Search Results (171)

Background/Objectives: With increasing life expectancy, interest in healthy aging has grown substantially. Dietary habits are among the key factors that contribute to achieving healthy aging. This study analyzes the relationship between dietary habits and the age–health association in older adults, using the first two years of data from an ongoing annual cohort study conducted in a region of Japan. Methods: We used observational data from approximately 1200 community-dwelling males and females aged 55 to 75 at baseline, drawing on the first two years of a ten-year annual cohort study conducted from 2023 to 2032. First, dietary habits were classified using an ordinal latent block model (OLBM), a model-based clustering approach applied to food frequency questionnaire (FFQ) data. We then examined whether the age–health gradient—measured across 33 indicators—differed significantly across the derived dietary habit types, using random effects models. Results: Dietary habits in the analyzed sample were categorized into six distinct types. Parameter estimates from the model suggest that the extracted patterns represent a continuum ranging from low to high dietary diversity. Regression analyses indicated that, in females, a negative association between age and LDL-C levels was observed among those with highly diverse dietary habits. Conclusions: The data-driven classification of dietary habits based on FFQ responses highlights the potential importance of dietary diversity. Full article

The accelerated pace of urbanization has significant effects on the community composition, structure, regional distribution, and diversity characteristics of vegetation within urban river corridors. Spontaneous plants have strong environmental adaptability, high plasticity, and shorter life cycles; they also operate largely independently of human control. As a result, they are widely distributed throughout urban river corridors, and their ability to respond rapidly to heterogeneous habitats within these corridors makes them an ideal subject for studying the reciprocal mechanisms between rapid urbanization and riverine biodiversity. Based on a survey of 208 plots across six river corridors in Changchun, China, we found that the hydrological gradient was the strongest predictor of spontaneous herbaceous community distribution among the environmental factors examined. A total of 181 native herbaceous plant species, belonging to 55 families and 140 genera, were recorded. The Asteraceae, Poaceae, Fabaceae, Lamiaceae, and Polygonaceae families dominated. TWINSPAN classification divided the native herbaceous plant communities into 11 types, with the dominant species being predominantly low-growing perennial herbaceous plants. Canonical correspondence analysis (CCA) ordination confirmed this pattern, showing that the community distribution from aquatic to terrestrial habitats primarily aligned along the first CCA axis (defined by water depth and canopy cover), while the second axis reflected gradients in anthropogenic disturbance and slope. Thus, even in intensively managed urban rivers, natural hydrological processes remain pivotal in shaping riparian plant community composition and enhancing biodiversity. This study provides a scientific foundation for the conservation and sustainable utilization of plant resources in urban river corridors. Full article

Industry 5.0 emphasizes human-centered integration of artificial intelligence in industrial contexts, yet successful adoption depends critically on workforce perception and acceptance. This research develops and validates a machine learning framework for predicting AI-related perceptions and expected impacts in the construction industry under small sample constraints typical of specialized industrial surveys. Specifically, the study aims to develop and empirically validate a predictive AI decision support model that estimates the expected impact of AI adoption in the construction sector based on digital competencies, ICT utilization, AI training and experience, and AI usage at both individual and organizational levels, operationalized through a composite AI Impact Index and two process-oriented outcomes (perceived task automation and perceived cost reduction). Using a dataset of 51 survey responses from Slovak construction professionals collected in 2025, we implement a methodologically rigorous approach specifically designed for limited-data regimes. The framework encompasses ordinal target simplification from five to three classes, dimensionality reduction through theoretically grounded composite indices reducing features from 15 to 7, exclusive deployment of low variance regularized models, and leave-one-out cross-validation for unbiased performance estimation. The optimal model (Lasso regression with recursive feature elimination) predicts cost reduction perception with R² = 0.501, MAE = 0.551, and RMSE = 0.709, while six classification targets achieve weighted F1 = 0.681, representing statistically optimal performance given sample constraints and perception measurement variability. Comparative evaluation confirms regularized models outperform high variance alternatives: random forest (R² = 0.412) and gradient boosting (R² = 0.292) exhibit substantially lower generalization performance, empirically validating the bias-variance trade-off rationale. Key methodological contributions include explicit bias-variance optimization preventing overfitting, feature selection via RFE reducing input space to six predictors (personal AI usage, AI impact on budgeting, ICT utilization, AI training, company size, and age), and demonstration that principled statistical approaches achieve meaningful predictions without requiring large-scale datasets or complex architectures. The framework provides a replicable blueprint for perception and impact prediction in data-constrained Industry 5.0 contexts, enabling targeted interventions, including customized training programs, strategic communication prioritization, and resource allocation for change management initiatives aligned with predicted adoption patterns. Full article

Background: This study investigated the association between tongue strength, measured using the Iowa Oral Performance Instrument (IOPI), and upper airway collapse patterns observed during drug-induced sleep endoscopy (DISE) in patients with obstructive sleep apnea syndrome (OSAS). Methods: Thirty patients who underwent polysomnography, DISE, and tongue pressure measurement were retrospectively analyzed. Upper airway collapse was assessed using the VOTE classification. The tongue strength task performed using the IOPI requires participants to compress an air-filled bulb placed on the hard palate with anterior tongue to generate maximum isometric tongue pressure. Group comparisons and ordinal logistic regression with Firth’s penalized likelihood were performed to evaluate associations between tongue pressure and collapse patterns. Results: The participants had a mean age of 41.5 ± 12.5 years, including 27 males and 3 females. The mean tongue strength was 50.4 ± 15.3 kPa, with no significant sex-related differences. Patients with tongue strength <40 kPa showed significantly higher odds of tongue base collapse (adjusted OR 12.79, 95% CI 1.30–126.91) and epiglottic collapse (adjusted OR 54.05, 95% CI 1.66–1760.25). No significant differences were observed for velum or oropharyngeal collapse. Conclusions: Lower tongue strength was associated with increased likelihood of tongue base collapse during DISE. Tongue strength measurement may serve as a practical, non-invasive tool for identifying patients with reduced tongue muscle function and potential tongue-related airway obstruction. Full article

Background: Alzheimer disease (AD) is a neurodegenerative condition that progressively develops structural changes in the brain, resulting in different stages of severity, which makes accurate multiclass classification from magnetic resonance imaging (MRI) challenging. Despite promising outcomes of deep learning models, a great number of current methods disregard disease progression, suffer from evaluation leakage, or lack interpretability. Objectives: This paper introduces DeepAttentionADNet, a lightweight hybrid CNN–Transformer framework designed for multiclass staging of Alzheimer’s disease using MRI images. Methods: The proposed model integrates convolutional feature extraction with transformer-based global context modeling. To capture the ordered nature of disease severity, a progression-aware ordinal learning objective is proposed. Moreover, consistency regularization is utilized to enhance robustness by imposing consistent prediction with spatial perturbation. A leakage-free k-fold cross-validation protocol is adopted, in which data splitting is performed prior to augmentation. Also, to promote interpretability, token-level importance maps based on transformer embeddings are utilized to visualize spatial regions that were used to make classification decisions. Results: The experimental findings on a multiclass MRI dataset of Alzheimer disease demonstrate consistent and high performance across cross-validation folds (mean F1-score (0.991 ± 0.003) and AUROC (0.9998 ± 0.0002)), without losing transparency and progress awareness. Conclusions: The proposed framework provided a robust and interpretable method of Alzheimer disease severity classification using MRI. Full article

Background/Objectives: Cochlear implants (CIs) constitute a viable method for auditory rehabilitation in patients with profound sensorineural hearing loss after temporal bone fractures (TBFs). These patients comprise a challenging population due to the anatomical deformity and neural injury. Methods: By performing this systematic review, we attempted to evaluate the viability of CIs in the context of TBF. The literature search, across Pubmed/MEDLINE, Scopus and Google Scholar, was performed under the PRISMA guidelines. The selected time period was from December 1995 to September 2025. The final analysis included 11 manuscripts. The majority of the studies were retrospective case series with a moderate risk of bias. Results: The primary outcome was postoperative auditory function, evaluated with speech perception tasks and aided sound-field pure-tone audiometry. The secondary outcomes were the report of radiological and electrophysiologic prognosticators of implants’ viability, timing of surgery, procedural feasibility and complications. Across the studies, CIs conferred meaningful auditory benefit when the cochlear nerve was intact. High-Resolution Computed Tomography (CT) was utilized for TBF classification and cochlear patency, whereas Magnetic Resonance Imaging (MRI) and a promontory test were crucial for the assessment of neural integrity. Prompt placement, optimally within 12 months after trauma, was related to improved outcomes by limiting cochlear fibrosis and ossification. Despite patients’ impedance fluctuation, restricted speech perception in noise and frequent abnormal facial nerve excitation, the overall audiologic and speech discrimination results are comparable to non-trauma recipients. Conclusions: A CI appears to be the choice of treatment over auditory brainstem implants, as long as the cochlear nerve remains intact. Rapid implantation in well-selected patients coupled with ordinal mapping and follow-up can restore dysfunctional hearing and improve patients’ quality of life. Full article

Background: Low and middle-income countries (LMICs) such as Mexico are experiencing rapid population aging, accompanied by increasing levels of functional dependency and growing long-term care (LTC) needs. Objectives: We aimed to identify the factors associated with varying levels of functional dependency in order to assist population health planning and LTC policy in aging populations in Mexico. Methods: This cross-sectional study analyzed data from the 2021 wave of the Mexican Health and Aging Study (MHAS). Functional dependency was assessed through a modified Autonomie Gérontologie Groupes Iso-Ressources (AGGIR) scale, adapted to incorporate cognitive and physical assessments suitable for the Mexican context. Socioeconomic, health-related, and psychological variables were examined using ordinal logistic regression models. Results: Among 8049 participants included in the analysis, 87.08% were classified with non-to-mild dependency, 9.13% with moderate dependency, and 3.79% with severe dependency. More severe levels of functional dependency were associated with older age, lower educational attainment, not having a partner (being single, widowed, separated or divorced), and the presence of chronic conditions such as hypertension and cardiovascular disease. Conclusions: In contrast, higher educational attainment and regular physical activity were associated with less severe levels of dependency. These associations highlight the multifactorial nature of dependency in later life. The application of a graded, multidimensional dependency classification provides a more comprehensive and differentiated understanding of care needs than binary functional measures. This population-level perspective may support the prioritization of healthy aging strategies and long-term care planning in rapidly aging middle-income settings such as Mexico. Full article

Background/Objectives: Cellulite is a common aesthetic condition in women, traditionally assessed using visual inspection and palpation-based scales that are inherently subjective. Therefore, image-based methods that may support standardized severity grading are of growing interest. To evaluate infrared thermography as an imaging-based method for grading cellulite severity and to perform methodological validation of a newly developed thermographic classification scale by comparing it with clinical palpation and anthropometric parameters. Methods: This retrospective, non-interventional study analyzed anonymized clinical and thermographic data from 81 women with clinically assessed cellulite. Cellulite severity was evaluated using the Nürnberger–Müller palpation scale and a newly developed five-point thermographic scale based on skin surface temperature differentials and histogram pattern analysis. The associations between the assessment methods were evaluated using ordinal statistical measures, and agreement was assessed using weighted Cohen’s kappa statistics. Results: Thermographic grading demonstrated high agreement with palpation-based assessment, with a percentage agreement of 93.8% and an almost perfect agreement based on weighted Cohen’s κ. A strong ordinal association was observed between the methods. Thermography consistently classified a subset of cases as one grade higher compared with palpation. No statistically significant associations were observed between thermographic grade and body mass index or waist-to-hip ratio. Conclusions: Infrared thermography enables image-based grading of cellulite severity and shows a strong concordance with established palpation scales. The proposed thermographic classification provides preliminary methodological validation of an imaging-based grading approach. Further multicenter studies involving multiple assessors and diverse populations are required to assess reproducibility, specificity, and potential clinical applicability. Full article

The article examines the implementation of 3D printing in civil protection and crisis management with a focus on the educational process, while 3D printing technology enables the creation of various teaching aids that streamline teaching and enrich theoretical knowledge. The empirical part of the study is based on a quantitative questionnaire survey among students of the Faculty of Safety Engineering of the University of Žilina in Žilina, with hypotheses set in advance and forming the basis for the construction of the questionnaire. The questionnaire collected data on the subjective evaluation of 3D printing through continuous, nominal, and ordinal responses and was completed by 277 students. Statistical methods of simple and group classification, as well as t-test, ANOVA, Kruskal–Wallis and Pearson’s correlation analysis were used to evaluate the data. Statistical significance was used to determine whether observed differences and relationships were unlikely to have arisen by chance. In addition, effect size measures were used in correlation and regression analyses to assess the strength and practical relevance of statistically significant relationships. The results of the study show that 3D printing significantly contributes to improving education and preparedness in civil protection, as it allows for more material-efficient and flexible production of educational aids compared to traditional custom production. Thus, it supports the development of more resilient communities and contributes to long-term sustainability. The findings confirmed that 3D printing is a suitable tool for improving public preparedness for emergencies. Full article

Deep learning models have advanced rapidly, leading to claims that they now match or exceed human performance. However, such claims are often based on closed-set conditions with fixed labels, extensive supervised training, and do not considering differences between the two systems. Recent findings also indicate that some models align more closely with human categorisation behaviour, whereas other studies argue that even highly accurate models diverge from human behaviour. Following principles from comparative psychology and imposing similar constraints on both systems, this study investigates whether these models can achieve human-level accuracy and human-like categorisation through three experiments using subsets of the ObjectNet dataset. Experiment 1 examined performance under varying presentation times and task complexities, showing that while recent models can match or exceed humans under conditions optimised for machines, they struggle to generalise to certain real-world categories without fine-tuning or task-specific zero-shot classification. Experiment 2 tested whether human performance remains stable when shifting from N-way categorisation to a free-naming task, while machine performance declines without fine-tuning; the results supported this prediction. Additional analyses separated detection from classification, showing that object isolation improved performance for both humans and machines. Experiment 3 investigated individual differences in human performance and whether models capture the qualitative ordinal relationships characterising human categorisation behaviour; only the multimodal CoCa model achieved this. These findings clarify the extent to which current models approximate human categorisation behaviour beyond mere accuracy and highlight the importance of incorporating principles from comparative psychology while considering individual differences. Full article

Metabolic acidosis is common after kidney transplantation and has been linked to adverse renal outcomes. However, its relationship with histological injury in kidney allografts remains poorly characterized. We aimed to explore the association between metabolic acidosis and histopathological features in kidney allograft biopsies. This single-center, cross-sectional observational study included 63 adult kidney transplant recipients who underwent clinically indicated allograft biopsies. Metabolic acidosis was defined as a serum bicarbonate level < 22 mmol/L at the time of biopsy. Histological lesions were assessed according to the Banff classification. Lesion severity was evaluated using descriptive statistics, nonparametric comparisons, ordinal logistic regression, and multivariable logistic regression models adjusted for renal function, proteinuria, and time from transplantation. Sensitivity analyses additionally adjusted for hemoglobin and donor-related variables. Patients with metabolic acidosis exhibited numerically higher severity scores for both acute inflammatory lesions and chronic histological changes, including total inflammation and interstitial fibrosis/tubular atrophy (IFTA). Across ordinal analyses and multivariable regression models, consistent directional trends toward a greater histological injury burden were observed among acidotic patients; however, none of these associations reached statistical significance, and confidence intervals were wide. Sensitivity analyses yielded directionally consistent effect estimates. In this biopsy-based analysis, metabolic acidosis showed consistent directional trends toward a higher burden of inflammatory and chronic histological lesions, although these findings did not reach statistical significance. Full article

Diabetic retinopathy (DR) is a major cause of preventable vision loss, and its early detection is essential for timely clinical intervention. However, existing deep learning-based DR recognition methods still face two fundamental challenges: substantial lesion-scale variability and significant background noise in retinal fundus images. To address these issues, we propose a lightweight framework named Multi-Scale Soft-Thresholding Attention Network (MSA-Net). The model integrates three components: (1) parallel multi-scale convolutional branches to capture lesions of different spatial sizes; (2) a soft-thresholding attention module to suppress noise-dominated responses; and (3) hierarchical feature fusion to enhance cross-layer representation consistency. A squeeze-and-excitation module is further incorporated for channel recalibration. On the APTOS 2019 dataset, MSA-Net achieves 97.54% accuracy and 0.991 AUC-ROC for binary DR recognition. We further evaluate five-class DR grading on APTOS2019 with 5-fold stratified cross-validation, achieving 82.71 ± 1.25% accuracy and 0.8937 ± 0.0142 QWK, indicating stable performance for ordinal severity classification. With only 4.54 M parameters, MSA-Net remains lightweight and suitable for deployment in resource-constrained DR screening environments. Full article

Background: BI-RADS (Breast Imaging Reporting and Data System) mammogram classification is central to early breast cancer detection. Despite being an ordinal scale that reflects increasing levels of malignancy suspicion, most models treat BI-RADS as a nominal task using cross-entropy loss, thereby disregarding the inherent class order. This mismatch between the clinical severity of misclassification and the model’s optimization objective remains underexplored. Methods: We systematically evaluate whether incorporating ordinal-aware loss functions improves BI-RADS classification performance under controlled, architecture-fixed conditions and dataset imbalance. Using a unified training pipeline across multiple datasets, we compare ordinal losses to standard cross-entropy, analyzing the effect of dataset- and label-level balancing. Area under the receiver operating characteristic curve (AUROC) and macro-F1 scores are reported as averages over five seeds. Results: Balanced sampling across datasets during training led to statistically significant improvements. Ordinal loss functions, such as Earth Mover Distance (EMD), consistently achieved higher performance across multiple metrics compared to conventional cross-entropy approaches commonly reported in the literature. Improvements were particularly evident in reducing severe misclassifications, demonstrating that aligning the learning objective with the ordinal structure of BI-RADS enhances robustness and clinical relevance. Conclusions: Aligning the learning objective with the ordinal BI-RADS structure substantially improves classification accuracy without changing the underlying architecture. These findings emphasize the importance of loss design, regularization, and data-balancing strategies in medical AI, supporting more reliable breast cancer screening. Full article

The diverse rating scales used by brokerage firms pose significant challenges for aggregating analyst recommendations in financial research. We develop a momentum-based normalization framework that transforms heterogeneous rating changes into standardized sentiment signals using firm-relative, past-only empirical distribution functions with event-based lookback and expanding global quantile classification. Using 68,660 rating events from 270 brokerage firms covering 106 large-cap U.S. stocks (2019–2025), our approach generates statistically significant Buy–Sell spreads at all horizons: 1-month (0.96%, t = 3.07, p = 0.002), 2-month (1.36%, t = 3.07, p = 0.002), and 3-month (1.94%, t = 3.66, p < 0.001). Fama–French six-factor regressions confirm 13.6% annualized alpha for Buy signals (t = 3.81) after controlling for market, size, value, profitability, investment, and momentum factors. True out-of-sample validation on May–September 2025 data achieves 107% retention of in-sample 1-month performance (four of five months positive), indicating robust signal generalization. The framework provides a theoretically grounded and empirically validated methodology for standardizing analyst sentiment suitable for quantitative investment strategies and academic research. Full article

Accurate prediction of soil texture is essential for effective soil management, precision agriculture, and hydrological modeling. This study proposes a novel, data-driven approach for estimating soil texture without the need for laboratory-based analysis. High-frequency in situ soil moisture measurements from EnviroSCAN (Sentek Technologies, Stepney, Australia) sensors and satellite-derived vegetation indices (NDVI) from Sentinel-2 were collected across 25 sites in Hungary. Temporal soil moisture dynamics were encoded using a Long Short-Term Memory (LSTM) neural network, designed to capture soil-specific hydrological response behavior from time-series data. The resulting latent embeddings were subsequently used within an ordinal regression framework to predict ordered soil texture classes, explicitly enforcing physical consistency between classes. Model performance was evaluated using leave-one-soil-out cross-validation, achieving an overall classification accuracy of 0.54 and a mean absolute error (MAE) of 0.50, indicating predominantly adjacent-class errors. The proposed approach demonstrates that soil texture can be inferred from dynamic environmental responses alone, offering a transferable alternative to fraction-based regression models and supporting scalable sensor calibration and digital soil mapping in data-scarce regions. Full article