Search Results (27,697)

Background and Objectives: The use of a standard chest X-ray has become a routine diagnostic method in daily clinical practice for the evaluation of a wide range of lung diseases. During the COVID-19 pandemic, significant challenges occurred in achieving accurate diagnostics and selecting appropriate therapies for patients with different symptoms of diseases. The aim was to cross-correlate radiological findings and clinical data and to develop models to predict hospitalization status, while evaluating the prognostic importance of the different variables. Materials and Methods: A set of variables including Brixia score, and clinical data: gender, age, hypertension, and diabetes was used to explore their association with patient hospitalization. Four different machine learning (ML) methods (Decision Tree—DT, Logistic Regression—LR, Random Forest—RF and Support Vector Machine—SVM) were used for hospitalization outcome prediction. Results: SVM appeared to be with the highest AUC (0.851), with low sensitivity, while DT was the most balanced in the context of AUC, accuracy, sensitivity, and specificity. Brixia score appeared to be the most important predictor for hospitalization within the group of predictors (gender, age, hypertension and diabetes). Conclusions: All four ML models that used in this study provided “good” prediction capabilities (AUC > 0.8), with the exception of SVM that had low sensitivity, emphasizing Brixia score as the strongest predictor of hospitalization. Application of ML methods have considerable potential in various aspects of medical clinical practice and future studies could potentially indicate the importance of applying the ML model in more precise diagnosis, therapy and prognosis of the patient’s clinical condition. Full article

Background: The aim of this study was to examine the relationship between anxiety levels, emotional intelligence, and stress coping strategies in individuals diagnosed with personality disorders. According to Lazarus and Folkman’s transactional model of stress, the appraisal of stressors and available psychological resources determines the selection of coping strategies—whether adaptive or maladaptive. Material and Methods: This observational case series study involved 30 individuals diagnosed with personality disorders (ICD-10 codes F60 and F61). Psychological assessments were conducted at two time points: upon admission to a day-care psychiatric unit and after three months of standard therapeutic intervention. The following standardized instruments were administered: the State-Trait Anxiety Inventory (STAI), the Emotional Intelligence Questionnaire (INTE), and the Mini-COPE Inventory for Coping with Stress. Results: Elevated levels of anxiety—particularly trait anxiety—were significantly associated with maladaptive coping strategies, including denial and self-blame. Conversely, higher emotional intelligence was positively correlated with the use of adaptive coping mechanisms, such as planning and proactive problem-solving. Conclusions: The findings support the hypothesis that both anxiety and emotional intelligence are significant predictors of stress coping styles in individuals with personality disorders. The results underscore the importance of considering these psychological variables in the design and implementation of therapeutic programs. Enhancing emotional intelligence may substantially improve treatment outcomes and overall psychological functioning in this clinical population. However, further studies with larger sample sizes are needed. Full article

Background: Selective internal radiation therapy (SIRT) with yttrium-90 microspheres has become an established locoregional treatment for hepatocellular carcinoma (HCC). Nevertheless, real-world data on clinical outcomes, including efficacy, safety, and prognostic determinants, remain limited. Methods: This study retrospectively analysed 56 patients with radiologically and/or histologically confirmed HCC who underwent SIRT at a tertiary referral centre. Baseline demographics, clinical information, tumour characteristics, procedural data, and follow-up outcomes were recorded. The primary endpoints were overall survival (OS) and progression-free survival (PFS). Secondary outcomes included radiological response (mRECIST), histological necrosis, and treatment-related toxicity. Prognostic pathways were explored using structural equation modelling (SEM). Results: The mean age at the beginning of SIRT was 65.0 ± 11.6 years; most patients were male (87.5%) and had preserved liver function (mean ALBI −2.9 ± 0.4). BCLC staging distribution was 50% stage A, 32.1% stage B, and 17.9% stage C. According to mRECIST criteria at 6 months, 15.2% achieved complete response (CR), 47.8% partial response (PR), 30% stable disease (SD), and 7% progressive disease (PD). Median OS was 19 months (12–32) for BCLC stage A, 28 months (3–42) for stage B, and 19 months (12–56) for stage C (log-rank p = 0.743). SEM identified diffuse tumour morphology as the most significant predictor of poor prognosis. Radical treatments were performed in 28% of patients, including four liver transplants and ten resections. Adverse events occurred in 11 patients, of which 7 were Clavien–Dindo grade I and 4 were grade II. Conclusions: In this real-world HCC group, SIRT provided durable tumour control and survival with excellent tolerability. Full article

Rift Valley fever (RVF) transmission has intensified in southwestern Uganda since 2016. To quantify human and livestock exposure and associated risks, we conducted a cross-sectional serosurvey in Isingiro, Kabale and Rubanda districts between October and November 2023. A total of 766 humans and 2383 livestock were sampled and tested for RVF antibodies using ELISA, with structured questionnaires capturing demographic, behavioral and environmental data. Human seroprevalence was 11.5% (88/766), varying by district (13.8% Isingiro, 11.8% Rubanda, 6.8% Kabale; p = 0.04). Independent predictors from the multivariate model included raw-meat consumption (aOR 6.11; 95% CI 1.16–27.80), cattle ownership (aOR 2.33; 95% CI 1.27–4.36), male sex (aOR 1.64; 95% CI 1.02–2.66) and younger age compared with ≥50 years (31–49 years: aOR 2.02; 95% CI 1.20–3.48; 18–30 years: aOR 2.37; 95% CI 1.04–5.14). Herd-level seroprevalence was 42.5% (204/480), associated with cattle presence (aOR 6.48; 95% CI 4.10–10.40), lack of carcass burial (aOR 15.70; 95% CI 4.23–63.60), on-farm slaughter (aOR 2.14; 95% CI 1.21–3.89) and increased mosquito activity (aOR 1.75; 95% CI 1.13–2.73). Animal-level seroprevalence was 14.6% (347/2383), highest in cattle (33.8%), with cattle having markedly higher odds than goats (aOR 6.73; 95% CI 4.96–9.14). These findings demonstrate substantial transmission and highlight cattle-centered interfaces as primary targets for control to humans. Full article

South Asian Americans experience multifaceted sociocultural and acculturative stressors that influence mental well-being, yet few studies have applied contemporary behavioral theories to understand relaxation behaviors in this population. This cross-sectional study examined predictors of initiating and sustaining relaxation behaviors using the Multi-Theory Model (MTM) of health behavior change. A web-based survey of 271 South Asian adults incorporated the Perceived Stress Scale (PSS-10), MTM constructs, and sociodemographic characteristics. Reliability was high across MTM subscales (Cronbach’s α = 0.81–0.93). Structural equation modeling demonstrated acceptable fit (CFI > 0.90, TLI > 0.90, RMSEA < 0.08, SRMR < 0.08). Hierarchical regressions revealed that among participants practicing relaxation (n = 202), behavioral confidence significantly predicted initiation (β = 0.481, p < 0.001), followed by participatory dialogue (β = 0.194, p < 0.05) and changes in the physical environment (β = 0.242, p < 0.01). Emotional transformation strongly predicted sustenance (β = 0.395, p < 0.001), along with practice for change (β = 0.307, p < 0.05) and changes in the social environment (β = 0.210, p < 0.05). MTM constructs explained 69.8% of initiation variance and 70.4% of sustenance variance. Among non-practitioners, participatory dialogue predicted initiation (β ≈ 0.18–0.34, p < 0.05), and emotional transformation predicted sustenance (β = 0.570, p < 0.001). These findings underscore MTM’s strong predictive utility and support culturally tailored interventions enhancing confidence, emotional regulation, and social/environmental supports to promote relaxation behaviors in South Asian communities in the United States. Full article

Background: Kidney biopsy is the diagnostic gold standard for characterizing glomerular disease and other intrarenal pathologies. Despite its clinical importance, epidemiological trends in kidney biopsy incidence remain poorly understood in many developed healthcare systems. This study characterizes temporal and demographic trends in kidney biopsy utilization in Germany between 2006 and 2023, providing crucial data for resource allocation in renal pathology services. Methods: Data on all kidney biopsies (OPS code 1-465.0) performed in German hospitals were extracted from the Federal Statistical Office database and stratified by age and sex. Population denominators were obtained from national census data. Incidence rates per 100,000 inhabitants per year were calculated, and temporal trends were analyzed using Poisson regression with year as a continuous predictor variable. Separate models were fitted for overall population incidence, age-stratified incidence, and sex-stratified incidence. Results: The incidence of kidney biopsies increased 96.6% over 18 years, from 8.59 per 100,000 inhabitants in 2006 to 16.89 per 100,000 in 2023 (IRR: 1.0296 per year, 95% CI: 1.0287–1.0305; p < 0.0001). Age-stratified analysis revealed pronounced heterogeneity, with the oldest patients (>80 years) experiencing the steepest increase of 7.74% annually, while the youngest age group (<20 years) showed no significant temporal change. Sex-stratified analysis demonstrated similar increases in both males and females (3.36% and 3.04% annually, respectively). Conclusion: The substantial increase in kidney biopsy utilization in Germany over nearly two decades mirrors international patterns and suggests a global shift toward more liberal biopsy utilization in aging populations. Multiple factors likely contributed to this increase, including demographic aging, improved procedural safety and accessibility, evolving diagnostic guidelines, and expanding therapeutic options for glomerular disease. These findings underscore the need for national registry systems to optimize resource allocation for renal pathology and ensure equitable diagnostic access across healthcare systems. Full article

With increasing life expectancy, a growing proportion of patients undergoing surgery for gynecologic cancers are older adults, underscoring the need for reliable predictors of postoperative recovery and patient engagement. Cognitive function and physical frailty are recognized determinants of surgical outcomes, yet their relative impact on patient centered outcomes remains insufficiently explored. This prospective observational study included 68 women aged 65 years and older who underwent abdominal surgery for gynecologic malignancies. Preoperative cognitive function was assessed using the Montreal Cognitive Assessment, and physical frailty was evaluated with the Clinical Frailty Scale. Postoperative outcomes included early recovery parameters, complications, surgical decision satisfaction, and home-based adherence. Higher cognitive scores were associated with earlier mobilization, shorter hospital stay, better postoperative adherence, and greater decision satisfaction, whereas higher frailty scores were associated with delayed recovery and increased complication risk. In regression analyses, preoperative cognitive function was significantly associated with both postoperative adherence and surgical decision satisfaction, whereas physical frailty was not. These findings indicate that preoperative cognitive screening may have predictive value for patient centered recovery behaviors and decision satisfaction in this setting; however, the prediction estimates should be considered exploratory and warrant validation in larger, multicenter cohorts. Full article

Short-form video platforms such as TikTok (TikTok Pte. Ltd., Singapore) host large volumes of user-generated, often ephemeral, content related to irregular migration, where relevant cues are distributed across visual scenes, on-screen text, and multilingual captions. Automatically identifying migration-related videos is challenging due to this multimodal complexity and the scarcity of labeled data in sensitive domains. This paper presents an interpretable multimodal classification framework designed for deployment under data-scarce conditions. We extract features from platform metadata, automated video analysis (Google Cloud Video Intelligence), and Optical Character Recognition (OCR) text, and compare text-only, OCR-only, and vision-only baselines against a multimodal fusion approach using Logistic Regression, Random Forest, and XGBoost. In this pilot study, multimodal fusion consistently improves class separation over single-modality models, achieving an F1-score of 0.92 for the migration-related class under stratified cross-validation. Given the limited sample size, these results are interpreted as evidence of feature separability rather than definitive generalization. Feature importance and SHAP analyses identify OCR-derived keywords, maritime cues, and regional indicators as the most influential predictors. To assess robustness under data scarcity, we apply SMOTE to synthetically expand the training set to 500 samples and evaluate performance on a small held-out set of real videos, observing stable results that further support feature-level robustness. Finally, we demonstrate scalability by constructing a weakly labeled corpus of 600 videos using the identified multimodal cues, highlighting the suitability of the proposed feature set for weakly supervised monitoring at scale. Overall, this work serves as a methodological blueprint for building interpretable multimodal monitoring pipelines in sensitive, low-resource settings. Full article

Background: Malnutrition in adolescents remains a significant public health issue worldwide, with undernutrition and overweight often coexisting. Accurate nutritional screening during adolescence is complicated by variability in biological maturation and class imbalance, particularly among underweight adolescents. Objective: This study aims to develop and validate machine learning models for classifying the nutritional status of adolescents, accounting for class imbalance and biological maturation, and to evaluate model stability and variable importance at different stages of peak height velocity (PHV). Methods: In this cross-sectional study, 4232 adolescents aged 11 to 18 years were recruited from nine educational institutions in Tunisia. Their nutritional status was classified according to the International Obesity Task Force (IOTF) BMI thresholds into three categories: underweight (14.4%), normal weight (68.3%), and overweight (17.2%). Ten anthropometric, behavioral, and maturation-related predictors were analyzed. Six supervised machine learning algorithms were evaluated using a 70/30 stratified split between training and test sets, with five-fold cross-validation. Class imbalance was addressed by ROSE combined with cost-sensitive learning. Model performance was assessed using accuracy, Cohen’s kappa coefficient, macro F1 score, sensitivity, specificity, and AUC. Results: The cost-sensitive Random Forest (RF) model achieved the best overall performance, with an accuracy of 0.830, a macro F1 score of 0.767, a macro-AUC of 0.921, and a macro- sensitivity of 0.743. The class-specific sensitivities were 0.70 (underweight), 0.91 (normal weight), and 0.62 (overweight), with no major misclassification between the extreme categories. Performance remained stable across the different maturation phases (accuracy from 0.823 to 0.839), with optimal discrimination in the pre-PHV (macro-AUC = 0.936; sensitivity for underweight = 0.82) and post-PHV (macro-AUC = 0.931) periods. Body mass was the main predictor (importance = 1.00), followed by waist circumference (0.34–0.53). The importance of age for classifying underweight increased significantly from the pre-PHV (0.10) to the post-PHV (0.75) period. A two-stage hierarchical model further improved underweight detection (stage 1 AUC = 0.911; sensitivity = 0.732). Conclusions: A cost-sensitive RF model, combined with ROSE, provides robust classification of adolescents’ nutritional status maturation, significantly improving underweight detection while preserving overall accuracy. This approach is particularly well-suited to public health screening in schools as a first-stage assessment that requires clinical confirmation and promotes a maturation-aware interpretation of nutritional risk among adolescents. Full article

Laryngeal squamous cell carcinoma (SCC) remains a major clinical challenge due to substantial mortality and limited preoperative risk stratification. Narrow-Band Imaging (NBI) enables real-time visualization of mucosal microvasculature, yet the molecular correlates of high-risk NBI phenotypes in vocal fold lesions are incompletely defined. In a prospective cohort of 145 patients with vocal fold lesions, NBI microvascular patterns were graded using the Ni classification and dichotomized using a pre-specified high-risk threshold (Ni ≥ 4 vs. Ni ≤ 3). Histopathology was classified according to WHO 2017. Epithelial expression of IL-6, LIF, LIFR and CXCL9 was quantified by immunohistochemistry using the immunoreactive score (IRS). Associations were tested using non-parametric methods and logistic regression, and diagnostic performance was assessed by ROC analysis. SCC was diagnosed in 63/145 cases. The Ni category showed a strong stepwise association with WHO 2017 histopathological severity. Using Ni ≥ 4, diagnostic performance for SCC was balanced (sensitivity 82.5%, specificity 82.9%; accuracy 82.8%). LIF and LIFR expression decreased with increasing histopathological severity and higher-NBI-risk categories, whereas CXCL9 increased with more suspicious NBI patterns; epithelial IL-6 did not differ across lesion categories. In multivariable logistic regression, Ni ≥ 4 was the strongest independent predictor of SCC (adjusted OR 8.90), while higher LIF (adjusted OR 0.73) and LIFR (adjusted OR 0.78) were independently associated with lower odds of SCC (model AUC 0.943). Multivariable analysis confirmed NBI as the strongest independent predictor of carcinoma, while epithelial LIF and LIFR expression showed inverse associations with histological malignancy and high-risk NBI vascular patterns. LIF/LIFR and CXCL9 show distinct, biologically plausible associations with NBI risk phenotypes, suggesting that selected tissue markers may complement NBI for refined SCC risk stratification. Full article

Background: Current cancer treatment strategies target the preservation and enhancement of patient quality of life. Therefore, we aimed to assess the causal impact of hemoglobin (Hb) levels on global quality of life in cancer patients. Methods: We conducted a retrospective analysis using data collected from new cancer patients. The dataset included responses to the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire, demographic, and disease-related variables. We applied the Linear Non-Gaussian Acyclic Model (LiNGAM) algorithm to identify potential causal relationships among those, and their impact on global quality of life. Furthermore, to evaluate the relative importance of Hb levels on global quality of life, we utilized a Random Forest Classifier (RFC). Results: The Random Forest Classifier (RFC) emerged as the most accurate model for classifying global quality of life scores (QL2) in our analysis. RFC analysis showed that Hb level ranked as the 10th most important feature among the 23 predictors in all patients for the global quality of life. However, the LiNGAM algorithm identified the Hb value as the most significant causal factor on global quality of life (total causal effect = 3.5) for anemic patients. Moreover, the Hb value was also a significant causal factor in patients in the “other cancers” and “stage 4” subcategories, with total causal effect figures of 2.9 and 2.5, respectively. Conclusions: This study suggests that Hb levels may exert a beneficial causal effect on global quality of life in cancer patients with anemia and among those with stage 4 disease and cancers other than breast, lung, or colorectal cancer. Full article

Background: Sex-related differences in cardiovascular disease outcomes are well recognized. Their impact on short-term outcomes in acute pulmonary embolism (PE) remains unclear. This study aimed to assess the association between sex and in-hospital outcomes in patients with acute PE. Methods: We performed a retrospective observational cohort study including 322 consecutive adult patients with acute PE admitted to a university hospital. Clinical, hemodynamic, laboratory, and imaging data were collected at presentation. The primary outcome was a composite poor outcome defined as intensive care unit (ICU) admission, systemic thrombolysis, or in-hospital mortality. Multivariable logistic regression analysis was used to evaluate whether sex independently predicted adverse outcomes after adjustment for established prognostic factors. Results: This study included 322 patients with acute pulmonary embolism (mean age 64.4 ± 13.1 years), of whom 50.0% were women. The composite poor outcome occurred more frequently in women than in men (34.0% vs. 22.7%, p = 0.032). Female sex was associated with increased odds of poor outcome in univariate analysis (odds ratio (OR) 1.76; 95% confidence interval (CI) 1.08–2.88). This association remained significant after multivariable adjustment (adjusted OR 1.69; 95% CI 1.02–2.82; p = 0.042). No significant sex differences were observed for individual components of the composite endpoint. Conclusions: Female sex was independently associated with a higher risk of adverse in-hospital outcomes in acute PE, suggesting that sex-specific factors may influence early prognosis and should be considered in future risk stratification models. Full article

Accurate field-scale meteorological information is required for precision agriculture, but operational numerical weather prediction products remain spatially coarse and cannot resolve local microclimate variability. This study proposes a data fusion superresolution workflow that combines global GFS predictors (0.25°), regional station observations from Southern Moravia (Czech Republic), and static physiographic descriptors (elevation and terrain gradients) to predict the 2 m air temperature 24 h ahead and to generate spatially continuous high-resolution temperature fields. Several model families (LightGBM, TabPFN, Transformer, and Bayesian neural fields) are evaluated under spatiotemporal splits designed to test generalization to unseen time periods and unseen stations; spatial mapping is implemented via a KNN interpolation layer in the physiographic feature space. All learned configurations reduce the mean absolute error relative to raw GFS across splits. In the most operationally relevant regime (unseen stations and unseen future period), TabPFN-KNN achieves the lowest MAE (1.26 °C), corresponding to an ≈24% reduction versus GFS (1.66 °C). The results support the feasibility of an operational, sensor-infrastructure-compatible pipeline for high-resolution temperature superresolution in agricultural landscapes. Full article

Background: Periapical pathosis in periapical radiographs must be properly diagnosed for the success of endodontic treatment but is often muddled by 2D imaging limitations and subjective interpretation. Artificial intelligence (AI) offers a solution, but whether the diagnostic granularity of AI versus human clinicians in everyday clinical practice has been adequately explored remains to be addressed. The purpose of this study was to evaluate the diagnostic accuracy of ChatGPT-5 in detecting periapical radiographic abnormalities compared with the three-expert consensus reference standard. Methods: In this diagnostic accuracy retrospective study, 270 periapical radiographs were independently read by a large language model (ChatGPT-5) and a three-board-certified oral radiologist consensus. The AI was given a standardized prompt to label radiographic features, like the presence of periapical radiolucency, border, shape, and integrity of lamina dura. Diagnostic accuracy, agreement (Cohen’s κ), and predictors of correct AI classification were compared with the expert consensus reference standard. Results: ChatGPT-5 demonstrated high sensitivity (87.5%) but low specificity (12.5%), resulting in an overall diagnostic accuracy of 50.0%. This performance profile reflects a tendency toward over-identification of pathology, with the model classifying 87.5% of radiographs as abnormal compared with 50.0% by expert consensus. Agreement was almost perfect for anatomical localization (arch, κ = 0.857) but poor for binary abnormality detection (κ = 0.000). For morphological descriptors, statistically significant disagreement was observed for lesion border characterization (κ = 0.127; p < 0.001), whereas lesion shape demonstrated only descriptive divergence without reaching statistical significance (κ = 0.359). Root resorption assessment also differed significantly between evaluators (p = 0.046). Regression analysis showed that well-defined corticated borders (OR = 60.25, p < 0.001) and first molar-associated lesions (OR = 32.55, p < 0.001) were significant predictors of correct AI classification. Conclusions: This study demonstrates that while ChatGPT-5 Vision can visually interpret periapical radiographs with high sensitivity, limited specificity and inconsistent morphological feature characterization restrict its reliability for independent clinical diagnosis. The AI system tends to over-diagnose systematically and categorizes lesions more structurally and defined compared to dental experts. AI has the potential for being optimized as a sensitive first-screening test, but its findings must be validated by dental professionals to avoid false positives and ensure proper characterization. Full article

Residuals play a central role in linear regression, yet their geometry is often hidden by inverse- and pseudoinverse-based formulas. We develop a rank-aware framework for residual projection that makes the underlying orthogonality explicit. When the design matrix has codimension one, the unexplained component of the response lies along a single unit normal to the predictor space, and the residual projector reduces to the rank-one operator $n{n}^{\top }$, avoiding matrix inversion. For general designs, the residual lies in a higher-dimensional orthogonal complement spanned by an orthonormal basis N, and the residual projector factorizes as $N{N}^{\top }$. Using cross-products, wedge products, and Gram determinants, we provide basis-independent characterizations of the residual subspace. We further introduce the Geometric Multicollinearity Index (GMI), a scale-invariant diagnostic derived from the polar sine that quantifies the collapse of predictor-space volume under multicollinearity. Synthetic perturbation studies and an illustrative real-data experiment show that the proposed projectors reproduce ordinary least squares residuals, that GMI responds predictably to controlled collinearity, and that the projector viewpoint clarifies the distinction between regression residuals and PCA reconstruction residuals in both full-rank and rank-deficient settings. Full article