Search Results (2,936)

NASA’s Fire Information for Resource Management System (FIRMS) provides near-real-time thermal anomaly detections from VIIRS, but not all detections correspond to wildfire incidents: industrial heat, agricultural burning, and sensor artifacts produce false alarms that contribute to alert fatigue for emergency-management analysts. We study whether contextual machine learning (ML) features improve wildfire-incident classification from FIRMS detections, and—more importantly—whether reported gains survive leakage-controlled evaluation. We construct a labeled dataset by matching 521,395 VIIRS SNPP detections across CONUS in 2024 to 3766 NIFC 2024 wildfire perimeters, yielding 131,771 (25.3%) wildfire-matched and 389,624 candidate non-wildfire detections spanning 1067 distinct wildfire incidents. We benchmark five operational baselines and six classifiers under four validation regimes (random, event-aware, 5° spatial-block, and temporal holdout) with and without raw geographic coordinates. A naive random split inflates LightGBM to F1 $=0.985$, but a leakage-controlled event-aware split reduces it to F1 $=0.767$, and a spatial-block holdout to F1 $=0.627$. Feature attribution shows geographic coordinates account for 88.9% of model gain—the summed share of LightGBM’s total split-gain attributed to the three coordinate features within the full-feature model; removing coordinates improves spatial-block generalization from F1 $=0.627$ to $0.818$, demonstrating that raw coordinates drive memorization of where 2024 fires occurred rather than transferable discrimination. We further show that spatiotemporal clustering must be causal: a model using full-partition clustering appears strong (F1 $=0.908$) but leaks future detections, whereas a properly causal trailing-window version ties plain LightGBM in-distribution (F1 $=0.762$). Combining causal clustering with no raw coordinates is the most robust configuration under spatial transfer (spatial-block F1 $=0.868$ vs. $0.627$ for the coordinate model). Bootstrap 95% confidence intervals show these gaps far exceed statistical uncertainty, and sensitivity analyses show the conclusions are robust to the spatial-block size and to the clustering-window choice. Under natural class prevalence (14%), precision falls to 0.69, and results are sensitive to the labeling buffer. All ML models nonetheless far exceed FIRMS high-confidence thresholding (F1 $=0.128$). We argue that spatial leakage—not raw accuracy—is the central methodological issue for FIRMS wildfire-incident classification, and recommend coordinate-free, causal spatiotemporal-clustering features evaluated under spatial holdout. The system is intended as an analyst-prioritization decision-support layer, not autonomous incident confirmation. Full article

Alzheimer’s disease (AD) is the most prevalent neurodegenerative disorder worldwide, affecting approximately 56.9 million people in 2021 and projected to reach 152 million by 2050. Its defining pathological features, amyloid-beta plaques and neurofibrillary tangles, accumulate for up to two decades before cognitive symptoms emerge, placing the preclinical and mild cognitive impairment (MCI) stages at the centre of the early detection problem. Despite this, current diagnostic practice in routine clinical settings remains unreliable, with post-mortem studies placing the specificity of clinical AD diagnosis between 44.3 and 70.8% even in specialist memory clinics. Machine learning (ML) and deep learning (DL) applied to neuroimaging and electrophysiological data have emerged as candidate tools for closing this diagnostic gap, yet whether the accuracy figures reported in published studies translate into clinically useful performance on independent data remains unresolved. This study presents a structured comparative review of machine learning and deep learning methods reported across four publicly available Alzheimer’s disease datasets, namely the Alzheimer’s Disease Neuroimaging Initiative (ADNI), the Open Access Series of Imaging Studies (OASIS), the OpenNeuro ds004504 electroencephalography (EEG) dataset, and the Kaggle Alzheimer’s magnetic resonance imaging (MRI) dataset. Thirteen model families are examined through the published literature rather than through new experiments, and for each model and dataset combination, the best accuracy reported in the source study is recorded alongside the model’s mathematical formulation. All performance figures reported in this abstract and throughout the paper are taken from the published studies reviewed, not from new experiments conducted by the authors. Across the reviewed studies, deep learning architectures pre-trained on ImageNet and fine-tuned on neuroimaging data are reported to produce the highest accuracy on MRI classification tasks. Residual Network (ResNet)-101 is reported at 98.21 percent on ADNI and 97.45 percent on OASIS, while the IncepRes fusion architecture reaches 98.35% on OASIS by combining multi-scale feature extraction from InceptionV3 with residual connectivity from ResNet152V2. Traditional machine learning classifiers remain competitive on tabular clinical and biomarker data, with Extreme Gradient Boosting (XGBoost) reaching 91% on ADNI multiclass features. Logistic Regression achieves 82 to 85% on binary ADNI classification and is the only classifier in this review that provides explicit per-feature prediction contributions without post hoc tooling. Gaussian Naïve Bayes achieves 80 to 83% on the same task. On the OpenNeuro EEG dataset, K-nearest neighbours (KNN) with singular value decomposition (SVD) entropy features achieves 91% binary accuracy, with feature engineering quality determining performance more reliably than classifier architecture. Eight principal findings emerge from the cross-dataset analysis. Binary classification consistently outperforms multiclass by 10 to 30% across all datasets, reflecting the genuine biological ambiguity of the mild cognitive impairment category. Dataset size and augmentation predict reported accuracy more reliably than model architecture. Ensemble methods outperform individual classifiers by 5 to 8% in nearly every imaging study. Deeper architectures can overfit small clinical cohorts. EEG models trail MRI models by approximately 10 to 15% on comparable binary tasks. Cross-dataset generalisation has not been systematically evaluated in most studies, and the few that have tested it report accuracy drops of 5 to 10% or more when models encounter data from different scanners or cohorts. Eight recurring limitations constrain the clinical utility of these findings. Small sample sizes and limited demographic diversity, severe class imbalance inflating raw accuracy metrics, poor cross-dataset generalisation driven by scanner heterogeneity, limited deep learning interpretability, the dominance of binary over multiclass tasks, the absence of longitudinal modelling despite available datasets, inadequate standardisation of preprocessing and evaluation protocols, and the signal-to-noise ratio constraints specific to EEG recordings of elderly patients collectively define the gap between benchmark performance and clinical readiness. Future work must prioritise multi-centre training cohorts, multimodal fusion architectures, longitudinal progression modelling, and standardised interpretability evaluation as non-optional requirements for any system intended for clinical deployment. Full article

Exploratory lag-resolved correlation analysis is widely used when potential dependence between concurrently recorded signals may be delayed, transient, or weak. In autocorrelated time series, however, scanning across candidate lags creates a multiple-comparison problem, while temporal dependence invalidates naive permutation or parametric correlation tests. This paper presents a practical dependence-aware scan-level inference procedure for exploratory lag-resolved correlation analysis under temporal autocorrelation. The procedure combines baseline standardisation, lag-resolved Pearson correlation, dependence-preserving surrogate construction (here implemented using block permutation), and max-statistic correction so that inference is performed on the largest absolute correlation observed across the scanned lag domain rather than on post hoc selected lags. The contribution is integrative rather than metric-driven: established components are assembled into a fixed, auditable inference pipeline that preserves within-channel temporal structure while controlling familywise error across exploratory lag scans. The procedure is intended for multi-sensor stochastic systems in which weak synchrony must be distinguished from artefacts of temporal dependence and analytical flexibility. Synthetic null simulations illustrate false-positive inflation under naive lag scanning, characterise calibration through a block length sensitivity analysis, and compare complete inference pipelines, demonstrating that, under the dependence regimes examined here, valid exploratory lag inference requires scan-level multiplicity control in addition to dependence-preserving surrogate generation. Full article

Background and Clinical Significance: Iatrogenic aorto-ostial dissection is a rare but potentially life-threatening complication of percutaneous coronary intervention (PCI), most commonly involving the right coronary artery. Although ostial stenting is generally considered the standard bailout strategy, failure of initial sealing may occur in selected anatomical settings and remains poorly understood. A focused narrative review of the literature was conducted through PubMed/MEDLINE, Scopus and Web of Science to identify reports of PCI-related aorto-coronary dissection with particular attention to dissection morphology, propagation mechanisms, bailout strategies, and outcomes after ostial stenting; Case Presentation: A 76-year-old man presented with non-ST-elevation myocardial infarction. Coronary angiography showed severe ostial right coronary artery (RCA) disease and significant left anterior descending artery stenosis. Following drug-eluting stent implantation in the RCA, extensive aorto-ostial dissection with retrograde extension into the sinus of Valsalva occurred. Initial ostial stenting failed to seal the dissection and was complicated by hyperacute stent thrombosis. After successful rewiring of the true lumen, a second overlapping drug-eluting stent was implanted using a stent-in-stent technique, followed by prolonged balloon inflation, achieving complete sealing and stabilization. Serial computed tomography angiography confirmed stability, and staged PCI of the LAD was successfully performed five days later; Conclusions: Failure of primary sealing may depend not only on procedural factors but also on dissection morphology. Transverse dissections with wide entry tears may be less effectively sealed by a single ostial stent, whereas overlapping stenting with prolonged balloon inflation may represent a more effective bailout strategy. Full article

Landslide susceptibility mapping (LSM) serves as a fundamental technical support for geohazard prevention and mitigation across mountainous terrains. This research constructs a multi-scale terrain unit integrated modeling framework targeting complex mountainous geomorphic settings, taking Zhenping County as the research object. Multi-resolution digital elevation model (DEM) datasets, multi-source satellite remote sensing imagery (GF-2), geological vector datasets and hydrological survey data are jointly adopted as the basic data source. The r.slopeunits module embedded in GRASS GIS is utilized to automatically segment slope units, and a comprehensive composite index S, coupling slope partition quality indicator F and model prediction accuracy metric R, is proposed to adaptively optimize two critical slope-unit hyperparameters: circular variance (c) and minimum unit area (a). Four DEM spatial resolutions (15 m, 25 m, 50 m, 100 m) are systematically calibrated with 42 groups of c–a parameter combinations to screen out the optimal slope-unit segmentation scheme (c = 0.1, a = 200,000 m²). Twelve landslide predisposing covariates covering topography, hydrology, lithology, human engineering activities and land cover are selected after multicollinearity diagnosis via Variance Inflation Factor and mean utility factor contribution evaluation. Logistic regression tree (LMT), LMT-Adaboost and LMT-Random Subspace are compared by random cross-validation and spatial block cross-validation. Parameter sensitivity analysis is further carried out to quantify the stability of model outputs against DEM resolution and slope-unit parameter perturbations. The LMT-RSM ensemble achieved the highest spatial cross-validation AUC (0.954 ± 0.019), outperforming LMT (0.925 ± 0.023) and AdaBoost-LMT (0.934 ± 0.021). The DeLong test confirmed that LMT-RSM’s superiority over LMT is statistically significant (p < 0.0001). The proportion of landslides in the very high and high susceptibility zones under the LMT-RSM model reached 95.98%, demonstrating relatively excellent spatial discrimination. This study provides an operational framework combining optimized slope units, ensemble learning, and spatially explicit validation for robust LSM in complex terrain, and offers a reproducible technical pathway for landslide risk prevention in mountainous regions. Full article

Geopolitical disruptions at maritime chokepoints cascade through interconnected economic systems, yet the pathways along which such shocks travel and the nodes at which they are absorbed remain poorly understood. The aim of this study is to trace, within a single coupled framework, how the 2026 Strait of Hormuz oil-price shock propagated through Korean-origin aviation demand, Southeast Asian destination tourism, and the macroeconomies of four oil-importing economies, and to identify where and how the shock was absorbed. Treating the disruption as an exogenous perturbation, we follow its diffusion across four interacting nodes: oil prices, Korean-origin aviation demand to Southeast Asian destinations, destination-level tourism flows, and national macroeconomic states. Using a triple-difference design with event-study and placebo-year tests on monthly route-level data, and supported by explicit parallel-trend, control-stability, and route-classification robustness checks, we find that aviation demand to leisure routes contracted by roughly 27%, accompanied by an almost identical fall in flight frequency and an unchanged load factor—a pattern consistent with a market-clearing capacity adjustment. The effect concentrated after the March blockade and stabilized thereafter, suggesting a self-limiting rather than self-amplifying dynamic. Downstream, destination-level arrivals did not contract proportionally, plausibly buffered by source-market substitution that scales with a destination’s market diversification. Along the macroeconomic branch, the same shock co-moved with rising inflation and depreciating currencies, but the magnitude of these responses varied with fuel-pricing and exchange-rate regimes. We interpret these findings as an exploratory, systems-level account in which chokepoint oil shocks act as multi-node propagation-and-absorption processes, where resilience appears to emerge endogenously from market substitution and policy–regime heterogeneity rather than being externally imposed. Full article

Modern Bayesian hierarchical methodologies allow us to leverage spatio-temporal dependencies between observations, enhancing both health effect estimation and map visualization in efficient and flexible ways. However, the necessary levels of statistical software are often unavailable or difficult to access. We have recently examined Bayesian spatio-temporal models to estimate the association between COVID-19 death counts and various social and environmental risk factors, including ambient air pollution exposure. Typically, it is very common that in an infection disease mapping problem with count data, we have excessive zeros, and it is usually for over-dispersed count outcome variables. Furthermore, the theory suggests that the excess zeros are generated by a separate process from the count values and that the excess zeros need to be modeled independently. Our proposed models are specially designed to handle the zero-inflation and over-dispersion in count data through Zero-Inflated Negative Binomial regression with random effects that vary across time and space within a Markov Chain Monte Carlo framework. Drawing on our knowledge and experience, we aim to provide a simple, unified, and publicly available software that can be applied in various disease mapping studies under the contemporary Bayesian framework. Full article

Whether environmental, social, and governance (ESG) disclosure stabilizes share prices or merely masks bad news, it remains unsettled, and the evidence is conspicuously weak whenever the relationship is assumed to be linear. This study revisits the question by allowing the effect of ESG disclosure on future stock price crash risk to be nonlinear and by breaking down disclosure into its environmental, social, and governance components. Using an unbalanced panel of non-financial firms listed on the Ho Chi Minh Stock Exchange over 2018–2024, we estimate firm and year fixed effects models with firm-clustered standard errors, measuring one-year-ahead crash risk by negative conditional skewness (NCSKEW) and down-to-up volatility (DUVOL). Consistent with prior work, the linear association between overall ESG disclosure and crash risk is statistically insignificant. Once a quadratic term is introduced, however, a U-shaped relationship emerges, and dimension-level tests show that this curvature is driven almost entirely by social disclosure: the linear term is negative and the squared term positive and significant for both crash risk proxies, with turning points of 0.3316 (NCSKEW) and 0.2918 (DUVOL). The U shape is confirmed by the formal test of Lind and Mehlum for both proxies, is robust to additional profitability and valuation controls and, most strongly for NCSKEW, to panel-corrected and feasible-GLS estimators. Low variance inflation factors confirm that multicollinearity does not affect the estimates. The findings support a “too-much-of-a-good-thing” interpretation: social disclosure improves transparency and reduces crash risk up to a moderate threshold, beyond which incremental, hard-to-verify narrative disclosure becomes consistent with impression management and heightens crash risk. Because the turning point lies below the first quartile of social disclosure, most sample firms already operate where additional disclosure raises crash risk. This study reframes the ESG crash risk debate around the level and dimension of disclosure rather than its mere quantity. Full article

Background/Objectives: Korea has undergone rapid epidemiological transitions in cancer incidence over the past two decades. Using a 25-year nationwide dataset (1999–2023), we characterize long-term trends for 61 cancer types, examine inter-cancer correlations, and forecast incidence to 2028. Methods: Annual incidence counts, crude rates, and age-standardized incidence rates (ASIRs) stratified by sex were obtained from the Korea Central Cancer Registry (KCCR) via the Korean Statistical Information Service (KOSIS). Annual percent change (APC) was estimated using log-linear regression. Pearson correlation coefficients were computed among cancer-specific ASIRs, with false-discovery-rate (FDR) correction for multiple comparisons. Multiple and hierarchical regression evaluated the statistical association of individual cancer types with the overall cancer rate, and variance inflation factors (VIFs) were used to quantify multicollinearity. Time series forecasting used damped Holt–Winters exponential smoothing; forecast accuracy was assessed with rolling-origin cross-validation (RMSE, MAE, MAPE) and benchmarked against ARIMA. A sensitivity analysis excluding the pandemic years (2020–2021) tested the robustness of trend estimates. Five-year prevalence data (2007–2023) were analyzed from the KCCR prevalence module. Results: Total cancer incidence increased from 101,854 in 1999 to 288,613 in 2023, a 183% increase. The overall ASIR rose from 402.7 to 522.9 per 100,000 (2020 standard population). The three fastest-growing cancers were thyroid (APC +7.56%, p < 0.001), prostate (+6.98%, p < 0.001), and breast (+5.03%, p < 0.001). Stomach (APC −2.20%) and liver (−2.90%) cancers showed significant declines. Hierarchical regression showed that adding thyroid, breast, and prostate to lung and stomach increased explained variance from R² = 0.449 to 0.997; however, high VIF values (up to ~263) indicate substantial multicollinearity and compositional dependence, so these coefficients should not be read as independent causal contributions. Holt–Winters and ARIMA produced comparable accuracy (mean MAPE 4.6% vs. 4.7%). The five-year cancer prevalence pool reached 1,035,107 in 2023. Forecasting projects a total incidence of approximately 319,000 by 2028. Conclusions: Korean cancer epidemiology is undergoing a transition from infection-related cancers toward hormone-sensitive and screening-detectable malignancies. These findings support strategic resource allocation for high-growth cancers while maintaining vigilance over rising pancreatic and other emerging cancers. Full article

Reducing aerodynamic drag on medium-duty freight trucks is essential for improving fuel efficiency; however, the relationship between local flow modification, aerodynamic loads, and propulsion-power demand has not yet been sufficiently quantified. This study evaluates the aerodynamic influence of a front deflector on a Chevrolet NQR 1015 box truck using steady RANS CFD with the k–ω SST turbulence model under zero-yaw conditions from 50 to 120 km/h. The numerical setup included near-wall inflation layers and mesh characterization, as well as grid-independence assessments based on C_D, and the Grid Convergence Index. The deflector produced consistent aerodynamic improvements, reducing average drag coefficient by 14.1%, while the average lift coefficient decreased by 73.5%. These aerodynamic changes reduced the average required propulsion power from 53.86 kW to 50.39 kW, corresponding to a 6.4% reduction, with a maximum saving of 8.1% at 120 km/h. Pressure, velocity, and pressure-coefficient C_P distributions indicate that the deflector promotes smoother flow redirection at the cab–box transition, attenuates suction peaks, and suggests lower pressure losses associated with the separated-flow and wake regions. Full article

Regression methods are widely used to investigate macroeconomic relationships; however, they are generally estimated without first examining whether the underlying variables exhibit fractal structures, persistence, and chaotic dynamics. Although nonlinear regression models relax the assumption of linearity, they rarely account for the complex geometric, long-memory, and dynamical properties that characterize macroeconomic time series. Motivated by this limitation, this study proposes a fractal-oriented Lie regression framework that integrates fractional persistence and Lie algebra to model nonlinear macroeconomic interactions within a unified analytical structure. For Türkiye, the empirical analysis employs monthly data on inflation, interest rates, exchange rates and oil prices covering the period 2000M1–2026M1, encompassing major economic crises and structural breaks. Prior to model estimation, the dynamical characteristics of the variables are examined using entropy measures, long-range dependency analysis, Lyapunov exponents and attractors. The results reveal persistent fractal structures, significant fractional dependence and chaotic behavior, indicating that macroeconomic variables evolve within a complex nonlinear dynamical system rather than around a conventional equilibrium. Based on these results, the variables are represented within a Lie algebra framework in which nonlinear transformation matrices preserve the underlying geometric structure while simultaneously capturing both self-dynamics and cross-variable interactions. The proposed Lie regression model demonstrates substantial improvements over standard regression methods in both model adequacy and forecasting performance. Oil prices emerge as the dominant transmitter of shocks by generating pronounced asymmetric effects on inflation, exchange rates and overall macroeconomic stability. The model achieves remarkable forecasting accuracy by reducing RMSE, MAE, and MAPE from 18.58, 13.61, and 69.92 under a standard regression model to 0.27, 0.22 and 16.4, respectively. Finally, the estimated Lie transformation matrix is employed as a policy-simulation mechanism to evaluate the transmission of alternative oil-price shocks. Scenarios based on 5%, 10%, and 20% increases in oil prices quantify the resulting adjustments in inflation, interest rates, and exchange rates by providing forward-looking assessments of macroeconomic vulnerability. The proposed framework extends standard regression analysis by explicitly incorporating fractional persistence and chaotic dynamics into a Lie algebra representation, thereby offering a more accurate and theoretically consistent approach for modeling complex macroeconomic systems. Full article

Accurate wildfire prediction increasingly determines whether emergency resources arrive before a disaster becomes uncontrollable, yet the dominant paradigm reduces the problem to binary occurrence, offering no estimate of the severity that drives suppression planning. This study develops a machine-learning framework for four-class wildfire severity prediction, conditional on ignition, from weather-station observations and calendar terms alone. We construct a composite severity index (CSI) by applying principal component analysis to five damage dimensions (burned area, suppression equipment, personnel, duration, and property loss) recorded for 868 wildfires in Gangwon Province, South Korea (2011–2022) and pair standard observations with effective humidity and six indices of the Canadian Forest Fire Weather Index (FWI) System. Under a leakage-safe protocol, the strongest tree ensembles reach a macro F1 of 0.46 to 0.50 (recommended configuration: 0.41 ± 0.03 across 20 repeated splits) against a four-class chance level of 0.25, and the recommended Random Forest attains an extreme-class recall of 0.474; the CSI target outperforms burned area by 5.5 macro-F1 points under identical inputs. A weather-only screen separates extreme from non-extreme events with an ROC AUC of 0.758, capturing 47% of extreme events at a 20% alert budget. We also quantify how oversampling misplaced before the train-test split inflates the macro F1 to 0.65–0.83, a cause for caution for the severity-prediction literature. Full article

Background: Uterine fibroids are the most common benign tumors of the female reproductive system and frequently affect women’s health-related quality of life (HRQoL). The increasing use of online surveys in clinical research raises concerns regarding the comparability and reliability of data collected through different recruitment methods. This study aimed to compare the clinical and methodological comparability of data obtained from an online survey and a clinic-based survey assessing symptom severity and HRQoL among women diagnosed with uterine fibroids. Methods: A cross-sectional observational study was conducted among 167 women with confirmed uterine fibroids. The clinic-based cohort included 82 patients recruited in a gynecological outpatient clinic, while the online cohort consisted of 85 women participating through an internet-based survey. Both cohorts were assessed using identical inclusion and exclusion criteria, the same questionnaire structure, and the validated Uterine Fibroid Symptom and Health-Related Quality of Life (UFS-QoL) instrument. Symptom severity scores and HRQoL outcomes were compared descriptively and methodologically. Results: The two independently recruited cohorts showed broadly similar distributions of several demographic characteristics and patient-reported outcomes, although important differences between the source populations should be considered when interpreting these findings. Mean symptom severity scores were 48.55 ± 21.61 in the clinic-based cohort and 46.33 ± 21.40 in the online cohort, while mean HRQoL scores were 57.23 ± 22.81 and 62.50 ± 19.32, respectively. Formal comparisons revealed no significant differences in symptom severity (p = 0.506) or overall HRQoL (p = 0.110). Among the six UFS-QoL domains, only the Concern domain differed significantly between cohorts (p = 0.005), whereas all other domains showed broadly similar distributions. Separate multivariable regression models were fitted for each cohort. Although direct comparison of the models was limited by differences in variable coding, both models identified symptom severity as the strongest independent predictor of HRQoL (β = −0.715 and β = −0.752) and showed similar overall model performance (R² = 0.595 and 0.578). Regression diagnostics confirmed normality of residuals, homoscedasticity, absence of influential outliers, and low variance inflation factors in both datasets. Conclusions: Despite differences in recruitment setting and source population, similar patterns of patient-reported HRQoL and symptom severity were observed across the two independently recruited cohorts. Similarities were observed across overall HRQoL scores, symptom severity measures, and multivariable regression models, suggesting that the relationships between symptom burden and quality of life remained consistent across recruitment methods. Although differences were identified in disease-related concerns and reproductive history, these findings did not substantially alter the overall pattern of results. Taken together, the findings demonstrate that similar patterns of patient-reported HRQoL and symptom severity were observed across two independently recruited cohorts of women with uterine fibroids. These findings support the feasibility of collecting disease-specific patient-reported outcomes within uterine fibroid-specific online communities but should not be interpreted as evidence that online and clinic-based recruitment methods generate equivalent study populations. Full article

Background/Objectives: Healthcare-associated infections (HAI) affect an estimated 4.3 million patients annually in EU/EEA hospitals; yet, reported prevalence rates vary nearly fivefold across member states, a degree of variation inconsistent with clinical or epidemiological differences alone. Romania exemplifies this paradox: it records one of the lowest reported HAI prevalence rates in Europe while sustaining one of the highest antimicrobial consumption levels on the continent. This study examines whether antimicrobial consumption data can serve as a cross-check on reported HAI prevalence across EU/EEA countries and discusses implications for European funding mechanisms. Methods: A cross-sectional ecological analysis was conducted using data from 26 EU/EEA countries. HAI prevalence was extracted from the ECDC Point Prevalence Survey 2022–2023; antimicrobial consumption indicators from the ESAC-Net Annual Epidemiological Report 2023. Pearson and Spearman correlations, multiple linear regression with Cook’s distance diagnostics, bootstrap resampling, and k-means cluster analysis were performed. Variance inflation factors were computed to assess multicollinearity; community sector AMC was excluded from the final regression model due to near-perfect collinearity with total AMC. Results: No antimicrobial consumption indicator was significantly associated with reported HAI prevalence (total AMC: r = 0.274, p = 0.175; broad-spectrum hospital proportion: r = 0.082, p = 0.692); bootstrap confidence intervals confirmed the instability of all estimates. Romania and Bulgaria were identified as influential outliers whose consumption profiles are substantially inconsistent with their reported infection rates, with model-based estimates of 7.3% and 7.0% respectively against reported values of 3.1% and 3.7%. Cluster analysis placed both countries in an isolated group with the highest antimicrobial consumption and broad-spectrum hospital antibiotic use in the sample alongside the lowest reported HAI prevalence, a configuration not replicated elsewhere in the EU/EEA. Conclusions: The absence of a significant aggregate association between antimicrobial consumption and reported HAI prevalence, combined with the systematic identification of Romania and Bulgaria as influential observations whose consumption profiles are inconsistent with their reported infection rates, raises the hypothesis of surveillance underreporting as a plausible explanation, though the ecological design does not permit causal inference and alternative explanations, including differences in antimicrobial stewardship maturity and prescribing culture, cannot be excluded. Antimicrobial consumption indicators, particularly the proportion of broad-spectrum antibiotics in hospital use, may serve as a proxy for HAI burden where direct surveillance is incomplete, and their integration into European surveillance frameworks is warranted. These findings have direct policy relevance for the allocation of resources under EU4Health, EU-JAMRAI 2, and national recovery and resilience programmes, and support investment in surveillance reform as a precondition for effective infection prevention programmes. Full article

Investors’ behavior in the auctions for government bonds is closely associated with the processing and valuing of information. This study explores investors’ behavior in relation to information in the context of the sovereign debt market in Armenia in August 2017 to December 2025. Armenia has a small financial market, which is relatively deep and involves only a small number of investors. This particular situation allows for testing the applicability of the rational inattention theory. While information in a small open economy can be abundant, it does not follow that information is valued in the same way. Investors in a small open economy focus their attention on monitoring some salient policy variables, including the central bank policy interest rate and headline inflation but ignore some more specific signals such as demand dynamics. We suggest that the spread between the cut-off yield and the weighted average yield in the auction can be used as a measure of information inattention. According to the rational inattention theory, investors allocate their attention strategically and focus on those signals that can be obtained easily and publicly. Therefore, our hypothesis is that the auction spread is consistent with partial information processing, whereby demand signals are underweighted relative to the policy rate. Indeed, the analysis suggests that the cut-off yield remains correlated with the policy rate, whereas the spread does not increase. This is consistent with the hypothesis that yield spreads reflect bounded rationality in attention allocation. During the periods of increased need for government borrowing, auctions become the key sources of signaling and thus need to be studied. Full article