Search Results (30,290)

Background: Neuroinflammation is recognized as a key contributor to Parkinson’s disease (PD), but the relationships between inflammatory signaling, immune-state alterations, and cell-type-specific transcriptional programs remain unclear. Methods: Public transcriptomic datasets, including GSE20141 (discovery cohort) and the substantia nigra subset of GSE114517 (external validation cohort), were analyzed. Genes identified by exploratory differential-expression screening in the discovery cohort were intersected with predefined inflammation- and chemokine-related gene sets to define a candidate space for downstream prioritization. Protein–protein interaction, Gene Ontology, KEGG, and immune-signature analyses were performed, followed by machine learning-based feature prioritization using Elastic Net, support vector machine-recursive feature elimination, and random forest. Prioritized candidates were further evaluated by cross-platform validation, single-nucleus transcriptomic mapping, and a hypothesis-generating in silico perturbation analysis in PD astrocytes. Results: Seventeen genes were retained at the intersection of PD-related differentially expressed genes and inflammation-/chemokine-associated gene sets. These candidates formed a response module enriched in mitochondrial organization, oxidative phosphorylation, and mitophagy pathways. Immune-signature analysis suggested an altered transcriptome-derived immune landscape in PD, with changes in NK cell-related signatures and significant correlations between immune-state scores and the candidate genes. Machine learning-based prioritization yielded five shared candidates, of which only CCL2 and PAK6 showed same-direction support with nominal significance in the external validation cohort. Single-nucleus transcriptomic analysis localized CCL2 predominantly to astrocytes, whereas PAK6 was more strongly associated with neuronal populations, particularly OTX2-positive ventral midbrain neurons. In silico perturbation analysis further predicted that CCL2 suppression in PD astrocytes may be associated with translational- and ribosome-related regulatory programs. Conclusions: CCL2 and PAK6 emerged as prioritized candidate biomarkers associated with PD-related inflammatory and chemokine-linked transcriptional alterations in the substantia nigra. More broadly, this study provides a multi-layered framework for candidate prioritization, cross-platform validation, and cell-type-level contextualization in PD neuroinflammation. Because the study is computational and the perturbation analysis is predictive, orthogonal experimental validation will be required to determine whether CCL2 and PAK6 are biomarkers of disease-associated transcriptional states, functional contributors to PD pathogenesis, or both. Full article

Background: Early risk assessment in acute pulmonary embolism (PE) remains challenging, particularly in normotensive patients. Lactate may offer incremental prognostic value beyond conventional tools. We investigated the association between arterial lactate and in-hospital mortality in acute PE. Methods: In this retrospective single-center study, 327 adult patients diagnosed with acute PE by computed tomography pulmonary angiography who underwent arterial blood gas analysis within the first six hours of emergency department presentation were included. Patients were categorized according to the occurrence of in-hospital mortality, including 103 (31.5%) non-survivors and 224 (68.5%) survivors, and their demographic, clinical, laboratory, and echocardiographic characteristics were compared accordingly. Results: Arterial lactate levels were significantly higher in non-survivors than survivors [4.1 vs. 1.9 mmol/L; p < 0.001], with a stepwise increase in mortality across lactate categories (<2, 2–4, >4 mmol/L; p < 0.001). In normotensive patients (n = 211), lactate ≥2 mmol/L was associated with higher mortality compared with <2 mmol/L (35.7% vs. 8.7%; OR 5.8, 95% CI 2.7–12.5; p < 0.001). In multivariable logistic regression analysis performed in normotensive patients, arterial lactate level, PESI score, and the presence of cerebrovascular disease were identified as independent predictors of in-hospital mortality, whereas troponin did not retain independent significance. In normotensive patients, lactate showed better discriminative ability than troponin I (AUC 0.718 vs. 0.553). Conclusions: Arterial lactate levels are independently associated with in-hospital mortality in acute PE. Elevated lactate may help identify high-risk patients even in the absence of hypotension and may provide incremental prognostic value beyond existing risk stratification tools. These findings suggest the use of arterial lactate in early risk assessment. Full article

Exchange rate volatility has intensified in recent decades, yet its systematic implications for banking-sector stability remain contested. This study investigates whether exchange rate volatility constitutes a meaningful source of financial fragility using a global panel of 103 countries over the period 2000–2021. Financial stability is proxied by the banking-sector Z-score, while exchange rate volatility is estimated using a EGARCH-based framework to capture time-varying uncertainty. To address cross-sectional dependence, heterogeneity, and endogeneity, the analysis employs Driscoll–Kraay fixed effects, two-step system GMM, and quantile regressions. The results reveal that exchange rate volatility exerts a statistically and economically significant negative effect on banking stability, reducing Z-scores across countries and income groups. The findings remain robust across alternative specifications and estimators. Bank-level fundamentals—capitalisation, liquidity, and credit—enhance stability, whereas higher non-performing loans and risk exposure amplify fragility. Macroeconomic conditions also matter, with stronger growth, institutional quality and external balances supporting resilience, while inflation, economic policy uncertainty and expansionary government spending weaken stability. By integrating time-varying volatility modelling with dynamic panel techniques in a large cross-country setting, this study provides new global evidence that exchange rate volatility is not merely a macroeconomic fluctuation but a structural source of banking-sector risk. The findings carry important implications for macroprudential policy, foreign-exchange management, and coordinated monetary–fiscal responses aimed at safeguarding financial stability in open economies. Full article

Aero-engine defects often exhibit micro-scale and high-frequency characteristics under complex metallic textures, which makes precise segmentation difficult. Most existing pixel-level methods rely on spatial-domain modeling and lack frequency-domain decoupling. As a result, high-frequency details are easily hidden by low-frequency background information. In addition, repeated downsampling weakens the representation of fine-grained structures, leading to inaccurate boundary localization and limited robustness. To address these issues, a spectrum-driven hierarchical learning network is proposed for aero-engine defect segmentation. First, a dual-band spectral module is constructed using the discrete cosine transform to separate high-frequency and low-frequency components, providing stable and physically meaningful frequency-domain priors for the network. Second, a detail-guided module is designed where high-frequency features adaptively guide skip connections, compensating information loss during encoding and improving boundary recovery. Furthermore, a low-frequency-driven region-aware modeling module is developed. The internal defect regions, boundary areas, and background regions are modeled hierarchically. A dynamic hyper-kernel generation mechanism performs region-sensitive convolutional modeling, improving adaptation to complex structural variations. Extensive experiments on the Turbo19 and NEU-Seg datasets demonstrate that the proposed method produces accurate defect boundaries and achieves mIoU scores of 89.82% and 91.44%, improving over the second-best method by 5.22% and 4.42%, respectively. Full article

The detection and monitoring of asbestos–cement roofing remain a critical public health and environmental challenge, especially in urban and suburban areas where asbestos-containing materials are still widespread due to their extensive use in the 20th century. Although hyperspectral and high-resolution multispectral remote sensing have proven effective for mapping asbestos–cement roofs, many existing approaches rely on proprietary software, limiting transparency, reproducibility, and large-scale adoption. This study presents a fully reproducible, cost-free Python-based workflow for the detection and temporal monitoring of asbestos–cement roofing using high-resolution multispectral WorldView-3 imagery. The workflow integrates atmospheric correction (using the Py6S radiative transfer model), spatial preprocessing, supervised pixel-based classification, postprocessing, and building-level aggregation within an open framework. A Maximum Likelihood Classifier is applied to VNIR and SWIR data using empirically defined roof typologies to enhance class separability. Pixel-level results are aggregated to the building scale through adaptive thresholding enabling the translation of spectral classifications into meaningful building-level information. Tested over the city of Mantua (Italy), the approach achieved reliable classification performance and enabled multi-temporal comparison to identify changes potentially due to roof remediation. Evaluation metrics (precision, recall, and F1-score) highlight the importance of carefully choosing the building-level threshold. By relying exclusively on open-source tools, the workflow enhances transparency, reproducibility, and scalability for long-term monitoring. Full article

This article examines whether a high-performing fraud detection model can also meet the demands of auditability, documentation, and regulatory transparency. Using the publicly available European credit card fraud dataset of 284,807 transactions, including 492 fraudulent cases, this study compares weighted logistic regression with XGBoost under severe class imbalance. Model performance is assessed through precision, recall, F1 score, ROC AUC, and precision–recall AUC, with particular attention to alert burden and fraud capture. Results show that XGBoost materially outperforms logistic regression in operational terms. While logistic regression achieves slightly higher recall, XGBoost raises precision from 0.061 to 0.562, improves PR AUC from 0.719 to 0.863, and reduces false positives from 1386 to 67. The PR AUC of 0.863 refers to the cross-validated average reported in the model comparison, while the holdout test result reported later in this paper is 0.852. It cuts the review queue from 1476 alerts to 153 while still identifying 86 of 98 fraud cases in the test set. Explainability is then introduced through SHAP, which provides both global feature attribution and transaction-level reasoning. The findings show that SHAP makes the boosted model readable at the level of both overall model behaviour and individual fraud flags, thereby supporting audit review, model validation, and regulatory scrutiny. The article argues that the combination of XGBoost and SHAP offers a stronger fit for auditing than either a weaker but transparent linear model or a stronger opaque classifier. One limit remains, since the dataset contains anonymised principal components rather than original business variables, which restricts semantic interpretation. Even so, the workflow provides a practical bridge between predictive fraud analytics and the demands of explainable, reviewable, and accountable AI in auditing. Full article

Light Detection and Ranging (LiDAR) three-dimensional (3D) object detection degrades under point sparsity, outliers, coordinate noise, and calibration drift, yet detector evaluation remains largely limited to clean benchmarks. This study focuses on sensing robustness rather than detector redesign. We introduce Bounded Graph Conditioning (BGC)—a deterministic pre-voxelization front-end that applies k-nearest-neighbor (kNN) neighborhood averaging with bounded residual correction upstream of an unchanged detector backbone. BGC is evaluated together with a reproducible sensor-degradation stress protocol and a risk-constrained operating-boundary analysis. Experiments on KITTI with PointPillars, SECOND, and Voxel R-CNN show that BGC most clearly improves retained detection quality and feasible operating coverage under strong noise and strong outlier stress; gains under other degradation types are smaller and backbone-dependent. In the primary score-level box-disjoint calibration/test evaluation on SECOND, maximum feasible coverage at a target risk bound of $0.2$ improves from $0.0754$ to $0.1374$ under strong noise ($\sigma =0.10$ m) and from $0.1323$ to $0.1591$ under strong outliers ($p=0.10$); a cross-backbone check on Voxel R-CNN confirms the same direction ($0.1860\to 0.2864$). Comparison with traditional filtering (SOR and ROR) reveals complementary strengths across fault types. A range-adaptive BGC variant that adjusts parameters per distance bin further improves performance under mixed unknown faults, spherical-coordinate noise, and on a dataset-matched nuScenes validation (adaptive BGC mAP/NDS: $0.2687/0.4493$ vs. baseline $0.2471/0.3846$ under strong noise). Severe translation drift collapses all configurations to full rejection, exposing an explicit sensing boundary beyond the reach of local conditioning. These results support BGC as a practical sensor-side robustness enhancement under the studied degradation protocol, with conditional rather than universal applicability across backbones and fault types. Full article

The paper addresses ECG arrhythmia classification using a novel input fusion strategy that combines spatial representations of ECG time series recordings. Four distinct time series-to-image transformations are considered, namely classical spectrograms, Gramian Angular Field (GAF), Recursive Plot (RP), and the S-Transform (ST). Classification of combined 2 × 2 images generated from single-lead ECG recordings is performed using both custom and ResNet-50 deep learning architectures. Finally, several distinct explainability algorithms are used to identify the relevant regions in the input images that mainly influence the classification decisions. Experiments performed on the MIT-BIH and Chapman–Shaoxing arrhythmia datasets revealed performance comparable to more sophisticated approaches in terms of accuracy (99%), F1-score (98.6%), and AUC (0.999) values. Full article

Background/Objectives: Chronic liver diseases, including metabolic dysfunction-associated steatohepatitis (MASH) and chronic viral hepatitis (CVH), are major global health concerns due to their potential progression to cirrhosis, liver failure, and hepatocellular carcinoma. Because liver biopsy, despite meeting the diagnostic gold standard, is invasive and associated with complications, non-invasive fibrosis assessment tools have been increasingly recommended in clinical practice. This study aimed to compare the diagnostic performance of several non-invasive fibrosis markers (ARR, APRI, FI, FIB-4, API, NFS, BARD) and transient elastography in detecting advanced liver fibrosis (F4) in patients with MASH and CVH. Methods: This retrospective study included 237 adult patients (77 MASH, 160 CVH) who underwent liver biopsy between 2017 and 2025 at the University Clinical Center of Serbia. CVH included chronic hepatitis B (CHB) and C (CHC). Patients were evaluated using serum fibrosis indices and TE, and results were compared to histological staging (F0–F4). ROC analysis assessed diagnostic performance. Results: Cirrhosis (F4) was more common in CVH than MASH (p < 0.001). In MASH, NFS (AUROC 0.931), FIB-4 (0.915), BARD (0.872), and APRI (0.878) showed high diagnostic accuracy for F4. In CHC, APRI (0.931), FIB-4 (0.863), and TE (0.938) had strong performance, while in CHB, TE (0.987) outperformed FIB-4 (0.821). Sensitivity and specificity varied by test and cohort, with TE consistently yielding the best results where available. Conclusions: Non-invasive methods, particularly NFS and FIB-4 for MASH and TE for CVH, effectively identify advanced fibrosis. Their application could significantly reduce the need for biopsy, especially in high-risk groups. TE demonstrated superior accuracy, but access limitations highlight the continued relevance of serum-based scores. Full article

Reliable pedestrian perception in autonomous driving depends not only on detecting the target, but also on how completely and consistently its three-dimensional geometry is captured from different sensor viewpoints. This study presents a LiDAR-based observability framework for evaluating pedestrian representation on the ANTA compact autonomous vehicle platform using a roof-mounted Top LiDAR (TL), a Front-Right LiDAR (FRL), and their fused configuration. The pedestrian was analyzed in a canonical local frame using geometric extent ratios, projected surface occupancy, voxel-based volumetric occupancy, and statistical descriptors of the local point distribution, integrated into a global observability score, $S_{3D}$. A Distance-Robustness Index (DRI), an overlap-based complementarity analysis, and a lightweight temporal centroid-sensitivity check over 20 consecutive frames were used to characterize performance across distance. Using ROS 2 bag data processed offline in MATLAB R2025b the fused configuration achieved the highest mean global score (0.563), compared with 0.504 for FRL and 0.432 for TL, and the highest robustness ($\mathrm{DRI}=0.5628$, $CV=10.7\%$). The results show that 1 m maximizes local density, 2–3 m maximize projected and volumetric completeness, and 7 m provides the best balanced observability. Within the evaluated platform and under the controlled benchmark conditions, complementary multi-LiDAR fusion provided the strongest overall geometry-aware pedestrian representation. Full article

Background: Vancomycin-resistant Enterococcus (VRE) bacteremia represents a major therapeutic and epidemiological challenge, particularly in regions with high antimicrobial resistance rates such as Southern Europe. Longitudinal local data are essential to guide infection control and antimicrobial stewardship strategies. This study aimed to evaluate temporal trends in incidence, management, and mortality of VRE bacteremia in a tertiary care center in Greece over a six-year period, including comparison before and after the coronavirus disease 2019 (COVID-19) pandemic. Methods: This retrospective observational study included adult patients with VRE bacteremia at the University Hospital of Heraklion, Greece, from 2018 to 2023. Demographic and clinical data, such as the Pitt Bacteremia Index (PBI), as well as microbiological, and treatment data were collected from patient records. Incidence was calculated per 10,000 patient-days. Comparisons were performed between survivors and non-survivors and between pre- and post-COVID-19 eras. Multivariate regression analysis was used to identify predictors of in-hospital mortality. Results: A total of 96 patients were included (mean age 68.6 ± 14.5 years; 56.3% male). The incidence of VRE bacteremia increased more than five-fold during the study period, from 0.242 cases per 10,000 patient-days in 2018 to a peak of 1.344 per 10,000 patient-days in 2022, remaining elevated in 2023 (1.001 per 10,000 patient-days). The overall in-hospital mortality was 54.2%. Non-survivors had significantly higher PBI scores compared to survivors (median 2.5 vs. 0, p = 0.005). In the multivariate analysis, higher PBI was independently associated with in-hospital mortality [odds ratio: 1.449 (95% confidence intervals: 1.166–1.801)]. Appropriate empirical therapy was administered in 41.7% of cases and was not significantly associated with survival. Post-COVID-19 patients were older (69.9 vs. 61.4 years, p = 0.0365), and antimicrobial regimens were more frequently adjusted according to susceptibility testing (55.7% vs. 18.2%, p = 0.0141), but mortality did not significantly differ between periods. Conclusion: VRE bacteremia incidence increased dramatically over the six-year study period in our tertiary center, with persistently high mortality exceeding 50%. Severity of illness at the diagnosis of bacteremia, as measured by the PBI, was an independent predictor of in-hospital mortality. Strengthened infection prevention measures, optimized antimicrobial stewardship, and early aggressive management are urgently needed to mitigate the growing burden of VRE bacteremia. Full article

This study aimed to enhance the accuracy and interpretability of erosion gully classification within black soil regions by focusing on Changxing Township, Xinxing District, Qitaihe City, Heilongjiang Province as the research site. Utilizing RTK (Real-Time Kinematic) surveying technology, three-dimensional topographic data were collected for 139 actively developing erosion gullies. Key morphological parameters—including gully length, depth, gradient, average top width, average bottom width, and slope gradients on both sides—were extracted to construct interactive features. The variable set was refined through correlation analysis and variance inflation factor (VIF) diagnostics to mitigate multicollinearity. A random forest model was employed as the primary classification approach and benchmarked against logistic regression, support vector machines (SVM), decision trees, and backpropagation neural networks. To address class imbalance, a combination of class weighting, Synthetic Minority Over-sampling Technique (SMOTE), and undersampling methods was implemented. Model tuning and interpretability assessments were performed using cross-validation, grid search optimization, and SHapley Additive exPlanations (SHAP) analysis. The findings demonstrate that the random forest model achieved superior overall performance, with test set accuracy, macro-averaged F1 score, and balanced accuracy values of 0.9143, 0.8087, and 0.8427, respectively. Among imbalance handling techniques, class weighting yielded better results compared to oversampling and undersampling. Feature importance and SHAP analyses identified gully length, average crest width, and their interaction with gully depth as the principal determinants influencing gully grade classification. These results elucidate the synergistic developmental dynamics of gully longitudinal extension, vertical deepening, and lateral widening. The proposed methodology offers valuable technical support for the rapid surveying, classification, and management decision-making processes related to black soil erosion gullies. Full article

Transparent clinical decision-making remains a critical barrier to deploying deep learning in medical diagnosis. Post hoc explanation methods approximate model behaviour after training but cannot guarantee that explanations faithfully reflect the underlying reasoning. This study proposes a Self-Explaining Neural Network (SENN) for Parkinson’s Disease (PD) screening via Ground Reaction Force (GRF) gait analysis, enforcing intrinsic interpretability through learnable basis concepts and input-dependent relevance scores computed jointly with the prediction. The architecture combines a four-block residual CNN backbone with stochastic depth regularisation, a 16-concept encoder with diversity and stability constraints, and temperature-scaled probability calibration for reliable clinical operating points. Evaluated on the PhysioNet Gait in Parkinson’s Disease dataset (306 subjects, 16 GRF sensors per foot), SENN achieves a subject-level ROC-AUC of 0.916 [95% CI: 0.867–0.964], sensitivity of 0.913 [0.862–0.963], specificity of 0.671 [0.485–0.858], and Average Precision of 0.942 [0.918–0.967], reported across five independent random seeds. Comparative evaluation against four deep learning baselines—CNN-Residual, BiLSTM, CNN-LSTM, and CNN-Attention—confirms that the interpretability constraints impose no statistically significant reduction in discriminative performance, with all pairwise ROC-AUC confidence intervals overlapping. Concept-level analysis reveals that the three most discriminative concepts correspond to disrupted midfoot loading patterns, increased step-length variability, and bilateral cadence asymmetry—all established biomechanical hallmarks of parkinsonian gait—providing clinically grounded, patient-specific explanations without post hoc approximation. These findings demonstrate that rigorous intrinsic interpretability and competitive predictive accuracy are simultaneously achievable in deep gait analysis, supporting the clinical adoption of transparent diagnostic AI. Full article

Objective: To identify risk factors for progression to sepsis in patients with non-ventilator hospital-acquired pneumonia (NV-HAP) and to develop a practical nomogram for individualized risk assessment in this population. Methods: We retrospectively screened 408 hospitalized patients with hospital-acquired pneumonia at Peking University Third Hospital between January 2017 and December 2021. After excluding patients with an unclear diagnosis date or missing critical variables required for SOFA score calculation, 368 eligible patients with NV-HAP were included and randomly divided into a training cohort (n = 260) and an internal validation cohort (n = 108). An independent temporal validation cohort of 68 patients admitted between January 2022 and December 2022 at the same center was further used for temporal validation. Univariable and multivariable logistic regression analyses with backward stepwise selection were performed in the training cohort to identify predictors associated with progression to sepsis. A nomogram was then constructed based on the final model and evaluated by discrimination, calibration, and decision curve analysis. Results: A total of 368 patients were included in the model development dataset. The final multivariable model retained six predictors: male sex (OR = 2.393, 95% CI: 1.333–4.296), diabetes (OR = 2.205, 95% CI: 1.126–4.319), coagulation dysfunction (OR = 3.327, 95% CI: 1.726–6.413), PaO₂/FiO₂ (OR = 0.955 per 10-unit increase, 95% CI: 0.912–1.001), platelet count (OR = 0.900 per 10 × 10⁹/L increase, 95% CI: 0.853–0.949), and bilirubin (OR = 1.176 per 1 μmol/L increase, 95% CI: 1.100–1.258). The nomogram showed acceptable performance, with an apparent C-index of 0.809 and a bootstrap-corrected C-index of 0.792 in the training cohort. The C-index was 0.750 (95% CI: 0.658–0.841) in the internal validation cohort and 0.754 (95% CI: 0.639–0.870) in the temporal validation cohort. Calibration analysis showed acceptable agreement between predicted and observed probabilities, and decision curve analysis indicated a positive net clinical benefit across clinically relevant threshold probabilities. Conclusions: In patients with NV-HAP, male sex, diabetes, coagulation dysfunction, lower PaO₂/FiO₂, lower platelet count, and higher bilirubin were associated with progression to sepsis. The developed nomogram showed acceptable discrimination, calibration, and clinical utility, and may serve as a practical tool for early individualized risk stratification in patients with NV-HAP. Full article

Background/Objectives: The interplay between cardiovascular risk factors and brain aging remains incompletely understood. We aimed to investigate the comparative associations of coronary artery calcium (CAC) and low-density lipoprotein cholesterol (LDL-C) with MRI-derived volumetric measures of the brain. Methods: In this retrospective, single-center, cross-sectional study, 84 participants who underwent coronary computed tomography for CAC scoring and brain magnetic resonance imaging within 90 days were included; LDL-C levels were available in 69 participants for LDL-based analyses. Brain volumetric measures were obtained using the automated lesionBrain pipeline within the volBrain platform, which performs fully automated tissue segmentation and lesion quantification based on multi-atlas and patch-based approaches. Associations were evaluated using Spearman’s correlation with false discovery rate correction and hierarchical multivariable regression, supported by bootstrap validation and post hoc power analysis. The cohort had a mean age of 58.0 ± 13.0 years (range 19–78) and was derived from routine clinical imaging. Results: LDL-C was positively associated with abnormal white matter volume (ρ = 0.334, p = 0.005), although this did not remain statistically significant after FDR correction (pFDR = 0.090). In fully adjusted models, LDL-C remained the only independent predictor (β = 0.006, 95% CI: 0.002–0.010, p = 0.007; standardized β = 0.225; partial R² = 11.7%), corresponding to a 6.2% increase in abnormal white matter volume per 10 mg/dL increase (derived from log-transformed models). CAC showed only a marginal association (p = 0.059). Post hoc power analysis demonstrated adequate power for LDL-C but insufficient power for CAC. Neither marker was associated with gray matter volume. Conclusions: In this cross-sectional cohort, higher LDL-C was independently associated with greater abnormal white matter volume after adjustment for cardiovascular risk factors, statin use, and CAC. No CAC–brain association was detected in this cohort, but limited statistical power means that small CAC effects cannot be excluded. These findings should be interpreted as associative rather than causal or mechanistic. Full article