Search Results (426)

Introduction: Patient comfort is a central concept in nursing practice, and is particularly important in emergency contexts, where clinical complexity and care overload challenge the provision of humanized care. Katharine Kolcaba’s Theory of Comfort offers a robust theoretical framework for assessing and promoting comfort in multiple domains. The main objective is to psychometrically validate the adapted version of Kolcaba’s Comfort Scale—COLCABA-32—in critically ill patients treated in a Portuguese hospital emergency department. Method: A quantitative, descriptive, cross-sectional study was conducted using a sample of 165 adult patients triaged with urgent clinical priority. Data collection was performed through individual interviews. The COLCABA-32 Scale and the Mini-Mental State Examination (MMSE) were used. Statistical analysis included descriptive statistics, principal component analysis (PCA), internal consistency (Cronbach’s alpha), and correlation with clinical priority according to the Manchester Triage. Results: PCA revealed six factors with eigenvalues greater than 1, explaining 59.01% of the total variance of the scale. The dimensions identified were psycho-emotional comfort and autonomy, physical and symptomatic comfort, relational comfort and information, spiritual comfort, environmental comfort and motivational comfort and hope. The overall Cronbach’s alpha was 0.897, indicating excellent internal consistency. Correlations with clinical priority confirmed partial convergent validity. Conclusions: The COLCABA-32 Scale demonstrated adequate psychometric properties for assessing the comfort of critically ill patients in an emergency setting and is a valid, reliable, and sensitive instrument for the multiple dimensions of comfort, as proposed by Kolcaba. Its application can contribute to more person-centered and evidence-based nursing practices. Full article

Gas Detection Systems (GDSs) are critical safety technologies deployed in semiconductor wafer fabrication facilities to monitor the presence of hazardous gases. A GDS receives input from gas detectors equipped with consumable gas sensors, such as electrochemical (EC) and metal oxide semiconductor (MOS) types, which are used to detect toxic, flammable, or reactive gases. However, over time, sensors degradations, accuracy drift, and cross-sensitivity to interference gases compromise their intended performance. To maintain sensor accuracy and reliability, routine manual calibration is required—an approach that is resource-intensive, time-consuming, and prone to human error, especially in facilities with extensive networks of gas detectors. This systematic review (PROSPERO on 11th October 2025 Registration number: 1166004) explored minimizing or eliminating the dependency on manual calibration. Findings indicate that using properly calibrated gas sensor data can support advanced data analytics and machine learning algorithms to correct accuracy drift and improve gas selectivity. Techniques such as Principal Component Analysis (PCA), Support Vector Machines (SVMs), multivariate regression, and calibration transfer have been effectively applied to differentiate target gases from interferences and compensate for sensor aging and environmental variability. The paper also explores the emerging potential for integrating calibration-free or self-correcting gas sensor systems into existing GDS infrastructures. Despite significant progress, key research challenges persist. These include understanding the dynamics of sensor response drift due to prolonged gas exposure, synchronizing multi-sensor data collection to minimize time-related drift, and aligning ambient sensor signals with gas analytical references. Future research should prioritize the development of application-specific datasets, adaptive environmental compensation models, and hybrid validation frameworks. These advancements will contribute to the realization of intelligent, autonomous, and data-driven gas detection solutions that are robust, scalable, and well-suited to the operational complexities of modern industrial environments. Full article

This paper investigates Electrocardiogram (ECG) rhythm classification using a progressive deep learning framework that combines time–frequency representations with complementary hand-crafted features. In the first stage, ECG signals from the PhysioNet Challenge 2017 dataset are transformed into scalograms and input to diverse architectures, including Simple Convolutional Neural Network (SimpleCNN), Residual Network with 18 Layers (ResNet-18), Convolutional Neural Network-Transformer (CNNTransformer), and Vision Transformer (ViT). ViT achieved the highest accuracy (0.8590) and F1-score (0.8524), demonstrating the feasibility of pure image-based ECG analysis, although scalograms alone showed variability across folds. In the second stage, scalograms were fused with scattering and statistical features, enhancing robustness and interpretability. FusionViT without dimensionality reduction achieved the best performance (accuracy = 0.8623, F1-score = 0.8528), while Fusion ResNet-18 offered a favorable trade-off between accuracy (0.8321) and inference efficiency (0.016 s per sample). The application of Principal Component Analysis (PCA) reduced the dimensionality of the feature from 509 to 27, reducing the computational cost while maintaining competitive performance (FusionViT precision = 0.8590). The results highlight a trade-off between efficiency and fine-grained temporal resolution. Training-time augmentations mitigated class imbalance, enabling lightweight inference (0.006–0.043 s per sample). For real-world use, the framework can run on wearable ECG devices or mobile health apps. Scalogram transformation and feature extraction occur on-device or at the edge, with efficient models like ResNet-18 enabling near real-time monitoring. Abnormal rhythm alerts can be sent instantly to users or clinicians. By combining visual and statistical signal features, optionally reduced with PCA, the framework achieves high accuracy, robustness, and efficiency for practical deployment. Full article

Monitoring ecosystem dynamics in arid regions requires robust indicators that can capture spatial heterogeneity and diverse ecological drivers. In this study, we introduce and evaluate two novel ecological indices: the Arid-region Remote Sensing Ecological Index (ARSEI), specifically designed for desert environments, and the Composite Remote Sensing Ecological Index (CoRSEI), which integrates both desert and non-desert systems. These indices are compared with the traditional Remote Sensing Ecological Index (RSEI) in the Tarim River Basin from 2000 to 2023. Principal component analysis (PCA) revealed that RSEI maintained the highest structural compactness (average PCA1 = 87.49%). In contrast, ARSEI (average PCA1 = 78.62%) enhanced sensitivity to albedo and vegetation (NDVI) in arid environments. Spearman correlation analysis further demonstrated that ARSEI was more strongly correlated with NDVI (ρ = 0.49) and precipitation (ρ = 0.62) than RSEI, confirming its improved responsiveness under water-limited conditions. CoRSEI exhibited higher internal consistency and spatial adaptability (mean values ranging from 0.45 to 0.56), with slight ecological improvements observed between 2000 and 2023. Ecological drivers varied across habitat types. In desert areas, evapotranspiration, precipitation, and soil moisture were the main determinants of ecological status, showing high coupling and synchrony. In non-desert regions, soil moisture and precipitation remained dominant, but vegetation indices and disturbance factors (e.g., fire density) exerted stronger long-term influences. Partial dependence analyses further confirmed nonlinear, region-specific responses, such as the threshold effects of precipitation on vegetation growth. Overall, our findings highlight the importance of differentiated ecological modeling. ARSEI enhances sensitivity in desert ecosystems, whereas CoRSEI captures landscape-scale variability across desert and non-desert regions. Both indices contribute to more accurate long-term ecological assessments in hyper-arid environments. Full article

Background: The automated analysis of intestinal organoids in microscopy images are essential for high-throughput morphological studies, enabling precision and scalability. Traditional manual analysis is time-consuming and subject to observer bias, whereas Machine Learning (ML) approaches have recently demonstrated superior performance. Purpose: This study aims to evaluate YOLO (You Only Look Once) for organoid segmentation and classification, comparing its standalone performance with a hybrid pipeline that integrates DL-based feature extraction and ML classifiers. Methods: The dataset, consisting of 840 light microscopy images and over 23,000 annotated intestinal organoids, was divided into training (756 images) and validation (84 images) sets. Organoids were categorized into four morphological classes: cystic non-budding organoids (Org0), early organoids (Org1), late organoids (Org3), and Spheroids (Sph). YOLO version 10 (YOLOv10) was trained as a segmenter-classifier for the detection and classification of organoids. Performance metrics for YOLOv10 as a standalone model included Average Precision (AP), mean AP at 50% overlap (mAP50), and confusion matrix evaluated on the validation set. In the hybrid pipeline, trained YOLOv10 segmented bounding boxes, and features extracted from these regions using YOLOv10 and ResNet50 were classified with ML algorithms, including Logistic Regression, Naive Bayes, K-Nearest Neighbors (KNN), Random Forest, eXtreme Gradient Boosting (XGBoost), and Multi-Layer Perceptrons (MLP). The performance of these classifiers was assessed using the Receiver Operating Characteristic (ROC) curve and its corresponding Area Under the Curve (AUC), precision, F1 score, and confusion matrix metrics. Principal Component Analysis (PCA) was applied to reduce feature dimensionality while retaining 95% of cumulative variance. To optimize the classification results, an ensemble approach based on AUC-weighted probability fusion was implemented to combine predictions across classifiers. Results: YOLOv10 as a standalone model achieved an overall mAP50 of 0.845, with high AP across all four classes (range 0.797–0.901). In the hybrid pipeline, features extracted with ResNet50 outperformed those extracted with YOLO, with multiple classifiers achieving AUC scores ranging from 0.71 to 0.98 on the validation set. Among all classifiers, Logistic Regression emerged as the best-performing model, achieving the highest AUC scores across multiple classes (range 0.93–0.98). Feature selection using PCA did not improve classification performance. The AUC-weighted ensemble method further enhanced performance, leveraging the strengths of multiple classifiers to optimize prediction, as demonstrated by improved ROC-AUC scores across all organoid classes (range 0.92–0.98). Conclusions: This study demonstrates the effectiveness of YOLOv10 as a standalone model and the robustness of hybrid pipelines combining ResNet50 feature extraction and ML classifiers. Logistic Regression emerged as the best-performing classifier, achieving the highest ROC-AUC across multiple classes. This approach ensures reproducible, automated, and precise morphological analysis, with significant potential for high-throughput organoid studies and live imaging applications. Full article

Helleborus orientalis L. is a valuable winter-flowering and understory landscape plant, but its application and breeding are hindered by poor heat tolerance and the lack of a robust germplasm evaluation system. In this study, 51 Helleborus L. hybrid individuals obtained through manual open pollination were evaluated using coefficient of variation (CV), Shannon–Weaver diversity index (H′), correlation analysis, principal component analysis (PCA), and cluster analysis to assess genetic diversity and ornamental value based on 17 phenotypic traits. The results showed rich phenotypic diversity among the hybrids. Quantitative traits showed CV ranging from 9.48% to 37.99% and H′ between 0.77 and 1.51, with flower count and leaf length being the most variable. Qualitative traits had H′ values from 0.52 to 1.55, with sepal color showing the highest diversity. Significant correlations were detected among heat tolerance, pest resistance, leaf and petiole length, as well as plant and flower form. PCA extracted six principal components accounting for 74.50% of cumulative variance. Cluster analysis classified the 51 germplasms into five groups. Using the AHP model, a comprehensive evaluation system was established, and 13 elite individuals were selected for variety rights application and characterization. This study provides a reference for establishing DUS test guidelines and advancing breeding and utilization of Helleborus L. Full article

As a novel approach, polyfloral honey originating from the three regions of the Caribbean Island of the Dominican Republic (D.R.) was analyzed. Using the HPLC-DAD technique, 10 specific flavonoids (FLV) together with 9 phenolic acids (PHA) were identified and compared with Spanish polyflorals (commercial brands, artisanal beekeepers, and experimental apiaries). On average, the total content of FLV and PHA was much higher in Spanish (14.2 and 20.1 mg/kg) than in D.R. (10.8 and 4.5 mg/kg) honeys. Unlike in Dominican honeys, chrysin (in FLV) and vanillic acid (in PHA) had the greatest impact on Spanish honey, with the latter alone accounting for more than 50% of the quantified PHAs. Unsupervised Principal Component Analysis (PCA) showed that the information provided by both FLV and PHA allowed us to differentiate honeys according to their geographical origin, particularly at the country level. Furthermore, a stepwise discriminant-analysis identified the PHA ferulic acid followed by the FLVs apigenin-7-glucoside, chrysin, and naringenin as the most influential compounds for distinguishing among groups of honeys. The resulting model correctly classified 80.3% of the original and 71.2% of the cross-validated cases, indicating acceptable efficiency and robustness. These findings highlight the potential of the analyzed compounds for the geographical authentication of honey, providing the beekeeping sector with valuable tools for ensuring honey provenance. Full article

Background: Dietary patterns in Eastern Europe are unevenly characterized despite their relevance for public health, food policy, and the sustainability of regional food systems. Objective: This study aimed to identify and compare the main dietary patterns across Eastern European countries (2010–2022) using FAOSTAT food balance data, and to examine their implications for public health and sustainable food systems. Methods: We conducted a comparative ecological analysis of FAOSTAT Food Balance Sheets for ten Eastern European countries (2010–2022). Multi-annual means were standardized as Z-scores. We applied principal component analysis (PCA) to major food groups and to selected subgroups (cereals, meat, vegetable oils), followed by agglomerative hierarchical clustering (Ward, Euclidean). EFSA macronutrient ranges and fiber cut-offs were used solely as descriptive benchmarks. Results: The PCA of major food groups identified two dominant axes separating plant-based patterns (cereals, vegetables) from animal/lipid-centered diets; subgroup analyses reproduced these oppositions (e.g., sunflower vs. rapeseed oils). Hierarchical clustering revealed a stable Central–Eastern core with higher lipid profiles (Czechia, Hungary, Slovakia, partially Poland) and a second pattern with higher carbohydrates and energy (Romania, Ukraine; proximity of Moldova, Belarus, Russian Federation). Countries differed markedly in fiber and energy: Romania showed the highest energy intake, while Slovakia had the lowest fiber, and Ukraine combined very high carbohydrates with low lipids. These structures were robust to sensitivity checks and consistent across biplots, heatmaps, and dendrograms. Conclusions: Eastern Europe comprises coherent dietary subgroups rather than a homogeneous profile. Beyond their public health relevance, these typologies provide an operational map for tailoring dietary guidelines, strengthening food security, and supporting the transition toward sustainable food systems. Future work should link food availability data with individual consumption, environmental indicators, and resilience metrics to inform long-term strategies for sustainable and equitable nutrition. Full article

The design and development of a robust and consistent manufacturing process for monoclonal antibodies (mAbs), augmented by advanced process analytics capabilities, is a key current focus area in the pharmaceutical industry. In this work, we describe the development and operationalization of multivariate statistical process monitoring (MSPM), a data-driven modelling approach, to monitor biopharmaceutical manufacturing processes. This approach helps in understanding the correlations between the various variables and is used for the detection of the deviations and anomalies that may indicate abnormalities or changes in the process compared to the historical dataspace. Therefore, MSPM enables early fault detection with a scope for preventative intervention and corrective actions. In this work, we will additionally cover the value of in silico data in the development of MSPM models, principal component analysis (PCA), and batch modelling methods, as well as refining and validating the models in real time. Full article

Cardiovascular diseases remain a leading cause of mortality worldwide, emphasizing the importance of early diagnosis. Heart sound analysis offers a non-invasive avenue for detecting cardiac abnormalities. This study systematically evaluates the effect of segmentation on phonocardiogram (PCG) classification performance. Unlike conventional fixed-window or HSMM-based methods, a data-adaptive segmentation approach combining Shannon energy and Otsu thresholding is proposed. After segmentation, features are extracted using Empirical Mode Decomposition (EMD) and Mel-Frequency Cepstral Coefficients (MFCCs), followed by classification with k-Nearest Neighbor (kNN), Support Vector Machine (SVM), and Random Forest (RF). Experiments on the PhysioNet/CinC 2016 and Pascal datasets revealed that segmentation markedly enhances classification accuracy. The optimal results were achieved using kNN with segmented EMD features, attaining 99.97% accuracy, 99.98% sensitivity, and 99.96% specificity; segmented MFCC features also provided high accuracy (99.37%). In contrast, non-segmented models yielded substantially lower performance. Principal Component Analysis (PCA) is applied for dimensionality reduction, preserving classification efficiency while minimizing computational cost. These findings demonstrate the critical importance of effective segmentation in heart sound classification and establish the proposed Shannon–Otsu-based method as a robust, interpretable, and resource-efficient tool for automated cardiac diagnostics. Using annotated PhysioNet recordings, segmentation achieved ~90% sensitivity for S1/S2 detection. A limitation is the absence of full segment annotations in the Pascal dataset, which prevents comprehensive timing-error evaluation. Full article

Ensuring the authenticity of meat products is a critical issue for consumer protection, regulatory compliance, and the integrity of local food systems. In this study, attenuated total reflectance Fourier-transform infrared (ATR-FTIR) spectroscopy combined with chemometric and machine learning models was applied to differentiate Maltese from non-Maltese pork. Spectral datasets were subjected to a range of preprocessing techniques, including Savitzky–Golay first and second derivatives, detrending, orthogonal signal correction (OSC), and standard normal variate (SNV). Linear methods such as principal component analysis–linear discriminant analysis (PCA-LDA), the soft independent modeling of class analogy (SIMCA), and partial least squares regression (PLSR) were compared against nonlinear approaches, namely support vector machine regression (SVMR) and artificial neural networks (ANNs). The results revealed that derivative preprocessing consistently enhanced spectral resolution and model robustness, with the fingerprint region (1800–600 cm⁻¹) yielding the highest discriminative power. While PCA-LDA, SIMCA, and PLSR achieved high accuracy, SVMR and ANN models provided a superior predictive performance, with accuracies exceeding 0.99 and lower misclassification rates under external validation. These findings highlight the potential of FTIR spectroscopy combined with nonlinear chemometrics as a rapid, non-destructive, and cost-effective strategy for meat authentication, supporting both consumer safety and sustainable food supply chains. Full article

This study develops a coupled hydropower–ecological optimization model to balance energy production and ecosystem sustainability. The ecological objective is quantified by a composite Eco-Index, derived via Principal Component Analysis from seven key parameters of 32 Indicators of Hydrologic Alteration, enhancing representativeness while reducing computational complexity. Hydrological years are classified into wet, normal, and dry types using the Standardized Runoff Index and runoff quantiles, showing that wet years exhibit the strongest hydropower–ecology coupling, followed by normal and dry years. The optimized average annual hydropower revenues are 3.75 billion USD in wet years, 3.10 billion USD in normal years, and 2.70 billion USD in dry years, with average EI values being 0.35, 0.27 and 0.26, respectively. Spatial analysis identifies Xiaowan and Nuozhadu reservoirs as critical control points sensitive to hydrological variability. Moreover, optimization substantially enhances system resilience and reduces vulnerability. These results demonstrate that coordinated cascade reservoir operation can improve system robustness while signaling a caveat for careful trade-offs between economic and ecological objectives. Full article

Graphite nodularity is a key indicator for evaluating the microstructure quality of ductile iron and plays a crucial role in ensuring product quality and enhancing manufacturing efficiency. Existing research often only focuses on a single type of feature and fails to utilize multi-source information in a coordinated manner. Single-feature methods are difficult to comprehensively capture microstructures, which limits the accuracy and robustness of the model. This study proposes a hybrid estimation model for the graphite nodularity of ductile cast iron based on multi-source feature extraction. A comprehensive feature engineering pipeline was established, incorporating geometric, color, and texture features extracted via Hue-Saturation-Value color space (HSV) histograms, gray level co-occurrence matrix (GLCM), Local Binary Pattern (LBP), and multi-scale Gabor filters. Dimensionality reduction was performed using Principal Component Analysis (PCA) to mitigate redundancy. An improved watershed algorithm combined with intelligent filtering was used for accurate particle segmentation. Several machine learning algorithms, including Support Vector Regression (SVR), Multi-Layer Perceptron (MLP), Random Forest (RF), Gradient Boosting Regressor (GBR), eXtreme Gradient Boosting (XGBoost) and Categorical Boosting (CatBoost), are applied to estimate graphite nodularity based on geometric features (GFs) and feature extraction. Experimental results demonstrate that the CatBoost model trained on fused features achieves high estimation accuracy and stability for geometric parameters, with R-squared (R²) exceeding 0.98. Furthermore, introducing geometric features into the fusion set enhances model generalization and suppresses overfitting. This framework offers an efficient and robust approach for intelligent analysis of metallographic images and provides valuable support for automated quality assessment in casting production. Full article

Background: Cardiovascular diseases (CVDs) remain the primary cause of global mortality, with arterial hypertension, ischemic heart disease (IHD), and cerebrovascular accident (CVA) forming a progressive continuum from early risk factors to severe outcomes. While numerous studies focus on isolated biomarkers, few integrate multidimensional visualization with artificial intelligence to reveal hidden, clinically relevant patterns. Methods: We conducted a comprehensive analysis of 106 patients using an integrated framework that combined clinical, biochemical, and lifestyle data. Parameters included renal function (glomerular filtration rate, cystatin C), inflammatory markers, lipid profile, enzymatic activity, and behavioral factors. After normalization and imputation, we applied correlation analysis, parallel coordinates visualization, t-distributed stochastic neighbor embedding (t-SNE) with k-means clustering, principal component analysis (PCA), and Random Forest modeling with SHAP (SHapley Additive exPlanations) interpretation. Bootstrap resampling was used to estimate 95% confidence intervals for mean absolute SHAP values, assessing feature stability. Results: Consistent patterns across outcomes revealed impaired renal function, reduced physical activity, and high hypertension prevalence in IHD and CVA. t-SNE clustering achieved complete separation of a high-risk group (100% CVD-positive) from a predominantly low-risk group (7.8% CVD rate), demonstrating unsupervised validation of biomarker discriminative power. PCA confirmed multidimensional structure, while Random Forest identified renal function, hypertension status, and physical activity as dominant predictors, achieving robust performance (Accuracy 0.818; AUC-ROC 0.854). SHAP analysis identified arterial hypertension, BMI, and physical inactivity as dominant predictors, complemented by renal biomarkers (GFR, cystatin) and NT-proBNP. Conclusions: This study pioneers the integration of multidimensional visualization and AI-driven analysis for CVD risk profiling, enabling interpretable, data-driven identification of high- and low-risk clusters. Despite the limited single-center cohort (n = 106) and cross-sectional design, the findings highlight the potential of interpretable models for precision prevention and transparent decision support in cardiovascular aging research. Full article

Polycyclic aromatic hydrocarbons (PAHs) are persistent organic pollutants with significant ecological and public health implications, particularly in urban wetlands exposed to chronic anthropogenic stress. This study evaluates the occurrence, spatial distribution, seasonal variability, and ecological risk of three low molecular weight PAHs—naphthalene (NAP), phenanthrene (PHEN), and anthracene (ANT)—in surface waters of Caño La Malaria, the main freshwater source of Cucharillas Marsh, Puerto Rico’s largest urban wetland. Surface water samples were collected at four locations during both wet- and dry-season campaigns. Samples were extracted and quantified by GC-MS. NAP was the dominant compound, Σ3PAHs concentrations ranging from 7.4 to 2198.8 ng/L, with higher wet-season levels (mean = 745.79 ng/L) than dry-season levels (mean = 186.71 ng/L); most wet-season samples fell within the mild-to-moderate contamination category. Compositional shifts indicated increased levels of PHEN and ANT during the wet season. No significant spatial differences were found (p = 0.753), and high correlations between sites (r = 0.96) suggest uniform input sources. Diagnostic ratios, inter-species correlations, and principal component analysis (PCA) consistently indicated a predominant pyrogenic origin, with robust PHEN–ANT correlation (r = 0.824) confirming shared combustion-related sources. PCA revealed a clear separation between dry- and wet-season samples, with the latter showing greater variability and stronger associations with NAP and ANT. Ecological risk assessment using hazard quotients (HQ_water) indicated negligible acute toxicity risk across all sites and seasons (<0.01); the highest HQ_water (0.0095), observed upstream during the wet season, remained within this range. However, benchmark exceedances by PHEN and ANT suggest potential chronic risks not captured by the acute ERA framework. These findings support integrated watershed management practices to mitigate PAH pollution and strengthen long-term ecological health in tropical urban wetlands. Full article