Search Results (1,966)

Cardiovascular disease (CVD), diabetes, and obesity pose major public health challenges in the United Arab Emirates (UAE), contributing substantially to morbidity, mortality, and healthcare expenditure. Despite progress in expanding access and service delivery, Health Quality Management (HQM) practices remain constrained. This study represents one of the first comprehensive, co-productive efforts to evaluate and strengthen HQM for CVD, diabetes and obesity in the UAE. Using a sequential, multi-phase design, it integrates evidence synthesis with the active engagement of interest groups to bridge gaps between research, policy, and practice. Phase 1 involves a scoping review to establish an evidence base on existing HQM practices and system-level challenges. Phase 2 conducts mapping and interviews with health professionals, policymakers, and patients to capture contextual insights. Phase 3 synthesizes findings to identify critical gaps, opportunities, and emerging research questions that can guide future inquiry. Phase 4 convenes consultative and consensus-building workshops to co-produce actionable recommendations and facilitate knowledge translation and exchange among health authorities, academic institutions, and other interest groups. Guided by the Institute of Medicine’s quality domains, the Donabedian model, and WHO quality indicators, this study situates HQM within the UAE’s ongoing shift toward value-based healthcare. The expected outcomes include the identification of key barriers to and facilitators of effective HQM, the formulation of context-specific recommendations to strengthen performance and coordination, production of knowledge translation outputs and the generation of new research priorities, thus contributing to achieving UAE Vision 2031 and global NCD targets. Full article

Background: In high-dimensional, small-sample omics studies such as metabolomics, feature selection not only determines the discriminative performance of classification models but also directly affects the reproducibility and translational value of candidate biomarkers. However, most existing methods primarily optimize classification accuracy and treat stability as a post hoc diagnostic, leading to considerable fluctuations in selected feature sets under different data splits or mild perturbations. Methods: To address this issue, this study proposes FRL-TSFS, a feature selection framework synergistically driven by filter-based Robust Rank Aggregation and L1-sparse modeling. Five complementary filter methods—variance thresholding, chi-square test, mutual information, ANOVA F test, and ReliefF—are first applied in parallel to score features, and Robust Rank Aggregation (RRA) is then used to obtain a consensus feature ranking that is less sensitive to the bias of any single scoring criterion. An L1-regularized logistic regression model is subsequently constructed on the candidate feature subset defined by the RRA ranking to achieve task-coupled sparse selection, thereby linking feature selection stability, feature compression, and classification performance. Results: FRL-TSFS was evaluated on six representative metabolomics and gene expression datasets under a mildly perturbed scenario induced by 10-fold cross-validation, and its performance was compared with multiple baselines using the Extended Kuncheva Index (EKI), Accuracy, and F1-score. The results show that RRA substantially improves ranking stability compared with conventional aggregation strategies without degrading classification performance, while the full FRL-TSFS framework consistently attains higher EKI values than the other feature selection schemes, markedly reduces the number of selected features to several tens of metabolites or genes, and maintains competitive classification performance. Conclusions: These findings indicate that FRL-TSFS can generate compact, reproducible, and interpretable biomarker panels, providing a practical analysis framework for stability-oriented feature selection and biomarker discovery in untargeted metabolomics. Full article

Background: Accurate deformity classification and fusion-level planning are essential in adolescent idiopathic scoliosis (AIS) surgery and are traditionally guided by Cobb angle measurement and the Lenke system. Multimodal large language models (LLMs) (e.g., ChatGPT-4.0; Claude 3.7 Sonnet, Gemini 2.5 Pro, DeepSeek-R1-0528 Chat) are increasingly used for image interpretation despite limited validation for radiographic decision-making. This study evaluated the agreement and reproducibility of contemporary multimodal LLMs for AIS assessment compared with expert spine surgeons. Methods: This single-center retrospective study included 125 AIS patients (94 females, 31 males; mean age 14.8 ± 1.9 years) who underwent posterior instrumentation (2020–2024). Two experienced spine surgeons independently performed Lenke classification (including lumbar and sagittal modifiers) and selected fusion levels (UIV–LIV) on standing AP, lateral, and side-bending radiographs; discrepancies were resolved by consensus to establish the reference standard. The same radiographs were analyzed by four paid multimodal LLMs using standardized zero-shot prompts. Because LLMs showed inconsistent end-vertebra selection, LLM-derived Cobb angles lacked a common anatomical reference frame and were excluded from quantitative analysis. Agreement with expert consensus and test–retest reproducibility (repeat analyses one week apart) were assessed using Cohen’s κ. Evaluation times were recorded. Results: Surgeon agreement was high for Lenke classification (92.0%, κ = 0.913) and fusion-level selection (88.8%, κ = 0.879). All LLMs demonstrated chance-level test–retest reproducibility and very low agreement with expert consensus (Lenke: 1.6–10.2%, κ = 0.001–0.036; fusion: 0.8–12.0%, κ = 0.003–0.053). Claude produced missing outputs in 17 Lenke and 29 fusion-level cases. Although LLMs completed assessments far faster than surgeons (seconds vs. ~11–12 min), speed did not translate into clinically acceptable reliability. Conclusions: Current general-purpose multimodal LLMs do not provide reliable Lenke classification or fusion-level planning in AIS. Their poor agreement with expert surgeons and marked internal inconsistency indicate that LLM-generated interpretations should not be used for surgical decision-making or patient self-assessment without task-specific validation. Full article

In disciplines such as epidemiology, economics, and public health, inference and estimation of heterogeneous treatment effects (HTE) are critical. This approach helps reveal differences in treatment effect estimates between subgroups, which supports personalized decision-making processes. While a variety of meta-learners (e.g., S-, T-, X-learners) have been proposed for estimating HTE, there is a lack of consensus on their relative strengths and weaknesses under different data conditions. To address this gap and provide actionable guidance for applied researchers, this study conducts a comprehensive simulation-based comparison of these methods. We first introduce the causal inference framework and review the underlying principles of the methods used to estimate these effects. We then simulate different data generating processes (DGPs) and compare the performance of S-, T-, X-, DR-, and R-learners with the causal forest, highlighting the potential of meta-learners for HTE estimation. Our evaluation reveals that each learner excels under distinct conditions: the S-learner yields the least bias and is most robust when the conditional average treatment effect (CATE) is approximately zero; the T-learner provides accurate estimates when the response functions differ significantly between the treatment and control groups, resulting in a complex CATE structure, and the X-learner can accurately estimate the HTE in imbalanced data.Additionally, by integrating Z-bias—a bias that may arise when adjusting the covariate only affects the treatment variable—with a specific sensitivity analysis, this study demonstrates its effectiveness in reducing the bias of causal effect estimates. Finally, through an empirical analysis of the Trends in International Mathematics and Science Study (TIMSS) 2019 data, we illustrate how to implement these insights in practice, showcasing a workflow for HTE assessment within the meta-learner framework. Full article

Tuberculosis remains one of the most prevalent infectious diseases, and the only currently available vaccine is the Mycobacterium bovis bacillus Calmette–Guèrin (BCG) vaccine. The uncontrolled passaging of the BCG strain led to genetically diverse BCG strains. Seven samples from clinical BCG-associated disease were obtained from the National Tuberculosis Reference Laboratory. Whole-genome sequencing and bioinformatics analysis were performed using tools such as fastqc, Trimmomatic, and CLC Genomics Workbench 24.0.3 to obtain consensus sequences and analyse deletions between M. bovis AF2122/97, BCG Danish, and clinical samples. Snippy was used to generate the phylogenomic tree, Prokka for annotation, and an in-house script to detect potential drug resistance. Four deletions were identified between M. bovis wildtype and M. bovis BCG. The phylogenomic tree showed that of the seven strains analysed, one was phylogenetically close to M. tuberculosis H37Rv, and another to the Danish BCG vaccine. Other samples were distantly related to each other and to reference strains. Two of the samples showed possible resistance to ethambutol. This would imply original misdiagnosis of the disease and subsequent ineffective treatment. This study emphasises the importance of genomic testing for accurate diagnosis of BCG disease and underscores the need for phylogenomic surveillance of M. bovis BCG strains circulating in South Africa. Full article

Background/Objectives: Artificial intelligence (AI) systems may enhance diagnostic accuracy in cone-beam computed tomography (CBCT) analysis. However, most validations focus on isolated tooth-level tasks rather than clinically meaningful full-mouth assessment outcomes. To evaluate the diagnostic accuracy of a commercial AI platform for detecting dental treatment features on CBCT images at both tooth and full-scan levels. Methods: In this retrospective single-center study, 147 CBCT scans (4704 tooth positions) were analyzed. Two experienced readers annotated treatment features (missing teeth, fillings, endodontic treatments, crowns, pontics, orthodontic appliances, implants), and consensus served as the reference. Anonymized datasets were processed by a cloud-based AI system (Diagnocat Inc., San Francisco, CA, USA). Diagnostic metrics—sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score—were calculated with 95% patient-clustered bootstrap confidence intervals. A “Perfect Agreement” criterion defined full-scan level success as an entirely error-free full-mouth report. Results: Tooth-level AI performance was excellent, with accuracy exceeding 99% for most categories. Sensitivity was highest for missing teeth (99.3%) and endodontic treatments (99.0%). Specificity and NPV exceeded 98.5% and 99.7%, respectively. Full-scan level Perfect Agreement was achieved in 82.3% (95% CI: 76.2–88.4%), with errors concentrated in teeth presenting multiple co-existing findings. Conclusions: The evaluated AI platform demonstrates near-perfect accuracy in detecting isolated dental features but moderate reliability in generating complete full-mouth reports. It functions best as an assistive diagnostic tool, not as an autonomous system. Full article

Accurate extrinsic calibration between radar and camera sensors is essential for reliable multi-modal perception in robotics and autonomous navigation. Traditional calibration methods often rely on artificial targets such as checkerboards or corner reflectors, which can be impractical in dynamic or large-scale environments. This study presents a fully targetless calibration framework that estimates the rigid spatial transformation between radar and camera coordinate frames by aligning their observed trajectories of a moving object. The proposed method integrates You Only Look Once version 5 (YOLOv5)-based 3D object localization for the camera stream with Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Random Sample Consensus (RANSAC) filtering for sparse and noisy radar measurements. A passive temporal synchronization technique, based on Root Mean Square Error (RMSE) minimization, corrects timestamp offsets without requiring hardware triggers. Rigid transformation parameters are computed using Kabsch and Umeyama algorithms, ensuring robust alignment even under millimeter-wave (mmWave) radar sparsity and measurement bias. The framework is experimentally validated in an indoor OptiTrack-equipped laboratory using a Skydio 2 drone as the dynamic target. Results demonstrate sub-degree rotational accuracy and decimeter-level translational error (approximately 0.12–0.27 m depending on the metric), with successful generalization to unseen motion trajectories. The findings highlight the method’s applicability for real-world autonomous systems requiring practical, markerless multi-sensor calibration. Full article

This paper evaluates multi-agent coordination strategies against single-agent retrieval-augmented generation (RAG) for open-source language models. Four coordination strategies (collaborative, sequential, competitive, hierarchical) were tested across Mistral 7B, Llama 3.1 8B, and Granite 3.2 8B using 100 domain-specific question–answer pairs (3100 total evaluations). Performance was assessed using Composite Performance Score (CPS) and Threshold-aware CPS (T-CPS), aggregating nine metrics spanning lexical, semantic, and linguistic dimensions. Under the tested conditions, all 28 multi-agent configurations showed degradation relative to single-agent baselines, ranging from −4.4% to −35.3%. Coordination overhead was identified as a primary contributing factor. Llama 3.1 8B tolerated Sequential and Hierarchical coordination with minimal degradation (−4.9% to −5.3%). Mistral 7B with shared context retrieval achieved comparable results. Granite 3.2 8B showed degradation of 14–35% across all strategies. Collaborative coordination exhibited the largest degradation across all models. Study limitations include evaluation on a single domain (agriculture), use of 7–8B parameter models, and homogeneous agent architectures. These findings suggest that single-agent RAG may be preferable for factual question-answering tasks in local deployment scenarios with computational constraints. Future research should explore larger models, heterogeneous agent teams, role-specific prompting, and advanced consensus mechanisms. Full article

This study investigates mean-square quasi-consensus for a class of linear discrete-time multi-agent systems with external disturbances, where both the system model and network uncertainties are considered. By introducing adjustable parameters, a more generalized modeling of the internal system uncertainties is achieved, and the network uncertainties among agents are described by Bernoulli variables. This study employs a method combining the parametric algebraic Riccati equation (PARE) and linear matrix inequalities, and a novel auxiliary lemma is developed based on the properties of the PARE. The results demonstrate that, under the designed control protocol, by satisfying the conditions related to the expectations of random uncertainties and network uncertainties, the multi-agent system can achieve mean-square quasi-consensus. Finally, numerical simulation examples are conducted to demonstrate the effectiveness of the results obtained in this study, and the fluctuation in the error trajectory curve is smaller than some existing results. Full article

In the financial sector, machine learning has become essential for credit risk assessment, often outperforming traditional statistical approaches, such as linear regression, discriminant analysis, or model-based expert judgment. Although machine learning technologies are increasingly being used, further research is needed to understand how they can be effectively combined and how different models interact during credit evaluation. This study proposes a technique that integrates hierarchical clustering, namely Agglomerative clustering and Balanced Iterative Reducing and Clustering using Hierarchies, along with individual supervised models and a self organizing map-based consensus model. This approach helps to better understand how different clustering algorithms influence model performance. To support this approach, we performed a detailed unsupervised component analysis using metrics such as the silhouette score and Adjusted Rand Index to assess cluster quality and its relationship with the classification results. The study was applied to multiple datasets, including a Taiwanese credit dataset. It was also extended to a multiclass classification scenario to evaluate its generalization ability. The results show that the quality metrics of the cluster correlate with the performance, highlighting the importance of combining unsupervised clustering and self organizing map consensus methods for improving credit evaluation. Full article

Several solutions are being explored to reduce methane intensity in dairy farms, but there is no consensus for commercial pastoral dairy systems in temperate zones. We evaluated the effects of essential oils (EO) supplementation on CH₄ intensity and performance in dairy cows within a commercial pasture-based system in southern Chile. Thirty multiparous cows were randomly assigned to a control group and a treated group, with a general average yield of 22.3 ± 5.37 kg/d and an average parity of 3.42 ± 1.13. The treated group received concentrate supplemented with a mixture of EOs. Enteric CH₄ emissions were measured using GreenFeed^®. Milk yield (kg/d), composition (% fat, % protein, urea, somatic cells), plasma biochemistry, and grassland proximal analysis (NIRs) were also evaluated. Results showed a significant increase in fat-corrected milk production (4.6 kg) in the treated group during the first trial period where the grassland was highly nutritious, offering 19.8% crude protein as well as a pool of long-chain fatty acids. Additionally, CH₄ intensity was significantly lower in the treated group (1.3 gCH₄/ECM) during the first phase. EO supplementation strategies represent a suitable non-invasive intervention suitable for commercial grassland-based systems in southern Chile that is strongly influenced by pasture quality. Full article

The rapid development of large artificial intelligence (AI) models—large language models (LLMs), multimodel large language models (MLLMs) and vision–language models (VLMs)—has enabled instruction-driven visual understanding, where a single foundation model can recognize and localize arbitrary objects from natural-language prompts. However, predictions from individual models remain inconsistent—LLMs hallucinate nonexistent entities, while VLMs exhibit limited recall and unstable calibration compared to purpose-trained detectors. To address these limitations, a new paradigm termed “multiple large AI model’s consensus” has emerged. In this approach, multiple heterogeneous LLMs, MLLMs or VLMs process a shared visual–textual instruction and generate independent structured outputs (bounding boxes and categories). Next, their results are merged through consensus mechanisms. This cooperative inference improves spatial accuracy and semantic correctness, making it particularly suitable for generating high-quality training datasets for fast real-time object detectors. This survey provides a comprehensive overview of the large multi-AI model’s consensus for object detection. We formalize the concept, review related literature on ensemble reasoning and multimodal perception, and categorize existing methods into four frameworks: prompt-level, reasoning-to-detection, box-level, and hybrid consensus. We further analyze fusion algorithms, evaluation metrics, and benchmark datasets, highlighting their strengths and limitations. Finally, we discuss open challenges—vocabulary alignment, uncertainty calibration, computational efficiency, and bias propagation—and identify emerging trends such as consensus-aware training, structured reasoning, and collaborative perception ecosystems. Full article

Background/Objectives: Metabolic and bariatric surgery (MBS) promotes improved redox response and weight loss and reduced cardiovascular risk. However, there is still no consensus on whether some of these results may be affected years after the surgery. This study evaluated the association between redox response and cardiovascular risk markers following MBS. Methods: Patients (n = 91) of both sexes who underwent MBS 2–7 years ago were evaluated. Antioxidant enzymatic activity (catalase, superoxide dismutase, glutathione-S-transferase, and glutathione peroxidase) and oxidative damage (malondialdehyde and carbonylated protein) were quantified. Blood pressure, glucose, insulin, triglyceride/glucose (TyG) index, LDL-C, HDL-C, non-HDL-C, triglyceride (TG), and cholesterol were analyzed. Principal component analysis (PCA) and generalized linear models were used. Results: The participants had a mean age of 39.82 ± 7.87 years, and a current body mass index of 29.53 ± 5.01 kg/m². The PCA identified two patterns: enzymatic antioxidant activity (PC1) and oxidative damage (PC2). No association was found between PC1 and cardiovascular risk markers. A positive association was observed between PC2 and diastolic blood pressure (β: 6.79, 95% confidence intervals [CI]: 1.97; 11.61), TyG index (β: 0.13, 95% CI: 0.05; 0.21), total cholesterol (β: 15.17, 95% CI: 3.61; 26.72), TG (β: 25.88, 95% CI: 8.58; 43.18; p = 0.003), and non-HDL-C (β: 10.91, 95% CI: 0.02; 21.88). Conclusions: Oxidative damage markers were positively associated with diastolic blood pressure, TyG index, TG, total cholesterol, and non-HDL-C levels after MBS. However, further studies are required to confirm and elucidate these findings. Full article

Background/Objectives: Asthma action plans (AAPs) are recommended for patients’ self-management of asthma and should be adapted to a country’s situation. This study aimed to develop expert consensus on the optimal structure, content, and action of asthma action plans for Vietnamese settings to ensure feasibility, acceptance, and implementation. Methods: A Delphi consensus was conducted over two rounds. The proposed items were evaluated by a Vietnamese panel of pulmonologists, allergists, tuberculosis/lung disease specialists, and general practitioners. Structured online questionnaires with five-point Likert scales were used. Consensus was defined as >80% agreement and <10% strong disagreement. Results: A total of 26 and 21 participants completed round 1 and round 2, respectively. The 4-zone format of AAP was preferred (42.3%) over the 3-zone (38.5%) or 2-zone (19.2%) formats. The AAP should include some key statements for asthma, symptoms for self-monitoring, an objective asthma control questionnaire, actions for changes in maintenance medication, and instructions in emergency situations. AAP zones should be classified by symptom frequency and severity. Patient actions should be tailored to their treatment regimen (MART or ICS/LABA + SABA). The APP might not include peak expiratory flow monitoring and oral corticosteroid self-administration for both the MART and ICS/LABA + SABA regimens and might not add SABA together with ICS dose escalation for the ICS/LABA + SABA regimen. Conclusions: This study established an expert consensus on fundamental AAP structural elements and actions for the Vietnamese. The failure to achieve consensus on PEF monitoring tools and OCS for the self-management of asthma exacerbation reflects concerns about medication abuse, especially in Vietnamese healthcare settings. Full article

Patients undergoing oral surgery are frequently polymedicated and preoperative prescriptions (analgesics, corticosteroids, antibiotics) can generate clinically significant drug–drug interactions (DDIs) associated with bleeding risk, serotonin toxicity, cardiovascular instability and other adverse events. This study prospectively evaluated whether large language models (LLMs) can assist in detecting clinically relevant DDIs at the point of care. Five LLMs (ChatGPT-5, DeepSeek-Chat, DeepSeek-Reasoner, Gemini-Flash, and Gemini-Pro) were compared with a panel of experienced oral surgeons in 500 standardized oral-surgery cases constructed from realistic chronic medication profiles and typical postoperative regimens. For each case, all chronic and procedure-related drugs were provided and the task was to identify DDIs and rate their severity using an ordinal Lexicomp-based scale (A–X), with D/X considered “action required”. Primary outcomes were exact agreement with surgeon consensus and ordinal concordance; secondary outcomes included sensitivity for actionable DDIs, specificity, error pattern and response latency. DeepSeek-Chat reached the highest exact agreement with surgeons (50.6%) and showed perfect specificity (100%) but low sensitivity (18%), missing 82% of actionable D/X alerts. ChatGPT-5 showed the highest sensitivity (98.0%) but lower specificity (56.7%) and generated more false-positive warnings. Median response time was 3.6 s for the fastest model versus 225 s for expert review. These findings indicate that current LLMs can deliver rapid, structured DDI screening in oral surgery but exhibit distinct safety trade-offs between missed critical interactions and alert overcalling. They should therefore be considered as decision-support tools rather than substitutes for clinical judgment and their integration should prioritize validated, supervised workflows. Full article