, to address the issue of imbalanced datasets, the improved K-means-SMOTE (KS) algorithm is adopted to augment the number of small-class samples, effectively reducing model bias. Experimental results indicate that the proposed MDF-iTransformer achieves a root-mean-square error (RMSE) of 7.2 kW, mean absolute error (MAE) of 5.6 kW, mean absolute percentage error (MAPE) of 2.7%, and an R-squared value (R²) of 0.92 for a 1 h prediction horizon. It still maintains an RMSE of 14.4 kW, MAE of 11.9 kW, MAPE of 3.68%, and R² of 0.74 at the 10 h horizon, with cross-season load forecasting errors consistently below 4%. Compared with other algorithms, MDF-iTransformer demonstrates higher accuracy and stronger robustness, playing a crucial role in the optimal operation of integrated energy systems. Full article

Background: Accurate and timely diagnosis of skin lesions, including Melanoma (MEL), Basal Cell Carcinoma (BCC), Squamous Cell Carcinoma (SCC), Actinic Keratosis (ACK), Seborrheic Keratosis (SEK), and Nevus (NEV), is often hindered by the severe class imbalance and high morphological similarity among pathologies in clinical practice. Although multimodal learning has shown potential in resolving these issues, existing approaches often fail to address predictive uncertainty or effectively integrate heterogeneous clinical metadata. Therefore, this study proposes DermaCalibra, a robust and explainable multimodal framework optimized for small-scale, imbalanced clinical datasets. Methods: The proposed framework integrates three essential modules: First, the Attention-Based Multimodal Channel Recalibration (AMCR) module introduces a probabilistic Bayesian uncertainty estimation mechanism via Monte Carlo dropout to adjust focal loss weights, prioritizing features from underrepresented classes. Second, the Metadata-Driven Dynamic Feature Modulation and Cross-Attention Fusion (MDFM-CAF) module, designed to resolve inter-class visual ambiguity, dynamically rescales dermoscopic feature maps using non-linear clinical context transformations. Lastly, the Gradient Feature Attribution (GFA) module is implemented to provide pixel-level diagnostic heatmaps and metadata importance scores. Results: Evaluated on the PAD-UFES-20 dataset, DermaCalibra achieves a balanced accuracy (BACC) of 84.2%, outperforming current state-of-the-art (SOTA) methods by 3.6%, and a Macro Area Under the Receiver Operating Characteristic Curve (Macro AUC) of 96.9%. Extensive external validation on unseen hospital and synthetic datasets confirms robust generalizability across diverse clinical settings without the need for retraining. Conclusions: DermaCalibra effectively bridges the gap between deep learning complexity and clinical intuition through uncertainty-aware reasoning and transparent interpretability. The framework provides a reliable and scalable computer-aided diagnostic tool for early skin lesion detection, particularly in resource-limited clinical environments. Full article

Background/Objectives: Multimodal neuroimaging, particularly the integration of electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS), has emerged as a key methodology for investigating brain function and classifying neural activity. However, the efficient fusion of these two signals remains a formidable challenge due to their significant spatio-temporal heterogeneity. This paper presents the BiSTF-Net, which integrates decoupled and bi-directional spatio-temporal fusion mechanisms to enhance the performance of cognitive task recognition. Methods: In BiSTF-Net, the spatial features of EEG and fNIRS are mutually guided and enhanced through an efficient bi-directional cross modal guidance (Bi-CMG). Then, the temporal latencies of fNIRS signals are aligned in a data-driven manner using adaptive temporal alignment (ATA). Subsequently, the aligned features are deeply fused into a modality-invariant, discriminative representation via a symmetric cross-attention fusion (SCAF) module. Results: Evaluated on the mental arithmetic (MA), motor imagery (MI), and word generation (WG) tasks, the BiSTF-Net achieves average accuracies of 83.33%, 82.09%, and 84.99% respectively. Conclusions: The BiSTF-Net exhibits superior performance compared to the existing methods, offers a robust and interpretable solution for multimodal EEG-fNIRS cognitive task classification, and provides a methodological foundation for future extensions to other multimodal data and broader real-world clinical applications. Full article

Large Language Models are increasingly used for high-level robotic reasoning, yet their latency and stochasticity complicate their direct use in low-level control. Moreover, extracting actionable navigation cues from multimodal context incurs inference costs that are challenging for embedded platforms. We present a plug-and-play framework that augments a finite-state machine with asynchronous velocity suggestions generated by a Large Language Model, using an off-the-shelf DistilGPT-2 model running on-device on a Jetson AGX Orin. The system extracts task-relevant cues from the current context and integrates them only if they satisfy deadline, schema, and kinematic validation, thereby preserving a deterministic 50 Hz control loop with a <5 ms fallback path. We compare multiple Large Language Models for embedded robot control and quantify trade-offs among model size, inference time, and output validity. To assess whether the Large Language Models add value beyond signal processing, we include an ablation against a standard smoothing baseline; the results indicate that the Large Language Models contribute anticipatory, context-dependent adjustments that are not captured by filtering alone. Experiments in Gazebo and on a real TurtleBot3 reduce the final position error from 0.246 m to 0.159 m and improve trajectory efficiency from 0.821 to 0.901 without increasing control-loop latency. Approximately 80% of the Large Language Models’ outputs pass validation and are applied. Overall, the framework reduces developer effort by enabling behavioral changes at the prompt level while maintaining interpretable, robust edge-based navigation. Full article

Background: Primary angiosarcoma of the breast (PAB) is a rare malignancy with no standardized treatment protocol. Objective: To quantify the impact of tumor grade on overall survival (OS) and evaluate the association of adjuvant chemotherapy and radiotherapy with survival in primary angiosarcoma of the breast (PAB). Methods: We systematically searched PubMed, Scopus, and Cochrane Library until 27 June 2025. Two reviewers independently screened studies, extracted data, and assessed risk of bias using the Newcastle-Ottawa Scale. Kaplan–Meier curve digitization was used to reconstruct individual patient data. Random-effects meta-analysis was performed for grade comparisons and therapy associations. Results: Eleven studies (436 patients) were included. Meta-analysis of six studies showed increasing tumor grade significantly predicted mortality, with homogeneous hazard ratios (HRs) of 1.2 (Grade 2 vs. 1) and 3.7 (Grade 3 vs. 1). Analysis of five studies revealed that adjuvant chemotherapy was associated with significantly improved survival (HR = 0.11, 95% CI: 0.02–0.45), while radiotherapy showed no benefit (p = 0.96). Included studies demonstrated low-moderate risk of bias. Conclusions: This first quantitative synthesis establishes histologic grade as a paramount prognostic factor in PAB and shows a strong association between adjuvant chemotherapy and survival benefit. These findings provide crucial evidence for risk stratification and support considering chemotherapy in multimodal treatment for this rare disease. Full article

“Unusual sporotrichosis”, a concept proposed in this review, refers to severe, extracutaneous, or anatomically atypical manifestations of sporotrichosis occurring in immunocompetent hosts and represents an underrecognized clinical subset associated with important diagnostic and therapeutic challenges. This systematic review aimed to characterize unusual sporotrichosis worldwide and to clarify its epidemiological, clinical, diagnostic, and therapeutic patterns. Following a registered protocol and PRISMA guidelines, PubMed, Scopus, and BVS/LILACS were searched up to November 2025 using a PICO-based strategy. Eligible studies included peer-reviewed case reports and case series with laboratory-confirmed sporotrichosis in patients without immunosuppression, diabetes mellitus, alcoholism, or other confounding comorbidities; classical lymphocutaneous and fixed cutaneous forms were excluded. From 922 records, 39 studies were included (13 case series and 26 case reports), yielding 55 cases reported between 1957 and 2024 across five world regions, mainly from the United States of America and Brazil. Adults aged 40–59 years (41.8%) and males (74.5%) predominated. Sapronotic transmission was most frequent (69.0%), although zoonotic transmission increased over time. Sporothrix schenckii/Sporothrix schenckii sensu stricto was the predominant species (87.3%). Osteoarticular (30.9%) and systemic (27.2%) forms were the most common presentations. Although cure was achieved in most cases (58.1%), sequelae were frequent (21.8%), and the worst prognosis—including most deaths—was observed in osteoarticular sporotrichosis. Unusual sporotrichosis is globally distributed and clinically distinct; therefore, early recognition and multimodal diagnostic and therapeutic strategies are essential to improve outcome. Full article