Search Results (8,408)

Background: The diagnosis of adult growth hormone (GH) deficiency (GHD) relies on demonstrating a reduced GH response to stimulation tests. Excess body weight, an increasingly prevalent condition, is associated with a blunted GH response to all types of stimulation tests. Therefore, establishing body mass index (BMI)-dependent cut-offs is essential for accurate interpretation. This study aimed to identify BMI-specific diagnostic thresholds for the insulin tolerance test (ITT), using residual pituitary function as the clinical gold standard. Methods: We retrospectively analyzed 105 patients with hypothalamic-pituitary disorders who underwent ITT. GHD was defined by the presence of at least three pituitary hormone deficiencies, while preserved somatotropic function was defined by the absence of other pituitary deficits and an insulin-like growth factor-I (IGF-I) standard deviation score ≥ 0. Receiver operating characteristic (ROC) curve analysis was used to determine optimal BMI-stratified cut-offs, defined as those maximizing sensitivity (SE) and specificity (SP). Results: The optimal GH cut-off was 2.8 μg/L for patients with normal weight (SE 84.6%, SP 97.4%) and those with overweight (SE 100%, SP 92.3%), and 2.1 μg/L for patients with obesity (SE 88.2%, SP 87.5%). The area under the ROC curve was 0.968, 0.957, and 0.897 for patients with normal weight, overweight, and obesity, respectively. Conclusions: This is the first study to define GH diagnostic thresholds for the ITT according to BMI, using a clinical definition of GHD as reference. More restrictive cut-offs in patients with obesity are needed to avoid GHD overdiagnosis and potential overtreatment. These findings should be considered hypothesis-generating and require prospective external validation before routine clinical implementation. Full article

Background/Objectives: Field-based health screening in adolescents requires accurate, non-invasive, and feasible diagnostic tools. This study evaluated the discriminatory capacity of anthropometric parameters and physical fitness tests for identifying waist-to-height ratio (WHtR)-defined surrogate cardiometabolic risk across sex and biological maturity status, determining exploratory cut-off thresholds. Methods: A cross-sectional study was conducted with 2944 Spanish adolescents (1459 males, 1485 females; age: 13.35 ± 1.20 years). Anthropometric variables (BMI, skinfolds, fat/muscle mass) and physical fitness tests (20-m shuttle run, handgrip, CMJ, SBJ, 20-m sprint, curl-up; evaluated in raw and body-mass-normalized formats) were assessed. Biological maturation was estimated via Age at Peak Height Velocity (APHV) using Mirwald equations and categorized into early, on-time, and late maturers relative to the sample mean. Surrogate risk was operationalized strictly as WHtR ≥ 0.50, without direct assessment of biochemical or hemodynamic parameters. Receiver operating characteristic (ROC) curves, optimal Youden-derived cut-offs, and internal bootstrap validation (1000 resamples) were performed. Results: Anthropometric parameters demonstrated high discriminatory performance for detecting WHtR-defined surrogate risk across all sex and maturation cohorts (AUC = 0.88–0.98). Unadjusted physical fitness tests showed poor overall classification performance. However, normalizing fitness metrics for body mass (particularly relative CMJ and cardiorespiratory fitness) substantially improved discriminatory capacity. Optimal cut-off values for anthropometric indicators displayed an observed descending pattern across progressively later-maturing cohorts. Conclusions: Anthropometric parameters represent highly accurate field proxies for WHtR-defined surrogate risk screening in adolescents. While unadjusted fitness metrics have limited utility for this anthropometric outcome, body-mass-normalized fitness parameters substantially recover classification capacity. Biological maturation timing should be carefully considered when future research derives and externally validates adolescent screening thresholds, as current cut-offs remain exploratory and sample-derived. Full article

Background: Chronic thromboembolic disease is a recognised sequela of acute pulmonary embolism and may occur with or without pulmonary hypertension. The purpose of this study was to evaluate differences in chronic thromboembolic burden, lesion type, and distribution between chronic thromboembolic pulmonary disease without pulmonary hypertension (CTEPD) and chronic thromboembolic pulmonary hypertension (CTEPH). Methods: This retrospective single-centre study included patients with CTEPD or CTEPH by right heart catheterisation using 2022 ESC/ERS criteria between 2021 and 2022. Two CTEPH patients were randomly selected per CTEPD patient. CTPA studies were reviewed by a blinded thoracic radiologist, assessing 32 pulmonary vessels from the main to segmental arteries for chronic thromboembolic lesions. Groups were compared by disease distribution, most proximal lesion level, Qanadli obstruction index, lesion type, and location. Exploratory receiver operating characteristic (ROC) analysis assessed discriminatory performance. Results: The 44 CTEPD and 88 CTEPH patients included had no differences in age, BMI, or sex. CTEPH patients had shorter six-minute walk distance (p = 0.001), greater right ventricular dilation/dysfunction (p < 0.001), and lower prevalence of deep vein thrombosis (p = 0.03). CTPA identified more lesions in CTEPH (21.2 vs. 10.0 lesions/case, p < 0.001) across more lobes (4.8 vs. 3.4, p < 0.001), with more proximal main/lobar disease (p < 0.001). CT obstruction index was 51% in CTEPH and 26% in CTEPD (p < 0.001). Total lesion number best discriminated CTEPH from CTEPD (AUC 0.91; optimal cutoff, 16 lesions). Conclusions: CTEPH demonstrates a greater, more diffuse, and more proximal chronic thromboembolic lesion burden on CTPA than CTEPD. Full article

Background and Objectives: The triglyceride-to-high-density lipoprotein cholesterol ratio (TG/HDL-C) is a simple lipid index associated with insulin resistance and atherogenic dyslipidemia. Previous evidence has supported the TG/HDL-C ratio as a simple surrogate marker of insulin resistance and an adverse metabolic profile. However, its relationship with glycemic control in real-world patients with type 2 diabetes mellitus (T2DM) remains uncertain. This study evaluated the association between the TG/HDL-C ratio and poor glycemic control in patients with T2DM. Materials and Methods: This retrospective observational study included patients with T2DM followed in outpatient clinics. Poor glycemic control was defined as glycated hemoglobin A1c (HbA1c) ≥ 7%. The association between the TG/HDL-C ratio and glycemic control was assessed using group comparisons, Spearman correlation, tertile analysis, and multivariable logistic regression adjusted for age, sex, LDL-C, total cholesterol, insulin use, statin use, and fenofibrate use. Receiver operating characteristic (ROC) analysis was used to evaluate the discriminatory performance of the TG/HDL-C ratio for identifying poor glycemic control. A sensitivity analysis was performed after excluding patients receiving fenofibrate. Results: A total of 1001 patients with T2DM were included, of whom 568 (56.7%) had poor glycemic control. The mean age was 60.9 ± 11.4 years, and 57.1% of participants were women. The poor- and adequate-glycemic-control groups were comparable with respect to age and sex. The TG/HDL-C ratio was higher in patients with HbA1c ≥7% than in those with HbA1c < 7% [3.35 (2.35–5.00) vs. 2.74 (1.87–3.82), p < 0.001] and increased progressively across tertiles. In multivariable analysis, the TG/HDL-C ratio remained associated with poor glycemic control after adjustment for available covariates (OR: 1.201, 95% CI: 1.125–1.282, p < 0.001). The association remained significant after excluding fenofibrate users. ROC analysis showed modest discrimination (AUC: 0.601, 95% CI: 0.566–0.636). Conclusions: The TG/HDL-C ratio was associated with poor glycemic control in patients with T2DM, showing a graded association across tertiles. However, its standalone discriminatory performance is modest. Given its modest discriminatory performance, the TG/HDL-C ratio should not be considered a standalone diagnostic or predictive tool for poor glycemic control; rather, it may serve as an accessible adjunctive metabolic marker associated with an adverse glycemic and lipid profile. Full article

Background/Objectives: Early risk stratification is essential in pulmonary embolism (PE), but a simple tool integrating routinely available clinical and laboratory variables is lacking. We aimed to develop a simple score for predicting 30-day mortality in patients presenting to the emergency department (ED) with PE. Methods: We conducted a multicenter study in three hospitals in Korea. The score was derived at the largest hospital using least absolute shrinkage and selection operator logistic regression with bootstrap stability selection, and validated in the pooled cohort from the remaining two hospitals. Discrimination was assessed using the area under the receiver operating characteristic curve (AUROC) and compared with PESI and sPESI. Calibration was assessed using the Brier score and calibration parameters. Results: Among 2446 patients, 1753 were included in the derivation cohort and 693 in the validation cohort. The final score (3C score) assigned one point each for history of cancer, international normalized ratio ≥1.15, and C-reactive protein ≥50 mg/L. In the validation cohort, the AUROC was 0.767 (95% CI, 0.703–0.822) for 30-day mortality, compared with 0.748 for PESI and 0.725 for sPESI. 30-day mortality increased from 2.4% (score 0) to 34.4% (score 3). A score of 0 identified 42.7% of patients as low risk, with a negative predictive value of 97.6%. Calibration was acceptable (Brier score, 0.077; calibration slope, 1.098). Conclusions: The 3C score showed discrimination comparable to PESI and sPESI and identified a substantial subgroup with low risk. Its simplicity may facilitate ED risk assessment, although further validation is required before clinical implementation. Full article

Objective: This study established a rat model of lipopolysaccharide (LPS)-induced acute lung injury (ALI) to evaluate pathological damage, collagen deposition, inflammatory cytokine levels, and key gene/protein expression following Hedyotis diffusa water extract (HDWE) intervention. Combined with ultra-high-performance liquid chromatography-quadrupole Orbitrap high-resolution mass spectrometry (UHPLC-Q-Orbitrap HRMS), transcriptomic analysis, and molecular simulation, this study identified the bioactive components of HDWE, evaluated their potential interactions with ALI-related targets, and explored the multi-omics-based protective mechanisms of HDWE. Methods: Thirty-six Sprague–Dawley (SD) rats were randomly divided into six groups: Control group, ALI group, DXMS group, HDWE-L group (100 mg/kg), HDWE-M group (200 mg/kg), and HDWE-H group (300 mg/kg). Hematoxylin and eosin (H&E) and Masson’s trichrome staining were used to evaluate lung pathological changes and collagen deposition. Enzyme-linked immunosorbent assay (ELISA) was used to measure serum tumor necrosis factor-α $\mathrm{T}\mathrm{N}\mathrm{F}-\mathsf{\alpha }$ interleukin-1β $\mathrm{I}\mathrm{L}-1\mathsf{\beta }$, erleukin-6 (IL-6), and interleukin-10 (IL-10) levels. Transcriptomic analysis identified differentially expressed genes (DEGs), followed by Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), receiver operating characteristic (ROC), and immune infiltration analyses. Quantitative real-time polymerase chain reaction (qRT-PCR) detected the mRNA expression levels of SPHK1, RELA, and NFKBIA. Immunohistochemistry evaluated the expression of eight hub targets, including endothelin-1 (EDN1), sphingosine kinase 1 (SPHK1), intercellular adhesion molecule 1 (ICAM1), interleukin-17 (IL-17), prostaglandin-endoperoxide synthase 2 (PTGS2/COX-2), NF-κB p65 (encoded by RELA), WT1-associated protein (WTAP), and myeloperoxidase (MPO). UHPLC-Q-Orbitrap HRMS characterized HDWE constituents. Molecular docking analysis was performed between 22 compounds and eight hub targets, followed by 100 ns molecular dynamics simulations and molecular mechanics-Poisson–Boltzmann surface area (MM/PBSA) binding free energy calculations for five core targets. Compared with the control group, the ALI group showed increased levels of TNF-α (86%), IL-1β (107%), and IL-6 (66%), accompanied by a 43% reduction in IL-10 and a 300% increase in lung collagen deposition. All HDWE doses alleviated inflammatory responses, with medium-dose HDWE showing the most pronounced effects. Specifically, medium-dose HDWE increased IL-10 levels by 52% and reduced IL-6, TNF-α, and IL-1β levels by 18%, 22%, and 11%, respectively. Transcriptomic analysis identified 2512 DEGs between the control group and ALI groups, 832 exclusive DEGs between the ALI group and HDWE-M groups, and 876 overlapping DEGs enriched in TNF, IL-17, and NF-κB signaling pathways. The eight-hub-gene diagnostic model achieved an area under the curve (AUC) of 0.969. RELA, SPHK1, and four other hub genes showed positive correlations with Th1, Th17, and neutrophil infiltration. In the ALI group, SPHK1, RELA, and NFKBIA mRNA expression levels were 1.30-, 0.96-, and 0.71-fold of those in the control group, respectively. Compared with the ALI group, high-dose HDWE treatment and low-dose HDWE treatment reduced SPHK1 expression to 0.62- and 0.57-fold, respectively, and increased NFKBIA expression to 1.68- and 1.58-fold, respectively. High-dose HDWE treatment reduced RELA expression to 0.43-fold. The expression levels of inflammation-related proteins were increased in the ALI group and were reduced after HDWE treatment. Twenty-two HDWE components were identified, 16 of which met the docking criteria. Asperulosidic acid exhibited favorable predicted binding affinities with all eight targets, with calculated binding free energies of −14.74, −14.92, −17.58, −23.04, and −16.10 kcal/mol for MPO, IL-17, NF-κB p65, PTGS2/COX-2, and SPHK1, respectively. Conclusions: This study provides systematic in vivo pharmacodynamic and in silico component-target evidence regarding the protective effects of HDWE against LPS-induced ALI. HDWE treatment increased NFKBIA expression and reduced SPHK1, RELA, and multiple inflammatory protein levels, suggesting that HDWE may regulate the IL-17/NF-κB-associated inflammatory network, although direct causal relationships require further validation. Asperulosidic acid may represent a key bioactive component with broad target-binding potential. This study was limited by the use of an LPS-induced rat ALI model without gene knockout or target inhibitor validation; therefore, further functional experiments are required to confirm the proposed regulatory mechanisms. Full article

Objective: Our objectives were to evaluate maternal serum YKL-40 levels in pregnancies complicated by preterm prelabor rupture of membranes (PPROM), compare them with healthy gestational age-comparable controls, and assess the association between YKL-40 levels and subsequent composite adverse neonatal outcomes (CANOs). Methods: This prospective observational study included 44 women with PPROM and 44 healthy pregnant controls between 24 and 37 weeks of gestation. Maternal serum YKL-40 concentrations were measured using an enzyme-linked immunosorbent assay (ELISA), with concentrations corrected for the manufacturer-specified 5-fold sample dilution. Multivariable Firth’s penalized logistic regression was used to evaluate the independent association of YKL-40 with PPROM and, within the PPROM cohort only, subsequent CANO. Exploratory receiver operating characteristic (ROC) analysis was performed to assess the ability of YKL-40 to discriminate established PPROM cases from healthy controls. The study was powered a priori only for the primary between-group comparison of YKL-40; the ROC and CANO analyses were not separately powered and are reported as exploratory. Results: Maternal serum YKL-40 levels were significantly higher in the PPROM group than in the control group (5.87 ± 2.64 vs. 2.44 ± 0.96 ng/mL, p < 0.001). In multivariable analysis, YKL-40 remained independently associated with PPROM (adjusted odds ratio 5.61, 95% CI 2.07–15.23, p < 0.001 per 1 ng/mL increase). Within the PPROM cohort, YKL-40 was not independently associated with CANO (p = 0.775). Exploratory ROC analysis yielded an AUC of 0.935 (95% CI 0.881–0.989); a ROC-derived cut-off of >3.3 ng/mL provided 86.4% sensitivity and 84.1% specificity for discriminating established PPROM cases from healthy controls. Conclusions: Maternal serum YKL-40 levels were significantly elevated in women with established PPROM and remained independently associated with PPROM status, but were not associated with subsequent CANO. Because YKL-40 was measured after PPROM diagnosis, the observed ROC performance reflects case–control discrimination rather than prospective prediction or established diagnostic utility. Larger prospective studies using clinically relevant comparison groups and independently validated assays are required to determine the potential clinical value of YKL-40 in PPROM. Full article

Objective: Ovarian, fallopian tube, and primary peritoneal cancers remain among the deadliest gynecological malignancies, largely because most cases are diagnosed at an advanced stage and no effective screening strategy is currently available. Increasing evidence suggests that many high-grade serous ovarian carcinomas originate from the fallopian tube. We aimed to explore the diagnostic performance of ex vivo fallopian tube cytology and the CytoSaLPs score for detecting tubal and adnexal malignancies in women undergoing salpingectomy or salpingo-oophorectomy. Methods: We conducted a prospective single-center observational study including 304 women undergoing salpingectomy or salpingo-oophorectomy for benign, premalignant or malignant gynecological indications between 2020 and 2023. Ex vivo cytological brushing of the distal fallopian tube was performed before fixation, followed by histopathological examination using the SEE-FIM protocol where appropriate. The primary analysis was performed at the specimen level. Of 544 paired specimens initially available for cytology–histology correlation, 53 non-diagnostic cytological specimens were excluded from the primary diagnostic performance analysis, leaving 491 evaluable paired specimens. Fallopian tube cytological findings were compared with histopathology as the reference standard. The discriminatory ability of the CytoSaLPs score was explored using receiver operating characteristic analysis. Results: Fallopian tube cytology demonstrated high sensitivity for histologically confirmed tubal malignancy, although specificity was moderate. Based on the primary specimen-level analysis, sensitivity was 94.4% and specificity was 71.0%. When fallopian tube cytology was compared with ovarian histology, sensitivity was 72.9% and specificity was 72.4%. For the adnexa considered as a single anatomical entity, sensitivity was 76.5% and specificity was 70.7%. The CytoSaLPs score showed good discriminatory ability for fallopian tube malignancy (AUC 0.8534), moderate discrimination for ovarian malignancy (AUC 0.6790), and fair discrimination for adnexal malignancy (AUC 0.730). The optimal score thresholds were derived from the same dataset and should therefore be considered provisional. Three serous tubal intraepithelial carcinoma lesions were identified histologically; two showed cytological abnormalities and elevated CytoSaLPs scores, whereas one specimen was non-diagnostic. Conclusions: This exploratory proof-of-concept study suggests that ex vivo fallopian tube and the CytoSaLPs score may provide a structured approach for detecting cytological abnormalities associated with tubal and adnexal malignancy. However, the findings were obtained in a tertiary gynecologic oncology population under ex vivo conditions, non-diagnostic specimens occurred in approximately 10% of samples, and the scoring system was developed and evaluated within the same cohort. Independent external validation and evaluation using clinically applicable in vivo sampling methods are required before any clinical implementation can be considered. Full article

Background/Objectives: Cutaneous squamous cell carcinoma (cSCC) is a highly prevalent malignancy. While Cemiplimab has transformed the treatment landscape across various disease stages, reliable pretreatment biomarkers for risk stratification remain lacking.. The Global Immune–Nutrition–Inflammation Index (GINI) is a composite biomarker integrating systemic inflammation and nutritional status into a single score. This study aimed to evaluate the prognostic value of the pretreatment GINI in patients with cSCC receiving Cemiplimab across all treatment settings. Methods: This retrospective cohort study evaluated 73 patients with unresectable, locally advanced, or metastatic cSCC treated with Cemiplimab between 2020 and 2023. Pretreatment laboratory parameters were extracted to calculate the GINI score. Receiver operating characteristic (ROC) curve analysis determined the optimal GINI cutoff to stratify patients into low- and high-GINI groups. Survival outcomes, including overall survival (OS) and progression-free survival (PFS), were analyzed using Kaplan–Meier curves and multivariable Cox proportional hazards models. Results: An optimal GINI cutoff of 74.4 divided the cohort into low-GINI (38%) and high-GINI (62%) groups. In the multivariable Cox regression models, a high pretreatment GINI remained independently associated with both inferior OS (adjusted HR 2.51, 95% CI 1.05–6.01, p = 0.039) and inferior PFS (adjusted HR 3.22, 95% CI 1.45–7.14, p = 0.004). When compared against five established inflammatory biomarkers (NLR, PLR, LMR, PNI, and CAR), the GINI consistently demonstrated comparable prognostic performance across multiple statistical approaches. Conclusions: The pretreatment GINI is a candidate prognostic marker for patients with cSCC undergoing Cemiplimab therapy. Given its cost-effectiveness and ready availability from routine clinical laboratory workups, the GINI score may improve prognostic risk stratification and could potentially inform risk assessment and clinical monitoring in real-world oncological practice. Full article

Background/Objectives: Machine learning is increasingly applied to identify hypertension from broad predictor panels, but whether it outperforms a few routine measurements is unclear. We compared machine learning pipelines against three readily obtained variables in a national Chilean survey. Methods: We analysed 5516 participants aged 15 years and older from the Chilean National Health Survey 2016–2017 with two valid blood-pressure readings. Hypertension was defined as mean systolic pressure ≥ 140 mmHg or mean diastolic pressure ≥ 90 mmHg or current antihypertensive treatment, the mean taken over the second and third readings. A total of 43 candidate predictors plus 11 laboratory missingness indicators formed 54 model inputs, excluding all blood pressure and hypertension-related variables. Data were partitioned once by census segment. Seventeen algorithms were compared under segment-grouped cross-validation with preprocessing fitted within folds; twelve were tuned identically, nested specifications independently, thresholds locked on development data and intervals derived from segment bootstrap. Results: Prevalence was 38.3% unweighted and 29.2% design-weighted. Across seven metrics, the twelve tuned pipelines were closely comparable, and none ranked first on all. On held-out data, the full XGBoost model reached an area under the receiver operating characteristic curve (AUC) of 0.890 (95% confidence interval [CI] 0.872 to 0.906) and the full penalised logistic model 0.882 (0.864 to 0.901). A model containing age, sex and waist-to-height ratio alone reached 0.882 (0.864 to 0.900) under XGBoost and 0.881 (0.861 to 0.898) under penalised logistic regression, differing from the corresponding full model of the nested comparison, which was tuned independently and reached 0.881 under penalised logistic regression and 0.891 under XGBoost, by −0.0004 (−0.0087 to +0.0081) under penalised logistic regression and −0.0084 (−0.0148 to −0.0024) under XGBoost, computed on unrounded values. Removing age cost 0.027 AUC. Findings held under design weighting, in the laboratory subsample and among untreated participants. Conclusions: Three routine measurements provided most of the discrimination achieved by fifty-four inputs; the remainder added no detectable increment under a penalised logistic specification and approximately 0.008 AUC under XGBoost. Equivalence was not formally tested, validation was internal, and transportability is undemonstrated. Full article

The active development of the foothill areas of the Almaty agglomeration (Southeastern Kazakhstan) requires reliable methods for landslide susceptibility assessment. This study aims to identify the spatial association between landslide occurrence and selected environmental and anthropogenic factors using the Frequency Ratio (FR) method and geographic information systems. The analysis is based on an inventory of 157 landslides, the SRTM digital elevation model, Landsat imagery, WorldClim climate data, geological maps, and OpenStreetMap data. Ten conditioning factors were analyzed: elevation, slope, aspect, precipitation, lithology, distance to faults, rivers and roads, the Normalized Difference Vegetation Index (NDVI), and land use. FR values were calculated for each factor and integrated to produce a landslide susceptibility map. Model performance was evaluated using Receiver Operating Characteristic (ROC) analysis and the Area Under the Curve (AUC). The resulting susceptibility map identifies areas with different levels of landslide susceptibility and provides a scientific basis for sustainable land-use planning, engineering-geological investigations, safer infrastructure development, natural hazard assessment, and disaster risk reduction in rapidly developing foothill regions. By supporting risk-informed land-use decisions and targeted mitigation measures, the study contributes to the long-term environmental safety and resilience of the Almaty agglomeration. Full article

Photovoltaic (PV) output degradation is difficult to detect early using outdoor operating data because it can overlap with normal output variations caused by solar irradiance and module temperature. This study evaluated PV output degradation detectability using irradiance-condition-specific relative-error distributions constructed from 1-min electrical and meteorological data from a 3 kW PV testbed. Irradiance-condition classes were defined using K_D and POP_D to reflect the daily irradiance levels and variability. For each class, a class-specific reference distribution was constructed from the normal-state relative-error distribution using Gaussian or kernel density estimation (KDE)-based density models according to goodness-of-fit. Output degradation conditions were simulated by reducing the measured power by 10–50%, and the separability between normal and output degradation conditions was evaluated using the negative log-likelihood (NLL) and right-tail (RT) scores. Performance was analyzed using the area under the precision–recall curve (AUC-PR), area under the receiver operating characteristic curve (ROC-AUC), recall, and F1 score. The results showed that 10–20% degradation was highly detectable under high-irradiance and low-variability conditions, whereas 40–50% degradation was required under low-irradiance or highly variable conditions. The RT score improved the threshold-based detection performance in some variable classes by reflecting the directional rightward shift caused by output degradation. These findings indicate that PV degradation detection should use irradiance-condition-specific reference distributions and directional degradation information, rather than a single reference distribution. Full article

Identifying the small group of customers who hold a given policy in severely imbalanced tabular data is a recurring screening problem in insurance analytics. This study considers binary caravan-insurance policy-ownership classification on the COIL 2000 benchmark, where the positive-class prevalence is below 6%. The benchmark is a single cross-section, so the label describes current ownership rather than a future purchase event. We propose an Attention-based Symmetric AutoEncoder (ASAE) that combines an auxiliary symmetric reconstruction branch, a channel attention gate, and a marginal log-variance regularizer on a 32-dimensional latent representation. The regularizer operates on individual latent variances and is treated as a heuristic rather than as an estimator of joint differential entropy. Under a common tuning and evaluation protocol on a stratified partition, the ASAE is compared with five conventional machine learning methods and seven neural models. Across five paired runs, it achieves an F1-score of 0.6008 ± 0.0115 and an area under the receiver operating characteristic curve (AUC) of 0.8584 ± 0.0034. Relative to TabNet, the strongest baseline considered, the mean differences are 0.064 in F1-score (95% confidence interval 0.043–0.085) and 0.032 in AUC (95% confidence interval 0.017–0.048). The ordering is preserved across five stratified re-splits, four imbalance-handling configurations, and a complete type-consistent preprocessing rerun in which nominal attributes are one-hot encoded, oversampled with SMOTENC, and reconstructed with categorical cross-entropy losses (F1-score 0.6241 ± 0.0074, AUC 0.8702 ± 0.0050). All reported results use stratified random partitions of COIL 2000. Because 27% of the records share an identical predictor vector with another record, the official challenge separation and two grouped partitions are also defined, so that exact-duplicate and sociodemographic overlap can be isolated from the primary split. The training code, split indices, and per-run predictions used for the reported tables are publicly available. Full article

Background: In heart failure with reduced ejection fraction (HFrEF), implantable cardioverter-defibrillators (ICDs) are used for the primary prevention of sudden cardiac death, yet many patients never receive appropriate therapy, and left ventricular ejection fraction (LVEF) alone poorly discriminates who will. We investigated whether a cumulative electrical risk score (ERS) derived from the surface electrocardiogram is associated with appropriate ICD therapy. Methods: In this single-center, retrospective study, 205 patients with HFrEF who underwent ICD implantation for primary prevention were classified according to whether they had received appropriate ICD therapy. A modified eight-parameter ERS was calculated from the baseline electrocardiogram. Associations were assessed using receiver operating characteristic (ROC) analysis and logistic regression. Results: The ERS showed moderate-to-good discrimination (AUC 0.795; p < 0.001); a cut-off of 3.5 yielded 91% sensitivity and 71.4% specificity. After adjustment for age, sex, LVEF, cardiomyopathy etiology, BNP and device duration, the ERS remained independently associated with appropriate ICD therapy (adjusted OR 2.189; 95% CI 1.246–3.845; p = 0.006). Conclusions: A cumulative electrical risk score from the standard electrocardiogram was independently associated with appropriate ICD therapy and may add risk information beyond LVEF. These retrospective findings warrant prospective, multicenter validation. Full article

Reservoir sweet spot screening combines seismic and well-log observations, but an observed gain may depend on the input representation, validation protocol, and construction of the screening target. We implement a controlled performance-decomposition protocol for paired observations from the public F3 Block. The protocol formalizes matched nested comparisons among log-only, basic seismic–log, and directional-gradient seismic–log representations. Within each contrast, the outer test observations, metric, model family, and validation-only selection rule remain fixed. For the composite target, basic fusion increases mean area under the receiver operating characteristic curve (AUROC) by 6.5, 8.8, and 3.4 percentage points for logistic regression, random forest, and gradient boosting, respectively. Directional-gradient enrichment changes AUROC by −5.6, +1.5, and −2.8 percentage points in the same model order. Spatial-block AUROC ranges from 49.4% to 57.8%, while leave-one-well-out AUROC ranges from 42.9% to 53.9%. The corresponding basic-fusion contrasts are −8.5 and +2.2 percentage points. A target-overlap audit shows that the measured fusion gain depends on target construction and directly corresponding log channels. Together, these controlled comparisons quantify how representation design, target construction, and validation protocol shape reported reservoir-screening performance. Full article