Search Results (168)

Emergency medical services confront significant challenges in delivering timely patient assessments within geographically isolated or disaster-impacted regions. While drones (unmanned aircraft systems, UAS) show transformative potential in healthcare, standardized protocols for drone-assisted patient evaluations remain underdeveloped. This study introduces the ABCD-IN-BARS protocol, a 9-step telemedicine checklist integrating patient-assisted maneuvers and drone technology to systematize remote emergency assessments. A wait-list randomized controlled trial with 68 first-aid-trained volunteers evaluated the protocol’s feasibility. Participants underwent web-based modules and in-person simulations and were randomized into immediate training or waitlist control groups. The ABCD-IN-BARS protocol was developed via a content validity approach, incorporating expert-rated items from the telemedicine literature. Outcomes included time-to-assessment, provider confidence (Modified Cooper–Harper Scale), measured at baseline, post-training, and 3-month follow-up. Ethical approval and informed consent were obtained. Most of the participants can complete the assessment with a cue card within 4 min. A mixed-design repeated measures ANOVA assessed the effects of Time (baseline, post-test, 3-month follow-up within subject) on assessment durations. Assessment times improved significantly over three time points (p = 0.008), improving with standardized protocols, while patterns were similar across groups (p = 0.101), reflecting skill retention at 3 months and not affected by injury or not. Protocol adherence in simulated injury identification increased from 63.3% pre-training to 100% post-training. Provider confidence remained high (MCH scores: 2.4–2.7/10), and Technology Acceptance Model (TAM) ratings emphasized strong Perceived Usefulness (PU2: M = 4.48) despite moderate ease-of-use challenges (EU2: M = 4.03). Qualitative feedback highlighted workflow benefits but noted challenges in drone maneuvering. The ABCD-IN-BARS protocol effectively standardizes drone-assisted emergency assessments, demonstrating retained proficiency and high usability. While sensory limitations persist, its modular design and alignment with ABCDE principles offer a scalable solution for prehospital care in underserved regions. Further multicenter validation is needed to generalize findings. Full article

Credit card fraud detection remains a major challenge due to severe class imbalance and the constantly evolving nature of fraudulent behaviors. To address these challenges, this paper proposes a hybrid framework that integrates a Variational Autoencoder (VAE) for probabilistic anomaly detection, a Graph Attention Network (GAT) for capturing inter-transaction relationships, and a stacking ensemble with XGBoost for robust prediction. The joint use of VAE anomaly scores and GAT-derived node embeddings enables the model to capture both feature-level irregularities and relational fraud patterns. Experiments on the European Credit Card and IEEE-CIS Fraud Detection datasets show that the proposed approach outperforms baseline models by up to 15% in F1-score, achieving values above 0.980 with AUCs reaching 0.995. These results demonstrate the effectiveness of combining unsupervised anomaly detection with graph-based learning within an ensemble framework for highly imbalanced fraud detection problems. Full article

Providing age-friendly metro service substantially enhances the elderly’s mobility and well-being. Despite recent progress in user profiling and mobility prediction, the prediction of the elderly’s metro travel patterns remains limited. To fill this gap, this study proposes a framework integrating user profiling and knowledge graph embedding to predict the elderly’s activity types at metro trip destinations, utilizing 180,143 smart card records and 885,072 points of interest (POI) records from Chongqing, China in 2019. First, an elderly metro travel profile (EMTP) tag system is developed to capture the elderly’s spatiotemporal metro travel behaviors and preferences. Subsequently, an elderly metro travel knowledge graph (EMTKG) is constructed to support semantic reasoning, transforming the activity types prediction problem into a knowledge graph completion problem. To solve the completion problem, the Temporal and Non-Temporal ComplEx (TNTComplEx) model is introduced to embed entities and relations into a complex vector space and distinguish between time-sensitive and time-insensitive behavioral patterns. Fact plausibility within the graph is evaluated by a scoring function. Numerical experiments validate that the proposed model outperforms the best-performing baselines by 13.37% higher Accuracy@1 and 52.40% faster training time per epoch, and ablation studies further confirm component effectiveness. This study provides an enlightening and scalable approach for enhancing age-friendly metro system service. Full article

Periodontitis is a common inflammatory disease affecting the supporting structures of teeth. Epigallocatechin-3-gallate (EGCG), a polyphenol found in green tea, is known for its therapeutic properties in various diseases, including periodontitis. This study aims to identify the gene targets of EGCG and investigate its potential in modulating molecular pathways associated with periodontitis. The potential gene targets of EGCG were obtained from the traditional Chinese medicine systems pharmacology database and analysis platform (TCMSP) and SwissTargetPrediction databases, while genes associated with periodontitis were sourced from GeneCards and Gene Expression Omnibus (GEO) datasets. By overlapping the two datasets, ten common target genes were identified. To explore their functional relevance, enrichment analyses such as Gene Ontology (GO) and REACTOME pathway mapping were conducted. Protein–protein interaction (PPI) networks were then generated, and further analyses involving molecular docking and molecular dynamics (MD) simulations were carried out to evaluate the binding affinity and structural stability of EGCG with the selected target proteins. Ten common genes (MMP2, MMP14, BCL2, STAT1, HIF1A, MMP9, MMP13, VEGFA, ESR1, and PPARG) were identified. PPI network and GO and pathway analyses identified the promising hub genes as ESR1, MMP2, MMP9, MMP13, and STAT1 and which highlighted roles in tissue development, extracellular matrix remodeling, and signaling pathways such as interleukin and matrix metalloproteinase activities. Molecular docking and MD simulations revealed strong binding interactions between EGCG and key proteins (ESR1, MMP2, MMP9, MMP13, and STAT1), with favorable binding energies and stable complexes. Among these, ESR1 and MMP13 exhibited the most favorable docking scores and stability in molecular dynamics simulations and MM–PBSA calculations. This study provides valuable insights into the molecular mechanisms of EGCG in periodontitis treatment. The findings suggest that ESR1 and MMP13 are the most promising targets for EGCG, supported by strong binding interactions and stable conformations in simulations. These results offer a foundation for further experimental studies and potential therapeutic applications of EGCG in managing periodontitis. Full article

Background: Ischemic stroke (IS) is a significant cause of global mortality and disability. Yiqi Huoxue Jieyu granules (YHJGs) show therapeutic potential for IS, but their mechanisms remain unclear. This study investigated YHJGs’ effects through network pharmacology, molecular docking, and experimental validation. Methods: Active YHJG components and IS targets were identified from TCMSP, GeneCards, and DisGeNET databases. Network analysis and molecular docking (AutoDock Vina) were performed. In vivo studies used 72 male Sprague-Dawley rats (MCAO model) divided into sham, model, nimodipine (10.8 mg/kg), and three YHJG dose groups (0.72, 1.44, 2.88 g/kg). Assessments included neurological scores, TTC staining, histopathology, and molecular analyses (qPCR/Western blot). Results: Network analysis identified 256 shared targets between YHJG and IS, with PI3K-AKT and MAPK as key pathways. Molecular docking showed strong binding between YHJG compounds (e.g., quercetin) and core targets (AKT1, ERK1/2). YHJG treatment significantly improved neurological function (p < 0.01), reduced infarct volume (p < 0.01), and attenuated neuronal damage. The expression of IL-1β, TNF-α, IL-6, AKT1, and pERK1/2/ERK1/2 significantly increased in the MCAO group (p < 0.01), while YHJG treatment significantly reduced their expression (p < 0.01). PPAR-γ expression significantly increased in the YHJG-H group (p < 0.01). Conclusions: The expression of IL-1β, TNF-α, IL-6, AKT1, and pERK1/2/ERK1/2 significantly increased in the MCAO group, while YHJG treatment significantly reduced their expression. PPAR-γ expression significantly increased in the YHJG-H group. YHJGs could treat IS through diverse ingredients, targets, and pathways by inhibiting inflammatory indices and AKT1 expression, and reducing ERK1/2 phosphorylation. Full article

Cognitive flexibility—the ability to adapt cognitive strategies and behavioral responses in changing environments—is a key component of executive function, supporting rule updating and conflict resolution. Individuals with substance addiction often exhibit behavioral rigidity and reduced adaptability, reflecting impairments in this domain. This study examined cognitive flexibility in individuals with methamphetamine dependence through three behavioral tasks—intra-dimensional task switching, extra-dimensional task switching, and the Wisconsin Card Sorting Test (WCST)—in combination with a subjective self-report measure. Results showed that, compared to healthy controls, methamphetamine-dependent individuals demonstrated elevated reaction time switch costs in Intra-dimensional Task Switching and increased accuracy switch costs in Extra-dimensional Task Switching, as well as more perseverative and non-perseverative errors in the WCST. These findings suggested not only reduced performances in explicitly cued rule updating and strategic shifting but also deficits in feedback-driven learning and inflexibility in cognitive set shifting on methamphetamine-dependent individuals. Moreover, their self-reported cognitive flexibility scores were aligned with their objective performance, significantly lower than healthy controls. In summary, these findings revealed consistent cognitive flexibility impairments at both behavioral and subjective levels in individuals with methamphetamine dependence, indicating a core executive dysfunction that may undermine adaptive functioning in real-life contexts. The study offers critical insights into the cognitive mechanisms underlying addiction and provides a theoretical foundation for targeted cognitive interventions. Full article

Background: Cardiomyocyte death is a key factor in myocardial ischemia–reperfusion injury (MI/RI), and the expression patterns and molecular mechanisms of pyroptosis-related genes (PRGs) in ischemia–reperfusion injury are poorly understood. Methods: The mouse MI/RI injury-related datasets GSE61592 and GSE160516 were obtained from the Gene Expression Omnibus database, and differential expression analysis was performed on each to identify differentially expressed genes (DEGs). The DEGs were intersected with the PRGs obtained from GeneCards to identify differentially expressed PRGs in MI/RI. Enrichment analysis identified key pathways, while PPI network analysis revealed hub genes. The expression patterns and immune cell infiltration of hub genes were also investigated. The molecular docking prediction of key genes was performed using MOE software in conjunction with the ZINC small molecular compounds database. Key gene expression was validated in an external dataset (GSE4105), a mouse MI/RI model, and an HL-1 cell hypoxia/reoxygenation model via RT-qPCR. Results: A total of 29 differentially expressed PRGs were identified, which are primarily associated with pathways such as “immune system process”, “response to stress”, “identical protein binding”, and “extracellular region”. Seven key genes (Fkbp10, Apoe, Col1a2, Ppic, Tlr2, Fstl1, Serpinh1) were screened, all strongly correlated with immune infiltration. Seven FDA-approved small molecule compounds exhibiting the highest docking potential with each key gene were selected based on a comprehensive evaluation of S-scores and hydrogen bond binding energies. Apoe, Tlr2, and Serpinh1 were successfully validated across external datasets, the mouse MI/RI model, and the cardiomyocyte H/R model. Conclusions: Apoe, Tlr2, and Serpinh1 may be key genes involved in MI/RI-related pyroptosis. Targeting these genes may provide new insights into the treatment of MI/RI. Full article

Credit card fraud remains a major cause of financial loss around the world. Traditional fraud detection methods that rely on supervised learning often struggle because fraudulent transactions are rare compared to legitimate ones, leading to imbalanced datasets. Additionally, the models must be retrained frequently, as fraud patterns change over time and require new labeled data for retraining. To address these challenges, this paper proposes an ensemble unsupervised learning approach for credit card fraud detection that combines Autoencoders (AEs), Self-Organizing Maps (SOMs), and Restricted Boltzmann Machines (RBMs), integrated with an Adaptive Reconstruction Threshold (ART) mechanism. The ART dynamically adjusts anomaly detection thresholds by leveraging the clustering properties of SOMs, effectively overcoming the limitations of static threshold approaches in machine learning and deep learning models. The proposed models, AE-ASOMs (Autoencoder—Adaptive Self-Organizing Maps) and RBM-ASOMs (Restricted Boltzmann Machines—Adaptive Self-Organizing Maps), were evaluated on the Kaggle Credit Card Fraud Detection and IEEE-CIS datasets. Our AE-ASOM model achieved an accuracy of 0.980 and an F1-score of 0.967, while the RBM-ASOM model achieved an accuracy of 0.975 and an F1-score of 0.955. Compared to models such as One-Class SVM and Isolation Forest, our approach demonstrates higher detection accuracy and significantly reduces false positive rates. In addition to its performance, the model offers considerable computational efficiency with a training time of 200.52 s and memory usage of 3.02 megabytes. Full article

Student behavior analysis plays a critical role in enhancing educational quality and enabling personalized learning. While previous studies have utilized machine learning models to analyze campus card consumption data, few have integrated multi-source behavioral data with large language models (LLMs) to provide deeper insights. This study proposes an intelligent educational system that examines the relationship between student consumption behavior and academic performance. The system is built upon a dataset collected from students of three majors at Xinjiang Normal University, containing exam scores and campus card transaction records. We designed an artificial intelligence (AI) agent that incorporates LLMs, SageGNN-based graph embeddings, and time-series regularity analysis to generate individualized behavior reports. Experimental evaluations demonstrate that the system effectively captures both temporal consumption patterns and academic fluctuations, offering interpretable and accurate outputs. Compared to baseline LLMs, our model achieves lower perplexity while maintaining high report consistency. The system supports early identification of potential learning risks and enables data-driven decision-making for educational interventions. Furthermore, the constructed multi-source dataset serves as a valuable resource for advancing research in educational data mining, behavioral analytics, and intelligent tutoring systems. Full article

SCALENEo (Smart ClinicAL rEasoning iN physiothErapy) is an innovative online serious game designed to improve clinical reasoning in musculoskeletal physiotherapy education. Adapted from the “Happy Families” card game, it provides an interactive, structured approach to developing students/learners’ ability to categorize clinical information into families of hypotheses. This digital platform supports both self-directed and collaborative learning, eliminating the need for continuous instructor supervision while ensuring meaningful engagement. SCALENEo features a unique feedback and scoring system that not only assesses students/learners’ decision-making processes but also promotes cautious and reflective reasoning over random guessing. By aligning with evidence-based pedagogical strategies, such as serious games and formative assessment, SCALENEo offers educators a powerful tool to reinforce critical thinking, improve student/learner engagement, and facilitate deeper learning in clinical reasoning education. Full article

This study examines whether and how community schools’ integrated student support services (academic, socioemotional, health, and family support) contributed to improving whole-child/youth development and reducing systemic inequalities of students’ learning/wellness outcomes across New York State under the Every Student Succeeds Act (ESSA). Applying a quasi-experimental method with propensity score matching to the state’s 2018–2023 school survey and report card databases, it provides new evidence on the efficacy of community school programs on average and by subgroups (race/ethnicity, poverty, disability, English language learner, and housing status). The results of matched comparisons between community schools and non-community schools are mixed, after considering their differences in terms of student demographics and baseline conditions. Overall, community schools showed policy implementation fidelity with more state funding, policy-aligned practices, and school-based health centers/clinics. However, community schools had no discernable impacts on academic achievement and chronic absenteeism overall, except that the operation of school-based health centers was associated with a reduction in absenteeism. In contrast, community schools had more positive impacts on high school graduation rates, particularly among disadvantaged minority students; the impacts are attributable to policy-aligned practices, set-aside funding, and school-based health center dental programs. Educational policy and research implications are discussed. Full article

Background/Objective: Executive functions (EFs) are essential in the daily management of arthritis, as they influence treatment adherence, decision-making, and the ability to cope with disease-related challenges. The objective of this study was to compare EFs alongside functional status and quality of life in patients with rheumatoid arthritis (RA) and psoriatic arthritis (PsA) and examine their associations with disease activity and clinical variables. Methods: In this cross-sectional study, 140 patients (70 RA, 70 PsA) were assessed using the Stroop-TBAG, Wisconsin Card Sorting Test (WCST), and Adult Executive Functioning Inventory (ADEXI). Functional status and quality of life were measured with the Health Assessment Questionnaire (HAQ) and WHOQOL-BREF, respectively. Correlations with disease activity (DAS28-CRP), age, and disease duration were examined. Results: RA patients had significantly higher disease activity and longer disease duration. They showed poorer performance on the Stroop Test (color–word time: 61.6 ± 14.8 vs. 52.4 ± 10.9 s, p < 0.001; errors: 3.2 ± 2.1 vs. 2.1 ± 1.5, p = 0.001), more WCST perseverative errors (p = 0.002), and higher ADEXI inhibition scores (13.9 ± 2.5 vs. 12.9 ± 3.0, p = 0.013). DAS28-CRP was correlated with EF impairments, disability, and poorer quality of life in RA (p < 0.05). In PsA, EFs remained relatively stable, although higher disease activity was associated with worse HAQ scores (p = 0.001). Treatment type was not linked to EF, but patients on combination therapy reported lower physical (p = 0.009) and psychological (p = 0.014) quality of life, along with higher HAQ scores (p = 0.016). Conclusions: This study revealed that patients with RA exhibit more pronounced executive dysfunction, along with lower ADL skills and quality of life compared to those with PsA. These findings highlight the need for multidimensional assessment strategies in inflammatory arthritis, especially in RA, where cognitive and functional outcomes are closely tied to clinical burden. Full article

The Every Student Succeeds Act requires that U.S. states provide a public evaluation of the performance of each public school while providing broad discretion in how states devise performance frameworks. One common method consists of states assigning each school an A–F letter grade based on English and math proficiency rates and other measures of academic performance. Proponents of the summary letter-grade system cite its simplicity as a virtue, while detractors contend that the system is simplistic to a fault. To bring greater clarity to these ongoing debates, we solicited opinions from parents regarding state letter-grade systems. We conducted semi-structured focus groups with parents in Arizona, North Carolina, and Texas (three focus groups per state). These conversations revealed that most parents were not aware that the state grades schools. Once the performance framework was explained, most parents expressed a belief that it is overly simplistic and insufficiently deferential to what they perceive as the subjective nature of school quality. Parents also revealed substantial tension between their conception of school quality and the way it is operationalized in the report card, with the latter ascribing much greater importance to state test scores. Full article

Background and Objectives: Acute kidney injury (AKI) is common in intensive-care unit (ICU) patients and is associated with increased mortality. Elderly patients tend to have more comorbid chronic diseases and are more prone to AKI than younger populations, resulting in higher rates of hospitalization and a higher incidence of AKI. Our aim in this study was to investigate the prognostic utility of BUN/albumin ratio (BAR) in predicting mortality in elderly critically ill patients with AKI. Materials and Methods: This study was conducted retrospectively on 154 elderly patients with AKI who were admitted to the ICU between October 2023 and September 2024.Data on the following demographic, clinical, and laboratory parameters were retrospectively collected from medical cards and electronic records. Results: In the non-survivor group, among comorbidities, lung disease was higher (p < 0.05), GCS was lower, and APACHE II was higher among clinical scores (p < 0.001). In the non-survivor group, diuretic use (p = 0.03), oliguria, RRT, vasopressor requirement, sepsis, and MV rates (p < 0.001),as well as BUN, phosphate, LDH, Crp, APTT, INR, and BAR rates, were higher (all p < 0.05) and albumin was lower (p = 0.01). Cut-off values of BUN, albumin, and BAR variables according to mortality status were determined by an ROC curve analysis, as follows:48.4 for BUN (p = 0.013), 31.5 for albumin (p = 0.001), and 1.507 for BAR (p = 0.001).According to the results of the ROC analysis performed to predict in-hospital mortality, the BAR level reached an AUC value of 0.655. A BAR value above 1.507 increases mortality by 3.944 times (p = 0.023). Conclusions: BAR is a simple and accessible biomarker that may serve as a predictor of in-hospital mortality in elderly patients with AKI. Its use may aid early risk stratification and decisionmaking in the ICU. Full article

Financial fraud detection is a critical application area within the broader domains of cybersecurity and intelligent financial analytics. With the growing volume and complexity of digital transactions, the traditional rule-based and shallow learning models often fall short in detecting sophisticated fraud patterns. This study addresses the challenge of accurately identifying fraudulent financial activities, especially in highly imbalanced datasets where fraud instances are rare and often masked by legitimate behavior. The existing models also lack interpretability, limiting their utility in regulated financial environments. Experiments were conducted on three benchmark datasets: IEEE-CIS Fraud Detection, European Credit Card Transactions, and PaySim Mobile Money Simulation, each representing diverse transaction behaviors and data distributions. The proposed methodology integrates a transformer-based encoder, multi-teacher knowledge distillation, and a symbolic belief–desire–intention (BDI) reasoning layer to combine deep feature extraction with interpretable decision making. The novelty of this work lies in the incorporation of cognitive symbolic reasoning into a high-performance learning architecture for fraud detection. The performance was assessed using key metrics, including the F1-score, AUC, precision, recall, inference time, and model size. Results show that the proposed transformer–BDI model outperformed traditional and state-of-the-art baselines across all datasets, achieving improved fraud detection accuracy and interpretability while remaining computationally efficient for real-time deployment. Full article