Search Results (635)

Background/Objectives: Automatic classification of ECG signal arrhythmias plays a vital role in early cardiovascular diagnostics by enabling prompt detection of life-threatening conditions. Manual ECG interpretation is labor-intensive and susceptible to errors, highlighting the demand for automated, scalable approaches. Deep learning (DL) methods are effective in ECG analysis due to their ability to learn complex patterns from raw signals. Methods: This study introduces two models: a custom convolutional neural network (CNN) with a dual-branch architecture for processing ECG signals and demographic data (e.g., age, gender), and a modified VGG16 model adapted for multi-branch input. Using the PTB-XL dataset, a widely adopted large-scale ECG database with over 20,000 recordings, the models were evaluated on binary, multiclass, and subclass classification tasks across 2, 5, 10, and 15 disease categories. Advanced preprocessing techniques, combined with demographic features, significantly enhanced performance. Results: The CNN model achieved up to 97.78% accuracy in binary classification and 79.7% in multiclass tasks, outperforming the VGG16 model (97.38% and 76.53%, respectively) and state-of-the-art benchmarks like CNN-LSTM and CNN entropy features. This study also emphasizes interpretability, providing lead-specific insights into ECG contributions to promote clinical transparency. Conclusions: These results confirm the models’ potential for accurate, explainable arrhythmia detection and their applicability in real-world healthcare diagnostics. Full article

Background/Objectives: Inborn errors of immunity (IEIs) represent a wide spectrum of diseases characterized by a predisposition to recurrent infections, as well as increased susceptibility to autoimmune, atopic, and autoinflammatory diseases and malignancies. The aim of this study was to report the registry-based frequency and describe the clinical characteristics of IEIs among patients in the Republic of Kazakhstan. Methods: We analyzed data from 269 patients belonging to 204 families who were either self-referred or referred by healthcare providers to the University Medical Center of Nazarbayev University with suspected IEIs. All patients resided in various regions across Kazakhstan. Results: A total of 269 diagnosed cases were identified in the national registry. The estimated prevalence was 1.3 per 100,000 population. The gender ratio was nearly equal, with 139 males and 130 females. The median age at diagnosis was 5 years (range: 1 month to 70 years), while the mean age was 11.3 years. The most common diagnosis was humoral immunodeficiency, observed in 120 individuals (44.6%), followed by complement deficiencies in 83 individuals (30.8%). Combined immunodeficiencies with syndromic features were found in 35 patients (13%), and phagocytic cell defects were identified in 12 patients (4.5%). The predominant clinical manifestations included severe recurrent infections and autoimmune cytopenias, while atopic and autoinflammatory symptoms were reported less frequently. Conclusions: These findings contribute to a better understanding of the registry-based distribution and clinical spectrum of IEIs in Kazakhstan and underscore the importance of early diagnosis and targeted care for affected individuals. Full article

Background/Objectives: Depression, anxiety and apathy are often associated with subjective cognitive complaints (SCCs) in people with Parkinson’s disease (PwPD) without cognitive impairment. Cognitive reserve (CR) enhances emotional resilience, allowing people to better cope with stress and emotional challenges, factors affecting quality of life. We aimed to explore the relationship between CR and mood/anxiety in cognitively intact PwPD with and without SCCs. Methods: In this cross-sectional study we enrolled 133 PwPD and normal cognitive function (age 59.8 ± 6.7 years; disease duration 9.0 ± 5.5 years; male/female 84/49). We assessed cognitive reserve (CR scale), subjective cognitive complaints (with PD-CFRS), QoL (PDQ8), mood, anxiety and apathy (BDI-II; STAI, PAS, Apathy scales). We used a t-test to compare groups (with/without SCC; M/F); correlations and moderation analysis to evaluate the relation between CR and behavioral features and the interplay between CR, behavioral discomfort and QoL. Results: The group with SCCs had significantly (p < 0.05) higher scores in PDQ8, Apathy, STAI, PAS-C and BDI-II scales than those with no SCCs. Males with SCCs had higher scores in PDQ8, Apathy scale and BDI-II while females differed in PDQ8 and Apathy scale scores. In the SCC group, late-life CR was negatively correlated with PAS-C (avoidance behavior) and BDI-II; correlations were confirmed in the male group where CR also correlated with PDQ-8 and PAS persistent anxiety. Conclusions: PwPD and SCCs are more depressed and anxious compared to people without SCCs. Furthermore, we found a relationship between depressive symptoms, anxiety and CR: PwPD with SCCs may rely on cognitive reserve to better cope with the feeling of anxiety and depression, especially in male gender. Full article

Background: Mild Cognitive Impairment (MCI) represents an intermediate stage between normal cognitive aging and Alzheimer’s Disease (AD). Early and accurate identification of MCI is crucial for implementing interventions that may delay or prevent further cognitive decline. This study aims to develop a machine learning-based model for differentiating between Cognitively Normal (CN) individuals and MCI patients using data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Methods: An ensemble classification approach was designed by integrating Extra Trees, Random Forest, and Light Gradient Boosting Machine (LightGBM) algorithms. Feature selection emphasized clinically relevant biomarkers, including Amyloid-β 42, phosphorylated tau, diastolic blood pressure, age, and gender. The dataset was split into training and held-out test sets. A probability thresholding strategy was employed to flag uncertain predictions for potential deferral, enhancing model reliability in borderline cases. Results: The final ensemble model achieved an accuracy of 83.2%, a recall of 80.2%, and a precision of 86.3% on the independent test set. The probability thresholding mechanism flagged 23.3% of cases as uncertain, allowing the system to abstain from low-confidence predictions. This strategy improved clinical interpretability and minimized the risk of misclassification in ambiguous cases. Conclusions: The proposed AI-driven ensemble model demonstrates strong performance in classifying MCI versus CN individuals using multimodal ADNI data. Incorporating a deferral mechanism through uncertainty estimation further enhances the model’s clinical utility. These findings support the integration of machine learning tools into early screening workflows for cognitive impairment. Full article

Continuous blood pressure (BP) monitoring provides valuable insight into the body’s dynamic cardiovascular regulation across various physiological states such as physical activity, emotional stress, postural changes, and sleep. Continuous BP monitoring captures different variations in systolic and diastolic pressures, reflecting autonomic nervous system activity, vascular compliance, and circadian rhythms. This enables early identification of abnormal BP trends and allows for timely diagnosis and interventions to reduce the risk of cardiovascular diseases (CVDs) such as hypertension, stroke, heart failure, and chronic kidney disease as well as chronic stress or anxiety disorders. To facilitate continuous BP monitoring, we propose an AI-powered estimation framework. The proposed framework first uses an expert-driven feature engineering approach that systematically extracts physiological features from photoplethysmogram (PPG)-based arterial pulse waveforms (APWs). Extracted features include pulse rate, ascending/descending times, pulse width, slopes, intensity variations, and waveform areas. These features are fused with demographic data (age, gender, height, weight, BMI) to enhance model robustness and accuracy across diverse populations. The framework utilizes a Tab-Transformer to learn rich feature embeddings, which are then processed through an ensemble machine learning framework consisting of CatBoost, XGBoost, and LightGBM. Evaluated on a dataset of 1000 subjects, the model achieves Mean Absolute Errors (MAE) of 3.87 mmHg (SBP) and 2.50 mmHg (DBP), meeting British Hypertension Society (BHS) Grade A and Association for the Advancement of Medical Instrumentation (AAMI) standards. The proposed architecture advances non-invasive, AI-driven solutions for dynamic cardiovascular health monitoring. Full article

Speaker profiling systems are often evaluated on a single corpus, which complicates reliable comparison. We present a fully reproducible evaluation pipeline that trains Convolutional Neural Networks (CNNs) and Long-Short Term Memory (LSTM) models independently on three speech corpora representing distinct recording conditions—studio-quality TIMIT, crowdsourced Mozilla Common Voice, and in-the-wild VoxCeleb1. All models share the same architecture, optimizer, and data preprocessing; no corpus-specific hyperparameter tuning is applied. We perform a detailed preprocessing and feature extraction procedure, evaluating multiple configurations and validating their applicability and effectiveness in improving the obtained results. A feature analysis shows that Mel spectrograms benefit CNNs, whereas Mel Frequency Cepstral Coefficients (MFCCs) suit LSTMs, and that the optimal Mel-bin count grows with corpus Signal Noise Rate (SNR). With this fixed recipe, EfficientNet achieves 99.82% gender accuracy on Common Voice (+1.25 pp over the previous best) and 98.86% on VoxCeleb1 (+0.57 pp). MobileNet attains 99.86% age-group accuracy on Common Voice (+2.86 pp) and a 5.35-year MAE for age estimation on TIMIT using a lightweight configuration. The consistent, near-state-of-the-art results across three acoustically diverse datasets substantiate the robustness and versatility of the proposed pipeline. Code and pre-trained weights are released to facilitate downstream research. Full article

Background: Hearing loss is increasingly prevalent and poses a significant public health concern. While both aging and occupational noise exposure are recognized contributors, their interactive effects and gender-specific patterns remain underexplored. Methods: This cross-sectional study analyzed data from 135,251 employees in Jiangsu Province, China. Demographic information, noise exposure metrics, and hearing thresholds were obtained through field measurements, questionnaires, and audiometric testing. Multivariate logistic regression, restricted cubic spline modeling, and interaction analyses were conducted. Machine learning models were employed to assess feature importance. Results: A nonlinear relationship between age and high-frequency hearing loss (HFHL) was identified, with a critical inflection point at 37.8 years. Noise exposure significantly amplified HFHL risk, particularly in older adults (OR = 2.564; 95% CI: 2.456–2.677, p < 0.001), with consistent findings across genders. Men exhibited greater susceptibility at high frequencies, even after adjusting for age and co-exposures. Aging and noise exposure have a joint association with hearing loss (OR = 2.564; 95% CI: 2.456–2.677, p < 0.001) and an interactive association (additive interaction: RERI = 2.075, AP = 0.502, SI = 2.967; multiplicative interaction: OR = 1.265; 95% CI: 1.176–1.36, p < 0.001). And machine learning also confirmed age, gender, and noise exposure as key predictors. Conclusions: Aging and occupational noise exert synergistic effects on auditory decline, with distinct gender disparities. These findings highlight the need for integrated, demographically tailored occupational health strategies. Machine learning approaches further validate key risk factors and support targeted screening for hearing loss prevention. Full article

The present study adopts the social constructivism theory and consumer decision-making process model with the aim of examining the social identity that consumers build through the purchase of electric vehicles (EVs) in line with their income, age, gender, and education. The study’s findings indicate that this social identity, shaped by income, age, gender and education, exerts a significant influence on consumer decision-making behavior. This identity is shaped not only by the make and model of EVs chosen, but also by their preferences for vehicle performance and technical features. The adoption of EVs by consumers is driven by dual objectives: the fulfilment of practical needs and the shaping of social identities in social interactions that correspond to their income, age, gender, and education. The study’s findings are of significant value in understanding the social identity aspirations of consumers in the electric vehicle consumer market, and provide a theoretical foundation for future electric vehicle companies to create products and corporate cultures that meet their target customers, thereby effectively promoting the popularization of electric vehicles. Full article

Background: Cardiovascular diseases are the leading cause of global mortality, with 80% of coronary heart disease in patients over 65. Understanding aging cardiovascular structures is crucial. Photon-counting computed tomography (PCCT) offers improved spatial and temporal resolution and better signal-to-noise ratio, enabling texture analysis in clinical routines. Detecting structural changes in aging left-ventricular myocardium may help predict cardiovascular risk. Methods: In this retrospective, single-center, IRB-approved study, 90 patients underwent ECG-gated contrast-enhanced cardiac CT using dual-source PCCT (NAEOTOM Alpha, Siemens). Patients were divided into two age groups (50–60 years and 70–80 years). The left ventricular myocardium was segmented semi-automatically, and radiomics features were extracted using pyradiomics to compare myocardial texture features. Epicardial adipose tissue (EAT) density, thickness, and other clinical parameters were recorded. Statistical analysis was conducted with R and a Python-based random forest classifier. Results: The study assessed 90 patients (50–60 years, n = 54, and 70–80 years, n = 36) with a mean age of 63.6 years. No significant differences were found in mean Agatston score, gender distribution, or conditions like hypertension, diabetes, hypercholesterolemia, or nicotine abuse. EAT measurements showed no significant differences. The Random Forest Classifier achieved a training accuracy of 0.95 and a test accuracy of 0.74 for age group differentiation. Wavelet-HLH_glszm_GrayLevelNonUniformity was a key differentiator. Conclusions: Radiomics texture features of the left ventricular myocardium outperformed conventional parameters like EAT density and thickness in differentiating age groups, offering a potential imaging biomarker for myocardial aging. Radiomics analysis of left ventricular myocardium offers a unique opportunity to visualize changes in myocardial texture during aging and could serve as a cardiac risk predictor. Full article

Background: This systematic review aimed to comprehensively evaluate the clinical, diagnostic, and therapeutic features of synchronous acute cholecystitis (AC) and acute appendicitis (AAP). Methods: The review protocol was prospectively registered in PROSPERO (CRD420251086131) and conducted in accordance with PRISMA 2020 guidelines. A systematic search was performed across PubMed, MEDLINE, Web of Science, Scopus, Google Scholar, and Google databases for studies published from January 1975 to May 2025. Search terms included variations of “synchronous,” “simultaneous,” “concurrent,” and “coexistence” combined with “appendicitis,” “appendectomy,” “cholecystitis,” and “cholecystectomy.” Reference lists of included studies were screened. Studies reporting human cases with sufficient patient-level clinical data were included. Data extraction and quality assessment were performed independently by pairs of reviewers, with discrepancies resolved through consensus. No meta-analysis was conducted due to the descriptive nature of the data. Results: A total of 44 articles were included in this review. Of these, thirty-four were available in full text, one was accessible only as an abstract, and one was a literature review, while eight articles were inaccessible. Clinical data from forty patients, including two from our own cases, were evaluated, with a median age of 41 years. The gender distribution was equal, with a median age of 50 years among male patients and 36 years among female patients. Leukocytosis was observed in 25 of 33 patients with available laboratory data. Among 37 patients with documented diagnostic methods, ultrasonography and computed tomography were the most frequently utilized modalities, followed by physical examination. Twenty-seven patients underwent laparoscopic cholecystectomy and appendectomy. The remaining patients were managed with open surgery or conservative treatment. Postoperative complications occurred in five patients, including sepsis, perforation, leakage, diarrhea, and wound infections. Histopathological analysis revealed AAP in 25 cases and AC in 14. Additional findings included gangrenous inflammation and neoplastic lesions. Conclusions: Synchronous AC and AAP are rare and diagnostically challenging conditions. Early recognition via imaging and clinical evaluation is critical. Laparoscopic management remains the preferred approach. Histopathological examination of surgical specimens is essential for identifying unexpected pathology, thereby guiding appropriate patient management. Full article

Background/Objectives: Lung cancer remains a major cause of cancer-related mortality, with regional differences in incidence and patient characteristics. This study aimed to verify and quantify a perceived dramatic increase in lung cancer cases at a Romanian center, identify distinct patient phenotypes using unsupervised machine learning, and characterize contributing factors, including demographic shifts, changes in the healthcare system, and geographic patterns. Methods: A comprehensive retrospective analysis of 4206 lung cancer patients admitted between 2013 and 2024 was conducted, with detailed molecular characterization of 398 patients from 2023 to 2024. Temporal trends were analyzed using statistical methods, while k-means clustering on 761 clinical features identified patient phenotypes. The geographic distribution, smoking patterns, respiratory comorbidities, and demographic factors were systematically characterized across the identified clusters. Results: We confirmed an 80.5% increase in lung cancer admissions between pre-pandemic (2013–2020) and post-pandemic (2022–2024) periods, exceeding the 51.1% increase in total hospital admissions and aligning with national Romanian trends. Five distinct patient clusters emerged: elderly never-smokers (28.9%) with the highest metastatic rates (44.3%), heavy-smoking males (27.4%), active smokers with comprehensive molecular testing (31.7%), young mixed-gender cohort (7.3%) with balanced demographics, and extreme heavy smokers (4.8%) concentrated in rural areas (52.6%) with severe comorbidity burden. Clusters demonstrated significant differences in age (p < 0.001), smoking intensity (p < 0.001), geographic distribution (p < 0.001), as well as molecular characteristics. COPD prevalence was exceptionally high (44.8–78.9%) across clusters, while COVID-19 history remained low (3.4–8.3%), suggesting a limited direct association between the pandemic and cancer. Conclusions: This study presents the first comprehensive machine learning-based stratification of lung cancer patients in Romania, confirming genuine epidemiological increases beyond healthcare system artifacts. The identification of five clinically meaningful phenotypes—particularly rural extreme smokers and age-stratified never-smokers—demonstrates the value of unsupervised clustering for regional healthcare planning. These findings establish frameworks for targeted screening programs, personalized treatment approaches, and resource allocation strategies tailored to specific high-risk populations while highlighting the potential of artificial intelligence in identifying actionable clinical patterns for the implementation of precision medicine. Full article

This study investigates the relationship between CEO characteristics and firm performance across emerging and developed economies using both panel regression and machine learning techniques. Drawing on Upper Echelons Theory, we examine whether CEO age, tenure, gender, founder status, and appointment origin influence Return on Assets (ROA), Return on Equity (ROE), and market-to-book ratio. We apply the fixed and random effects models for inference and deploy random forest and XGBoost models to determine the feature importance of each CEO trait. Our findings show that CEO tenure consistently predicts improved ROE and ROA, while CEO age and founder status negatively affect firm performance. Female CEOs, though not consistently significant in the baseline models, positively influence market valuation in emerging markets according to interaction models. Firm-level characteristics such as size and leverage dominate CEO traits in explaining performance outcomes, especially in machine learning rankings. By integrating machine learning feature importance, this study contributes an original approach to CEO evaluation, enabling firms and policymakers to prioritise leadership traits that matter most. The findings have practical implications for succession planning, diversity policy, and performance-based executive appointments. Full article

Background/Objectives: Systemic sclerosis (SSc) is a multisystemic chronic autoimmune disease, which leads to disability and possibly early retirement. The objective of our study was to explore the associations between employment status (ES) and demographic, clinical and functional features in a single-center EUSTAR cohort. Methods: Consecutive patients with SSc examined between November 2011 and June 2023, who were under the age of retirement in our country (62 years for women, 65 for men at the time), were included. All patients underwent a comprehensive clinical assessment and filled in a work assessment questionnaire as well as two validated health-related questionnaires: the Scleroderma Health Assessment Questionnaire (SHAQ) and the Duruoz Hand Index (DHI). Associations between ES and potential predictors (education level, disease characteristics, work conditions, SHAQ and DHI) were tested using logistic regression adjusted for age and gender. Results: Ninety-one patients (mean ± SD age 53.7 ± 11.8 years, twenty-two with diffuse skin involvement, fifty-six with a history of digital of digital ulcers (DUs)), were included. Only 22 patients were still employed, while 69 were retired, of which 38 retired because of SSc. Among the employed, nine performed manual labor, nine spent many hours standing and three had to work in a cold environment. When potential predictors were tested separately, adjusted for age and sex, patients with higher education (OR (95% CI) 11.36 (2.03–63.36), p = 0.006) and no history of digital ulcers had higher odds of being employed. The presence of joint contractures and weightlifting as a work demand were associated with unemployment. In a multivariable model, higher education (OR 5.91, 95% CI 0.97–36.09, p = 0.054 and younger age (OR 0.90, 95% CI 0.85–0.96, p = 0.001) were independently associated with continued employment. High school education did not show a significant effect (OR 0.089, 95% CI 0.015–0.530, p = 0.008). Patients with a history of digital ulcers had the lowest employment rates compared to those with no digital ulcer history. No significant associations were found between employment status and SHAQ or DHI scores. Conclusions: SSc is associated with significant work disability and early retirement. Higher education, the lack of Dus and younger age were highly associated with staying employed. Given the rarity of SSc, we consider that our good sample size (n = 91) reflects disease prevalence, but results should be tested in other studies and the single center should be considered when interpreting generalizability. Full article

Pulmonary arterial hypertension (PAH) is a severe complication associated with connective tissue diseases (CTDs), which is characterized by a significant influence on the patient’s prognosis and mortality. The prevalence of PAH varies depending on the type of CTD. Still, it is highly prevalent in patients with systemic sclerosis (SSc), systemic lupus erythematosus (SLE), mixed connective tissue disease (MCTD), and primary Sjögren’s syndrome (pSS). Identifying rheumatic disease-specific risk factors is crucial for early diagnosis and intervention. Risk factors for PAH development include specific sociological factors (related to race, gender, and age), clinical features (particularly severe Raynaud’s phenomenon and multiple telangiectasias), cardiological factors (pericarditis and left heart disease), biochemical factors (elevated NT-proBNP and decreased HDL-cholesterol), serological factors (presence of ANA, e.g., anti-U1-RNP or SSA, and antiphospholipid antibodies), and pulmonary factors (interstitial lung disease and decreased DLCO or DLCO/alveolar volume ratio < 70%, FVC/DLCO > 1.6). The analysis of risk factors can be the most useful during the selection of patients at high risk of PAH development. The initial diagnosis of PAH is usually based on transthoracic echocardiography (TTE) and is finally confirmed by right heart catheterization (RHC). Targeted therapies can improve outcomes and include endothelin receptor antagonists, prostacyclin analogs, phosphodiesterase inhibitors, and tailored immunosuppressive treatments. Effective management strategies require a multidisciplinary approach involving rheumatologists, cardiologists, and pulmonologists. The risk stratification and individualized treatment strategies can enhance survival and quality of life in patients with PAH-CTD. Full article

Background: Obesity is a major public health issue in developed countries, primarily managed through dietary interventions and physical activity. Food portion sizes influence the estimation of energy intake, particularly through bites, of which characteristics remain insufficiently defined. This study investigates the variability in bite energy content. Methods: This observational study was conducted over 14 months. Thirteen types of packaged food were provided to 30 Italian healthy volunteers (mean age 26.8 ± 8.5 years) in a semi-naturalistic dietary feeding setting. Participants’ anthropometric measurements were recorded. A total of 1850 bites were weighed and 420 bites were assessed for volume and energy content. Results: Bite volume and mass explained bite energy content at different rates. The most influential anthropometric feature was waist circumference. Gender modified the association between waist circumference and bite characteristics; males showed increased bite volume, mass, and energy content as waist circumference increased, whereas females showed little or no association. Age was inversely associated with bite volume and mass, with younger participants having larger bites. Gender significantly influenced average bite size, with females showing lower values than males. The use of a fork was associated with higher bite volume, mass, and energy compared to a spoon. Food eaten with bare hands had lower mass but higher energy content compared to food eaten with a spoon. The variability in bite energy was considerably greater per bite than per gram, reflecting the combined influence of food texture, bite size, and cutlery used. Conclusions: Bite energy variability, influenced by intrinsic factors (gender, age, waist circumference) and extrinsic factors (cutlery, food texture), significantly impacts portion size effect. Future bite counters should consider these elements for accurate dietary assessment. Full article