Explore the vast range of titles available.

Most patients with Post COVID Syndrome (PCS) present with a plethora of symptoms without clear evidence of organ dysfunction. A subset of them fulfills diagnostic criteria of myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS). Symptom severity of ME/CFS correlates with natural regulatory autoantibody (AAB) levels targeting several G-protein coupled receptors (GPCR). In this exploratory study, we analyzed serum AAB levels against vaso- and immunoregulatory receptors, mostly GPCRs, in 80 PCS patients following mild-to-moderate COVID-19, with 40 of them fulfilling diagnostic criteria of ME/CFS. Healthy seronegative (n=38) and asymptomatic post COVID-19 controls (n=40) were also included in the study as control groups. We found lower levels for various AABs in PCS compared to at least one control group, accompanied by alterations in the correlations among AABs. Classification using random forest indicated AABs targeting ADRB2, STAB1, and ADRA2A as the strongest classifiers (AABs stratifying patients according to disease outcomes) of post COVID-19 outcomes. Several AABs correlated with symptom severity in PCS groups. Remarkably, severity of fatigue and vasomotor symptoms were associated with ADRB2 AAB levels in PCS/ME/CFS patients. Our study identified dysregulation of AAB against various receptors involved in the autonomous nervous system (ANS), vaso-, and immunoregulation and their correlation with symptom severity, pointing to their role in the pathogenesis of PCS.

COVID-19 shares the feature of autoantibody production with systemic autoimmune diseases. In order to understand the role of these immune globulins in the pathogenesis of the disease, it is important to explore the autoantibody spectra. Here we show, by a cross-sectional study of 246 individuals, that autoantibodies targeting G protein-coupled receptors (GPCR) and RAS-related molecules associate with the clinical severity of COVID-19. Patients with moderate and severe disease are characterized by higher autoantibody levels than healthy controls and those with mild COVID-19 disease. Among the anti-GPCR autoantibodies, machine learning classification identifies the chemokine receptor CXCR3 and the RAS-related molecule AGTR1 as targets for antibodies with the strongest association to disease severity. Besides antibody levels, autoantibody network signatures are also changing in patients with intermediate or high disease severity. Although our current and previous studies identify anti-GPCR antibodies as natural components of human biology, their production is deregulated in COVID-19 and their level and pattern alterations might predict COVID-19 disease severity. COVID-19, similarly to systemic autoimmune diseases, is characterised by the presence of autoantibodies. Authors show here that the abundance and network signature of autoantibodies targeting G protein-coupled receptors and RAS-related proteins are altered in COVID-19 patients, and the level of disruption marks clinical severity.

Nowadays, the increasing number of medical diagnostic data and clinical data provide more complementary references for doctors to make diagnosis to patients. For example, with medical data, such as electrocardiography (ECG), machine learning algorithms can be used to identify and diagnose heart disease to reduce the workload of doctors. However, ECG data is always exposed to various kinds of noise and interference in reality, and medical diagnostics only based on one-dimensional ECG data is not trustable enough. By extracting new features from other types of medical data, we can implement enhanced recognition methods, called multimodal learning. Multimodal learning helps models to process data from a range of different sources, eliminate the requirement for training each single learning modality, and improve the robustness of models with the diversity of data. Growing number of articles in recent years have been devoted to investigating how to extract data from different sources and build accurate multimodal machine learning models, or deep learning models for medical diagnostics. This paper reviews and summarizes several recent papers that dealing with multimodal machine learning in disease detection, and identify topics for future research.

This paper develops mfEGRA, a multifidelity active learning method using data-driven adaptively refined surrogates for failure boundary location in reliability analysis. This work addresses the issue of prohibitive cost of reliability analysis using Monte Carlo sampling for expensive-to-evaluate high-fidelity models by using cheaper-to-evaluate approximations of the high-fidelity model. The method builds on the efficient global reliability analysis (EGRA) method, which is a surrogate-based method that uses adaptive sampling for refining Gaussian process surrogates for failure boundary location using a single- fidelity model. Our method introduces a two-stage adaptive sampling criterion that uses a multifidelity Gaussian process surrogate to leverage multiple information sources with different fidelities. The method combines expected feasibility criterion from EGRA with one-step lookahead information gain to refine the surrogate around the failure boundary. The computational savings from mfEGRA depends on the discrepancy between the different models, and the relative cost of evaluating the different models as compared to the high-fidelity model. We show that accurate estimation of reliability using mfEGRA leads to computational savings of ∼ 46% for an analytic multimodal test problem and 24% for a three-dimensional acoustic horn problem, when compared to single-fidelity EGRA. We also show the effect of using a priori drawn Monte Carlo samples in the implementation for the acoustic horn problem, where mfEGRA leads to computational savings of 45% for the three-dimensional case and 48% for a rarer event four-dimensional case as compared to single-fidelity EGRA.

[...]Article 31 of the Convention on the Rights of Persons with Disabilities14 states that adults and children with disabilities must have access to recreational, leisure, and sporting activities in both inclusive and disability-specific settings.

Detecting emotions is a growing field aiming to comprehend and interpret human emotions from various data sources, including text, voice, and physiological signals. Electroencephalogram (EEG) is a unique and promising approach among these sources. EEG is a non-invasive monitoring technique that records the brain’s electrical activity through electrodes placed on the scalp’s surface. It is used in clinical and research contexts to explore how the human brain responds to emotions and cognitive stimuli. Recently, its use has gained interest in real-time emotion detection, offering a direct approach independent of facial expressions or voice. This is particularly useful in resource-limited scenarios, such as brain–computer interfaces supporting mental health. The objective of this work is to evaluate the classification of emotions (positive, negative, and neutral) in EEG signals using machine learning and deep learning, focusing on Graph Convolutional Neural Networks (GCNN), based on the analysis of critical attributes of the EEG signal (Differential Entropy (DE), Power Spectral Density (PSD), Differential Asymmetry (DASM), Rational Asymmetry (RASM), Asymmetry (ASM), Differential Causality (DCAU)). The electroencephalography dataset used in the research was the public SEED dataset (SJTU Emotion EEG Dataset), obtained through auditory and visual stimuli in segments from Chinese emotional movies. The experiment employed to evaluate the model results was “subject-dependent”. In this method, the Deep Neural Network (DNN) achieved an accuracy of 86.08%, surpassing SVM, albeit with significant processing time due to the optimization characteristics inherent to the algorithm. The GCNN algorithm achieved an average accuracy of 89.97% in the subject-dependent experiment. This work contributes to emotion detection in EEG, emphasizing the effectiveness of different models and underscoring the importance of selecting appropriate features and the ethical use of these technologies in practical applications. The GCNN emerges as the most promising methodology for future research.

Major depressive disorder (MDD) is a multifaceted psychiatric illness with profound global consequences. To illuminate its molecular underpinnings, we employed a genome-driven integrative systems neuroimmunology approach to analyze transcriptomic profiles from 3114 individuals (1877 MDD patients and 1237 controls). This analysis uncovered coordinated neuroimmune transcriptomic shifts, marked by altered expression of genes involved in innate immune regulation, suppression of inflammatory responses, and pathways related to sensory perception, visual system development, and synaptic signaling. These alterations were consistently observed in both peripheral blood leukocytes (PBLs) and brain regions implicated in MDD. Among 31 genes jointly dysregulated in blood and brain, four stood out as robust predictors of MDD in PBLs: NEGR1 , PPP6C , SORCS3 , and PAX6 . Of these, PAX6 , a gene previously linked to MDD by GWAS, also exhibited differential expression in the amygdala and was functionally enriched in pathways governing immune modulation, vesicle trafficking, and neurodevelopmental processes, such as neuronal fate determination. In contrast, NEGR1 , PPP6C , and SORCS3 showed no significant changes in brain expression, suggesting a predominantly peripheral role. Importantly, these transcriptomic insights were reinforced in a murine model of chronic stress, where immunophenotyping revealed elevated PAX6 expression in peripheral myeloid cells. Together, these findings reveal a shared neuroimmune signature across the brain and immune system in MDD, highlighting PAX6 as a promising mechanistic link and potential biomarker for this disorder.

Facial expression recognition (FER) is essential for discerning human emotions and is applied extensively in big data analytics, healthcare, security, and user experience enhancement. This study presents a comprehensive evaluation of ten state-of-the-art deep learning models—VGG16, VGG19, ResNet50, ResNet101, DenseNet, GoogLeNet V1, MobileNet V1, EfficientNet V2, ShuffleNet V2, and RepVGG—on the task of facial expression recognition using the FER2013 dataset. Key performance metrics, including test accuracy, training time, and weight file size, were analyzed to assess the learning efficiency, generalization capabilities, and architectural innovations of each model. EfficientNet V2 and ResNet50 emerged as top performers, achieving high accuracy and stable convergence using compound scaling and residual connections, enabling them to capture complex emotional features with minimal overfitting. DenseNet, GoogLeNet V1, and RepVGG also demonstrated strong performance, leveraging dense connectivity, inception modules, and re-parameterization techniques, though they exhibited slower initial convergence. In contrast, lightweight models such as MobileNet V1 and ShuffleNet V2, while excelling in computational efficiency, faced limitations in accuracy, particularly in challenging emotion categories like “fear” and “disgust”. The results highlight the critical trade-offs between computational efficiency and predictive accuracy, emphasizing the importance of selecting appropriate architecture based on application-specific requirements. This research contributes to ongoing advancements in deep learning, particularly in domains such as facial expression recognition, where capturing subtle and complex patterns is essential for high-performance outcomes.

Kelp forests are essential marine ecosystems increasingly compromised by human activities. Effective reforestation strategies are urgently needed, and the “green gravel” method is a viable tool already used in some European regions. This study aimed to assess the success of this method using the native Kelp species Laminaria ochroleuca on the Portuguese coastline. Cultures of green gravel were reared until the specimens reached a size of approximately 3 cm. The gravel was then deployed at selected sites in Peniche, Berlengas, and Cascais. Over an eight-month period, scientific scuba divers monitored the integration of Kelp, along with associated fish, invertebrate, and algae communities. Nutrient availability, temperature, water movement, substrate type, and Rugosity Index (RI) were also measured. The highest success rate was 12% in Consolação, with Elefante and Galos (Berlengas) reaching 7% and 4%, respectively. By the end of the monitoring period, Cascais had no remaining Kelp on green gravel. Present data suggest that higher success is dependent on less rugged and higher RI topography. Higher grazing pressure, rougher terrain, and unexpected sedimentation appear to be the main obstacles to deployment success. Solid knowledge (biologic and topographic) on the restoration site, starting restoration actions near already established Kelp forests, and significantly scaling up restoration efforts could substantially improve the success of the green gravel method in future reforestation campaigns.

Causal machine learning is an approach that combines causal inference and machine learning to understand and utilize causal relationships in data. In current research and applications, traditional machine learning and deep learning models always focus on prediction and pattern recognition. In contrast, causal machine learning goes a step further by revealing causal relationships between different variables. We explore a novel concept called Double Machine Learning that embraces causal machine learning in this research. The core goal is to select independent variables from a gesture identification problem that are causally related to final gesture results. This selection allows us to classify and analyze gestures more efficiently, thereby improving models’ performance and interpretability. Compared to commonly used feature selection methods such as Variance Threshold, Select From Model, Principal Component Analysis, Least Absolute Shrinkage and Selection Operator, Artificial Neural Network, and TabNet, Double Machine Learning methods focus more on causal relationships between variables rather than correlations. Our research shows that variables selected using the Double Machine Learning method perform well under different classification models, with final results significantly better than those of traditional methods. This novel Double Machine Learning-based approach offers researchers a valuable perspective for feature selection and model construction. It enhances the model’s ability to uncover causal relationships within complex data. Variables with causal significance can be more informative than those with only correlative significance, thus improving overall prediction performance and reliability.