Search Results (45,234)

Hypertension remains one of the most pressing public health challenges worldwide, affecting more than one billion individuals and serving as a principal risk factor for cardiovascular morbidity and mortality. Whilst blood pressure measurement constitutes a routine component of clinical practice, the capacity to predict blood pressure values from readily obtainable patient characteristics could substantially enhance preventive care strategies and facilitate timely intervention. The present study examines whether machine learning methodologies can reliably forecast blood pressure measurements utilizing cardiovascular risk factors in conjunction with demographic and anthropometric data. We have analyzed data from 68,616 individuals following rigorous quality assessment of 70,000 patient records obtained from Kaggle’s cardiovascular disease repository. Beyond the 10 original variables, we engineered additional features encompassing demographic patterns, body composition indices, clinical risk indicators, and their interactions. Nine distinct predictive models were systematically evaluated, spanning from elementary baseline approaches through to sophisticated gradient boosting ensembles. CatBoost demonstrated superior performance, yielding systolic blood pressure predictions with a root mean squared error (RMSE) of 14.37 mmHg and coefficient of determination (R²) of 0.265, alongside diastolic blood pressure predictions with RMSE of 8.57 mmHg and R² of 0.187. These modest explained variance values—substantially below unity—reveal a fundamental limitation: blood pressure proves remarkably resistant to prediction from the demographic, anthropometric, and clinical variables typically available in epidemiological datasets. These findings illuminate a sobering reality regarding blood pressure prediction from routinely collected clinical data. The observation that standard variables account for merely one-quarter of blood pressure variance should temper expectations for machine learning applications within this domain, whilst simultaneously underscoring the necessity for richer data sources or novel biomarkers to achieve clinically meaningful predictive accuracy. Full article

Osteoarthritis (OA) is the most common form of arthritis and represents a major clinical and socioeconomic burden. Epidemiological data consistently show that OA affects women more frequently and, in several joints, more severely than men. Nevertheless, current in vitro models rarely consider sex-specific variables, limiting their ability to capture the biological mechanisms that shape the pathogenesis and progression of OA. Increasing evidence indicates that age-related hormonal fluctuations and subchondral bone remodeling strongly influence OA evolution, and that these processes differ between the sexes. For instance, the decline in estrogen levels during menopause has been associated with accelerated cartilage degeneration, increased osteoclastic activity, and a higher susceptibility to subchondral bone alterations, which may contribute to more aggressive clinical manifestations in women. These mechanisms are only partially reproduced in widely used experimental systems, including traditional biomaterial scaffolds and simplified osteochondral constructs, leaving important sex-dependent pathways unresolved. While advanced biomaterials enable precise control of stiffness, porosity, and biochemical cues, most current in vitro OA models still rely on sex-neutral design assumptions, limiting their ability to reproduce the divergent disease trajectories observed in men and women. By integrating material properties with dynamic loading and tunable hormonal conditions, next-generation in vitro systems could improve mechanistic understanding, increase the reliability of drug screening, and better support the development of sex-specific therapies through the combined efforts of bioengineering, materials science, cell biology, and translational medicine. Full article

Background: Alzheimer’s disease (AD), a progressive brain disorder, is the most common form of dementia and necessitates the development of effective intervention strategies. Ginseng-Natto composite fermentation products (GN) have demonstrated beneficial bioactivities in mouse models of AD; however, the underlying mechanism of action through which GN ameliorates AD requires further elucidation. Methods: Mice received daily intragastric administration of low- or high-dose GN for 4 weeks, followed by intraperitoneal injection of scopolamine to induce the AD model. The pharmacological effects of GN were systematically evaluated using the Morris water maze test, ELISA, and H&E staining. To further investigate the underlying mechanisms, 16S rRNA gene sequencing and metabolomics were employed to analyze the regulatory effects of GN on the gut–brain axis. Additionally, Western blotting was performed to assess the impact of GN on blood–brain barrier (BBB) integrity. Results: GN intervention significantly ameliorated cognitive deficits and attenuated neuropathological injury in AD mice, restoring the brain levels of acetylcholine (ACh), acetylcholinesterase (AChE), superoxide dismutase (SOD), malondialdehyde (MDA), glutathione peroxidase (GSH-Px), interleukin-6 (IL-6), and tumor necrosis factor-α (TNF-α) to normal ranges. GN reshaped the gut microbiota by promoting beneficial bacteria and inhibiting pro-inflammatory strains. It also regulated key metabolic pathways related to amino acid and unsaturated fatty acid metabolism. This metabolic remodeling restored the compromised BBB integrity by upregulating tight junction proteins (ZO-1, Occludin and Claudin-1). Conclusions: Our findings demonstrate that GN ameliorates AD through a gut-to-brain pathway, mediated by reshaping the microbiota-metabolite axis and repairing the BBB. Thus, GN may represent a promising intervention candidate for AD. Full article

Introduction: Rare diseases disperse expertise across institutions and borders, making structured second-opinion systems a pragmatic way to concentrate subspecialty knowledge and reduce diagnostic delays. This scoping review mapped the design, governance, adoption, and impacts of such services across implementation scales. Objectives: To describe how second-opinion services for rare diseases are organized and governed, to characterize technological and workflow models, to summarize benefits and barriers, and to identify priority evidence gaps for implementation. Methods: Using a population–concept–context approach, we included peer-reviewed studies describing implemented second-opinion systems for rare diseases and excluded isolated case reports, purely conceptual proposals, and work outside this focus. Searches in August 2025 covered PubMed/MEDLINE, Scopus, Web of Science Core Collection, Cochrane Library, IEEE Xplore, ACM Digital Library, and LILACS without date limits and were restricted to English, Portuguese, or Spanish. Two reviewers screened independently, and the data were charted with a standardized, piloted form. No formal critical appraisal was undertaken, and the synthesis was descriptive. Results: Initiatives were clustered by scale (European networks, national programs, regional systems, international collaborations) and favored hybrid models over asynchronous and synchronous ones. Across settings, services shared reproducible workflows and provided faster access to expertise, quicker decision-making, and more frequent clarification of care plans. These improvements were enabled by transparent governance and dedicated support but were constrained by platform complexity, the effort required to assemble panels, uneven incentives, interoperability gaps, and medico-legal uncertainty. Conclusions: Systematized second-opinion services for rare diseases are feasible and clinically relevant. Progress hinges on usability, aligned incentives, and pragmatic interoperability, advancing from registries toward bidirectional electronic health record connections, alongside prospective evaluations of outcomes, equity, experience, effectiveness, and costs. Full article

Bidens pilosa L., a traditional Chinese medicinal herb, has been used in clinical practice for the treatment of inflammatory diseases and cancer. BPA, an extract derived from the whole herb of B. pilosa L., has been shown to possess potent immunomodulatory properties by regulating tumor-associated macrophages (TAMs) and regulatory T cells (Tregs) within the tumor microenvironment (TME) in a mouse syngeneic colorectal cancer (CRC) model. RT-PCR and flow cytometry analyses showed that BPA, together with its flavonoid and polyacetylene constituents, effectively suppressed the differentiation of M2-TAMs and Tregs by downregulating Arg-1 and CD25 expression. They had minimal effects on the expression of markers associated with M1-TAMs and promoted the proliferation of CD4⁺ T cells that were inhibited by M2-TAMs and Tregs. In mice, BPA markedly inhibited the growth of syngeneic CRC tumors, accompanied by decreased serum levels of the immunosuppressive cytokine IL-10 and reduced expression of the proliferative marker Ki67 in tumor tissues. Moreover, BPA downregulated the mRNA expression of markers associated with M2-TAMs and Tregs, while increasing markers associated with M1-TAMs. Western blot analyses of tumor tissues revealed that BPA reduced the expression of marker proteins associated with M2-TAMs and Tregs, while increasing the expression of the immune-stimulatory markers CD80, GITR and CD4. In addition, combined treatment with BPA and 5-fluorouracil (5-FU), a commonly used chemotherapeutic agent for CRC, notably enhanced the anti-tumor effect in mice. These findings indicate that BPA, an active extract of B. pilosa L., showed antitumor activity in mice by suppressing the differentiation of pro-tumorigenic TAMs and Tregs within the TME. Full article

Acute Respiratory Distress Syndrome (ARDS) is a severe complication of acute lung injury (ALI) characterized by acute hypoxemic respiratory failure and diffuse alveolar damage, with a high mortality rate and a current lack of treatments beyond supportive care. Its complex pathophysiology involves immune cell activation, pro-inflammatory cytokine release, and disruption of the alveolar–capillary barrier, leading to pulmonary edema and fibrosis. This review explores the potential of small interfering RNA (siRNA) therapy as a novel pathogenetic treatment for ARDS. The mechanism of RNA interference is described, highlighting its high specificity for silencing target genes. The paper then evaluates various animal models used in ARDS preclinical research, noting the advantages of large animals (pigs) for their physiological similarity to humans and the suitability of rodents for studying long-term fibrotic stages. Finally, the review summarizes promising in vivo studies where siRNA-mediated knockdown of several genes (e.g., TIMP1, BTK, LCN2, HDAC7, CCL2, NOX4, TNFα and TLR4) significantly reduced inflammation, improved lung histology, and increased survival. The collective evidence underscores siRNA’s considerable potential for developing targeted therapies against ARDS, moving beyond symptomatic care to address the root molecular mechanisms of the disease. Full article

Cerebrovascular diseases are a leading cause of global mortality, underscoring the need for objective and quantitative 3D visualization of cerebral vasculature from dynamic imaging modalities. Conventional analysis is often labor-intensive, subjective, and prone to errors due to image noise and subtraction artifacts. This study tackles the challenge of achieving fast and accurate volumetric reconstruction from angiography sequences. We propose a multi-stage pipeline that begins with image restoration to enhance input quality, followed by neural segmentation to extract vascular structures. Camera poses and sparse geometry are estimated through Structure-from-Motion, and these reconstructions are refined by leveraging the segmentation maps to isolate vessel-specific features. The resulting data are then used to initialize and optimize a 3D Gaussian Splatting model, enabling anatomically precise representation of cerebral vasculature. The integration of deep neural segmentation priors with explicit geometric initialization yields highly detailed 3D reconstructions of cerebral angiography. The resulting models leverage the computational efficiency of 3D Gaussian Splatting, achieving near-real-time rendering performance competitive with state-of-the-art reconstruction methods. The segmentation of brain vessels using nnU-Net and our trained model achieved an accuracy of 84.21%, highlighting the improvement in the performance of the proposed approach. Overall, our pipeline significantly improves both the efficiency and accuracy of volumetric cerebral vasculature reconstruction, providing a robust foundation for quantitative clinical analysis and enhanced guidance during endovascular procedures. Full article

Accurate plant leaf image segmentation plays a crucial role in species recognition, phenotypic analysis, and disease detection. However, most segmentation models perform poorly in complex field environments due to challenges such as overlapping leaves and uneven sunlight. This research proposes an Edge-Aware High-Frequency Preservation Network (EHPNet) for leaf segmentation in complex field environments. Specifically, a High-Frequency Edge Fusion Module (HEFM) is introduced into the skip connections to preserve high-frequency edge information during feature extraction and enhance boundary localization. In addition, a Structural Recalibration Attention Module (SRAM) is incorporated into the decoder to refine edge structural features across multiple scales and retain spatial continuity, which leads to more accurate reconstruction of leaf boundaries. Experimental results on a composite dataset constructed from Pl@ntLeaves and ATLDSD show that EHPNet achieves 98.25%, 99.25%, 99.03%, 98.51%, and 98.77% in mean Intersection over Union (mIoU), accuracy, precision, recall, and F1 score, respectively. Compared with state-of-the-art methods, EHPNet achieves superior overall performance, which demonstrates its effectiveness for leaf segmentation in complex field environments. Full article

Background: Kidney dysfunction is common in intracerebral hemorrhage (ICH), but it is unclear whether reduced estimated glomerular filtration rate (eGFR) on admission is an independent driver of short-term outcomes or a marker of overall vulnerability. Methods: In this single-center retrospective study, we analyzed the data of consecutive patients with spontaneous ICH. Results: Among 276 patients, 92 (33.3%) presented with eGFR < 60 mL/min/1.73 m² on admission. Only 17/92 (18.5%) had documented pre-existing chronic kidney disease (CKD). Acute kidney injury (AKI) occurred more often in patients with eGFR < 60 mL/min/1.73 m² than in those with eGFR ≥ 60 mL/min/1.73 m² (25.0% vs. 10.3%). In survival models, eGFR ≥ 60 mL/min/1.73 m², predicted higher 90-day survival in the baseline model (OR 3.031, p = 0.013) but was attenuated after adjustment for age and premorbid modified Rankin Scale (mRS) and was no longer independent after additional adjustment for laboratory markers. Across all models, the National Institutes of Health Stroke Scale (NIHSS) score, hematoma volume, and history of coronary artery disease remained robust predictors. Higher leukocyte count predicted lower survival, whereas higher hemoglobin predicted higher survival. Among survivors, favorable functional outcome was independently associated with lower NIHSS, younger age, lower premorbid mRS, and absence of documented CKD. Admission eGFR category was not independently associated. Conclusions: Reduced admission eGFR primarily reflects baseline frailty and systemic derangement rather than an independent determinant of short-term survival after full adjustment, whereas documented CKD is more informative for disability among survivors. AKI occurs more frequently in patients presenting with reduced eGFR, supporting close renal monitoring in acute ICH. Full article

Monkeypox is a viral disease belonging to the smallpox family. Although it has milder symptoms than smallpox in humans, it has become a global threat in recent years, especially in African countries. Initially, incidental immunity against monkeypox was provided by smallpox vaccines. However, the eradication of smallpox over time and thus the lack of vaccination has led to the widespread and clinical importance of monkeypox. Although mathematical epidemiology research on the disease is complementary to clinical studies, it has attracted attention in the last few years. The present study aims to discuss the indispensable effects of three control strategies such as vaccination, treatment, and quarantine to prevent the monkeypox epidemic modeled via the Atangana–Baleanu operator. The main purpose is to determine optimal control measures planned to reduce the rates of exposed and infected individuals at the minimum costs. For the controlled model, the existence-uniqueness of the solutions, stability, and sensitivity analysis, and numerical optimal solutions are exhibited. The optimal system is numerically solved using the Adams-type predictor–corrector method. In the numerical simulations, the efficacy of the vaccination, treatment, and quarantine controls is evaluated in separate analyzes as single-, double-, and triple-control strategies. The results demonstrate that the most effective strategy for achieving the aimed outcome is the simultaneous application of vaccination, treatment, and quarantine controls. Full article

SHapley Additive exPlanations (SHAP) analysis has been applied in disease diagnosis and treatment effect evaluation. However, its application in the prediction and diagnosis of dairy cow diseases remains limited. We investigated whether the variance and autocorrelation of deviations in daily activity, rumination time, and milk electrical conductivity, along with daily milk yield, could be used to predict clinical mastitis in dairy cows using popular machine learning (ML) algorithms and identifying key predictive features using SHAP analysis. Quantile regression (QR) with second- or third-order polynomial models with the median or upper quantiles was used to process raw data from mastitic and healthy cows. Nine variables from the 14-day period preceding mastitis onset were identified as significantly associated with mastitis through logistic regression. These variables were used to train and validate prediction models using eleven classical ML algorithms. Among them, the partial least squares model demonstrated superior performance, achieving an AUC of 0.789, sensitivity of 0.500, specificity of 0.947, accuracy of 0.793, precision of 0.833, and F1-score of 0.625. SHAP analysis results revealed positive contributions of three features to mastitis prediction, whereas two features had negative contributions. These findings provide a theoretical basis for developing clinical decision-support tools in commercial farming settings. Full article

The COVID-19 pandemic has highlighted the importance of rapid clinical decision-making to facilitate the efficient usage of healthcare resources. Over the past decade, machine learning (ML) has caused a tectonic shift in healthcare, empowering data-driven prediction and decision-making. Recent research demonstrates how ML was used to respond to the COVID-19 pandemic. This paper puts forth new computer-aided COVID-19 disease screening techniques using six classes of ML algorithms (including penalized logistic regression, random forest, artificial neural networks, and support vector machines) and evaluates their performance when applied to a real-world clinical dataset containing patients’ demographic information and vital indices (such as sex, ethnicity, age, pulse, pulse oximetry, respirations, temperature, BP systolic, BP diastolic, and BMI), as well as ICD-10 codes of existing comorbidities, as attributes to predict the risk of having COVID-19 for given patient(s). Variable importance metrics computed using a random forest model were used to reduce the number of important predictors to thirteen. Using prediction accuracy, sensitivity, specificity, and AUC as performance metrics, the performance of various ML methods was assessed, and the best model was selected. Our proposed model can be used in clinical settings as a rapid and accessible COVID-19 screening technique. Full article

Background: New-onset postoperative atrial fibrillation (NOAF) is the most prevalent arrythmia after cardiac surgery with a significant clinical and economic impact. Therefore, simple and practical biomarkers for NOAF prediction remain a clinical priority. Increasing evidence indicates that malnutrition is linked to postoperative complications, including the onset of atrial fibrillation. The Prognostic Nutritional Index (PNI), which reflects the immunonutritional and inflammatory status through serum albumin concentration and lymphocyte count, has emerged as a reliable prognostic indicator in cardiovascular disease. The present study aimed to investigate the association between PNI and the development of NOAF in patients undergoing surgical aortic valve replacement (SAVR). Methods: A total of 241 consecutive patients who underwent AVR for severe aortic stenosis or regurgitation were enrolled in this study. The population was stratified into two groups according to the development of NOAF (NOAF group) or the lack thereof (no NOAF group). Results: In both univariate and multivariate logistic regression analyses adjusted for several established NOAF determinants, age and PNI, both as continuous variables, were independently associated with NOAF in both univariate (OR = 1.03; CI 95% = 1.01–1.06, p = 0.009, and OR = 0.9; CI 95% = 0.8–0.9, p = 0.01, respectively) and multivariate models (OR = 1.02; CI 95% = 1.01–1.06, p = 0.05, and OR = 0.9; CI 95% = 0.8–0.9, p = 0.03, respectively). When PNI was analyzed by tertiles, patients in the lowest tertile (PNI < 41.5) showed a significantly higher risk of developing NOAF at both univariate (OR = 1.9; CI 95% = 1.2–2.8, p = 0.004) and multivariate analysis (OR = 1.6; CI 95% = 1–2.6, p = 0.03), whereas age lost statistical significance (OR = 1.0; 95% CI = 0.9–1.05; p = 0.06). Furthermore, when the study population was divided into two groups based on the median age (70 years), PNI values differed significantly between NOAF and no NOAF patients only in patients under 70 years (p = 0.01). In this younger subgroup, PNI remained an independent predictor of NOAF, both when considered as a continuous variable (OR = 0.86; CI 95% = 0.74–0.98, p = 0.02), and nominal variable (PNI < 41.5, OR = 0.88; CI 95% = 0.80–0.97, p = 0.01). Conclusions: Overall, these findings identify PNI as an independent predictor of NOAF following SAVR, particularly in patients younger than 70 years. This study underlines the potential clinical value of preoperative nutritional assessment for risk stratification. Incorporating nutritional parameters such as PNI into current predictive models may enhance the accuracy of prognostic evaluation and support targeted perioperative management strategies. Full article

Accurate medical image segmentation plays a crucial role in clinical diagnosis by precisely delineating diseased tissues and organs from various medical imaging modalities. However, existing segmentation methods often fail to effectively capture low-level structural details and exhibit inconsistencies in feature connection, which may compromise diagnostic reliability. To address these limitations, this study proposes a novel Multilayer Perceptron–Transformer encoding architecture that integrates the Shift Multilayer Perceptron and Transformer mechanisms. Specifically, a SENet-based Atrous Spatial Pyramid Pooling module is designed to extract multi-scale contextual representations, while the Shift MLP refines underlying spatial features. Moreover, a channel–feature aggregation attention module is introduced to strengthen information flow between the encoder and decoder layers. Experimental results on the Automatic Cardiac Diagnostic Challenge dataset show an average Dice Similarity Coefficient (DSC) of 87.01% (83.32% for the right ventricle, 90.90% for the left ventricle, and 86.83% for the myocardium). On the Synapse multi-organ segmentation dataset, the proposed model achieves an average DSC of 79.35% and a 95% Haus Dorff Distance of 20.07 mm. These results demonstrate that MPT effectively captures both local and global anatomical structures, providing reliable support for clinical diagnosis. Full article

Neuroinflammation is a hallmark of both acute and chronic neurodegenerative diseases and is driven, in part, by activated glial cells, including microglia. A key regulator of this inflammatory response is the NLRP3 inflammasome, an immune sensor that can be triggered by diverse, unrelated stimuli such as pathogen-associated molecular patterns, cellular stress, and mitochondrial dysfunction. Despite progress in targeting NLRP3-mediated immune activation, many drug candidates fail, potentially due to the limited availability of physiologically relevant disease models. The SIM-A9 murine microglial cell line, established in 2014, has emerged as a widely used model for studying neuroinflammation; however, its proteome has not yet been systemically characterized. In this study, we investigated the proteomic landscape of SIM-A9 microglia treated with classical pro-inflammatory stimuli, including lipopolysaccharide (LPS) and extracellular ATP and nigericin (NG), to induce NLRP3 inflammasome activation. Using complementary proteomic approaches, we quantified 4903 proteins and observed significant enrichment of proteins associated with immune and nervous system processes. Differentially expressed proteins were consistent with an activated microglial phenotype, including the upregulation of proteins involved in NLRP3 inflammasome signaling. To our knowledge, this is the first comprehensive proteomic analysis of SIM-A9 microglia. These findings provide a foundational resource that may enhance the interpretation and design of future studies using SIM-A9 cells as a model of neuroinflammation. Full article