Dimitri Breda, Muhammad Tanveer, Jianhong Wu
et al.
Predicting the human burden of vector-borne diseases from limited surveillance data remains a major challenge, particularly in the presence of nonlinear transmission dynamics and delayed effects arising from vector ecology and human behavior. We develop a data-driven framework based on an extension of Sparse Identification of Nonlinear Dynamics (SINDy) to systems with distributed memory, enabling discovery of transmission mechanisms directly from time series data. Using severe fever with thrombocytopenia syndrome (SFTS) as a case study, we show that this approach can uncover key features of tick-borne disease dynamics using only human incidence and local temperature data, without imposing predefined assumptions on human case reporting. We further demonstrate that predictive performance is substantially enhanced when the data-driven model is coupled with mechanistic representations of tick-host transmission pathways informed by empirical studies. The framework supports systematic sensitivity analysis of memory kernels and behavioral parameters, identifying those most influential for prediction accuracy. Although the approach prioritizes predictive accuracy over mechanistic transparency, it yields sparse, interpretable integral representations suitable for epidemiological forecasting. This hybrid methodology provides a scalable strategy for forecasting vector-borne disease risk and informing public health decision-making under data limitations.
Rupsa Rani Mishra, D. Chandrasekhar Rao, Ajaya Kumar Tripathy
Manual observation and monitoring of individual cows for disease detection present significant challenges in large-scale farming operations, as the process is labor-intensive, time-consuming, and prone to reduced accuracy. The reliance on human observation often leads to delays in identifying symptoms, as the sheer number of animals can hinder timely attention to each cow. Consequently, the accuracy and precision of disease detection are significantly compromised, potentially affecting animal health and overall farm productivity. Furthermore, organizing and managing human resources for the manual observation and monitoring of cow health is a complex and economically demanding task. It necessitates the involvement of skilled personnel, thereby contributing to elevated farm maintenance costs and operational inefficiencies. Therefore, the development of an automated, low-cost, and reliable smart system is essential to address these challenges effectively. Although several studies have been conducted in this domain, very few have simultaneously considered the detection of multiple common diseases with high prediction accuracy. However, advancements in Internet of Things (IoT), Machine Learning (ML), and Cyber-Physical Systems have enabled the automation of cow health monitoring with enhanced accuracy and reduced operational costs. This study proposes an IoT-enabled Cyber-Physical System framework designed to monitor the daily activities and health status of cow. A novel ML algorithm is proposed for the diagnosis of common cow diseases using collected physiological and behavioral data. The algorithm is designed to predict multiple diseases by analyzing a comprehensive set of recorded physiological and behavioral features, enabling accurate and efficient health assessment.
Clemens Watzenböck, Daniel Aletaha, Michaël Deman
et al.
Quantitative disease severity scoring in medical imaging is costly, time-consuming, and subject to inter-reader variability. At the same time, clinical archives contain far more longitudinal imaging data than expert-annotated severity scores. Existing self-supervised methods typically ignore this chronological structure. We introduce ChronoCon, a contrastive learning approach that replaces label-based ranking losses with rankings derived solely from the visitation order of a patient's longitudinal scans. Under the clinically plausible assumption of monotonic progression in irreversible diseases, the method learns disease-relevant representations without using any expert labels. This generalizes the idea of Rank-N-Contrast from label distances to temporal ordering. Evaluated on rheumatoid arthritis radiographs for severity assessment, the learned representations substantially improve label efficiency. In low-label settings, ChronoCon significantly outperforms a fully supervised baseline initialized from ImageNet weights. In a few-shot learning experiment, fine-tuning ChronoCon on expert scores from only five patients yields an intraclass correlation coefficient of 86% for severity score prediction. These results demonstrate the potential of chronological contrastive learning to exploit routinely available imaging metadata to reduce annotation requirements in the irreversible disease domain. Code is available at https://github.com/cirmuw/ChronoCon.
Angelina Baric, Vasanti S. Malik, Anthea Christoforou
Abstract Background Ultra-processed food (UPF) contributes to nearly 50% of Canadians’ diets. Research in other countries has begun to implicate high intakes of UPFs and negative health outcomes, including body mass index, waist circumference, blood pressure, and unfavourable lipid profiles. There have been no population level examinations of the relationship between UPF consumption and cardiometabolic risk in Canada. Methods Drawing on the Canadian Health Measures Survey (2016/17 and 2018/19), this study investigates the relationship between UPF consumption and cardiometabolic risk factors among Canadians (ages 19–79, n = 6517). Dietary data collected by Food Frequency Questionnaire was classified as UPF or not using the NOVA classification system which scores foods by degree of processing. Participants were grouped into quartiles based on the daily servings of UPF. Sociodemographic and lifestyle variables were collected via household questionnaire and cardiometabolic outcomes were measured during a clinic visit. Multivariable linear regression analyses separately assessed the association between cardiometabolic risk factors and UPF quartiles while adjusting for various sociodemographic and lifestyle variables. Sensitivity analyses additionally adjusted for fruit and vegetable intake (servings/day) to determine the effect of diet quality on this relationship. All analyses were weighted to ensure national representativeness. Results UPF servings per day ranged from 1.2 in the lowest and 5.8 in the highest quartile. Compared to the lowest quartiles of UPF consumption, those in the highest were more likely to be male, in the lowest income quartile, Black or White, have lower household education, and higher physical activity and sedentary time. After adjustments, UPF consumption was positively associated with BMI, WC, diastolic BP, HBA1C, c-reactive protein, white blood cells (WBC), fasting triglycerides (TG), and fasting insulin. Fruit and vegetable intake attenuated the association for all outcomes, while BMI, WC, WBC, and TG remained significantly associated with increased UPF consumption. Conclusion This study is the first Canadian study looking at population level intakes of UPF across various cardiometabolic risk factors and adds to the growing body of literature demonstrating the detrimental health effects associated with UPF consumption.
Nutrition. Foods and food supply, Nutritional diseases. Deficiency diseases
Charles Apprey, Hammond Yaw Addae, Grace Boateng
et al.
Abstract The sustainable development goals seek to end all forms of malnutrition of women of reproductive age (WRA) by 2030. As such, recent data on nutrient adequacy are needed to aid in tracking progress. However, data on specific dietary nutrient intakes includes only iron, folate, vitamin A, and vitamin B12 in Ghana. Therefore, women's dietary diversity score (W‐DDS) is often used as a proxy measure of nutrient adequacy. It is hypothesised that there is no association between W‐DDS and Nutrient Adequacy among WRA in peri‐urban Ghana. Hence, this research evaluated the associations between W‐DDS and nutrient adequacy ratio (NAR) and assessed the determinants of mean nutrient adequacy ratio (MAR) in the Bosomtwe District of Ghana. A community‐based cross‐sectional study was conducted, and data collected on anthropometry, food insecurity, socio‐demographic characteristics and dietary intake using the 24‐hour recall from 407 WRA. In all, 21 nutrients were assessed. The mean age, W‐DDS, and MAR were 29.0 ± 6.7 years, 5.3 ± 1.9, and 0.65 ± 0.19 respectively. The NAR were generally high for the macronutrients as compared to micronutrients and the nutrients with low NAR included vitamin C (0.27 ± 0.19), vitamin A (0.15 ± 0.23), vitamin B12 (0.54 ± 0.32), calcium (0.28 ± 0.20), zinc (0.52 ± 0.23) and iron (0.57 ± 0.28) ‐ signifying the WRA may be consuming monotonous carbohydrate‐based diet. The hierarchical multivariable linear regression found a significant association between W‐DDS and MAR after controlling for confounders (β = 0.404, p < 0.001). The determinants of MAR were ethnicity (β = 0.110, p = 0.006) and body mass index (β = 0.189, p < 0.001). This study supports the use of W‐DDS as a proxy indicator of nutrient adequacy. Strategies meant to address nutrient inadequacies should be adaptable to different ethnic groups and overweight‐reducing strategies should be incorporated into broader nutrition initiatives.
ABSTRACT This study investigated adherence to Indonesia's Dietary Guidelines (IDG) among lactating women, examining related factors and association with nutrient intake adequacy, maternal and infant biomarkers, body mass index, and growth. Participants were lactating women (n = 220) from urban and rural West Java, Indonesia. Dietary intake (via 3‐day weighed food records), anthropometry and blood samples were assessed. Adherence was evaluated using a scoring system tailored for IDG and adapted from the Healthy Eating Index to assess intake of food groups, sugar, salt, fat, water, coffee, and breakfast habits. Starchy staples intake exceeded recommendations by nearly double (median 7.1 vs. recommended 3–4 servings/day), while vegetable (0.5 servings/day), fruit (1.0), and water (1300 mL/day) intake fell notably short. Protein‐rich food intake (3.5 servings/day) was closer to target. Only 1% of participants met three out of four food group targets. Adherence to the meal‐based MyPlate framework showed similar imbalances, with 68% of the plate occupied by starchy staples versus the recommended 33%. Sociodemographic factors, including education, wealth, and family size, were associated with adherence to IDG components. For instance, women in the highest wealth quintile had higher adherence scores for starchy staple moderation (mean 4.3) than those in the lowest (mean 2.9). Adherence to IDG components correlated positively with nutrient intake adequacy (e.g. protein‐rich food and overall adequacy: r = 0.19, 95% CI: 0.06–0.32) but not consistently with maternal or infant biomarkers. These findings highlight the need to refine dietary guidelines with clearer portion guidance and consideration of factors beyond intake adequacy during lactation.
Abstract Background Cardiovascular-kidney-metabolic (CKM) syndrome represents an emerging notion focused on the interconnection among cardiovascular, renal, and metabolic disorders. The predictive value of the cholesterol-high-density lipoprotein-glucose (CHG) index for advanced CKM syndrome and its stage-stratified mortality risk across stages 0 to 3 remains uncertain. This research aims to examine the clinical importance of the CHG and the triglyceride-glucose (TyG) indices in characterizing the development of advanced CKM syndrome and predicting mortality within the 0–3 stage. Methods We processed the data from the National Health and Nutrition Examination Survey (NHANES) 2003–2018. Associations were evaluated using multivariate logistic regression for disease progression and Cox models with restricted cubic splines (RCS) for mortality outcomes, accompanied by threshold effect and mediation analyses. Results Using multivariable logistic regression models, we found that both the CHG index and the TyG index are positively related with advanced CKM syndrome. Multivariable-adjusted modeling showed a 44% increase in the threat of all-cause mortality for each 1-unit rise in the CHG index, while no association with cardiovascular mortality was found. RCS analysis revealed a J-curve pattern in the association of the CHG index with all-cause mortality and cardiovascular mortality, with thresholds of 5.16 and 5.27. Mediation analyses identified that alkaline phosphatase, neutrophils, and the systemic immune-inflammatory index mediated between 2.1% and 17.2% of the effect in the relationship between the CHG index and all-cause mortality. Conclusions The CHG index demonstrates dual clinical utility: stratifying patients with advanced CKM syndrome and predicting nonlinear mortality across the early progressive continuum (stages 0–3). Its J-shaped association with mortality suggests complex pathophysiological relationships requiring further investigation.
Agriculture is vital for global food security, but crops are vulnerable to diseases that impact yield and quality. While Convolutional Neural Networks (CNNs) accurately classify plant diseases using leaf images, their high computational demands hinder their deployment in resource-constrained settings such as smartphones, edge devices, and real-time monitoring systems. This study proposes a two-step model compression approach integrating Weight Pruning and Knowledge Distillation, along with the hybridization of DenseNet with Involutional Layers. Pruning reduces model size and computational load, while distillation improves the smaller student models performance by transferring knowledge from a larger teacher network. The hybridization enhances the models ability to capture spatial features efficiently. These compressed models are suitable for real-time applications, promoting precision agriculture through rapid disease identification and crop management. The results demonstrate ResNet50s superior performance post-compression, achieving 99.55% and 98.99% accuracy on the PlantVillage and PaddyLeaf datasets, respectively. The DenseNet-based model, optimized for efficiency, recorded 99.21% and 93.96% accuracy with a minimal parameter count. Furthermore, the hybrid model achieved 98.87% and 97.10% accuracy, supporting the practical deployment of energy-efficient devices for timely disease intervention and sustainable farming practices.
Accurate diagnosis of Mendelian diseases is crucial for precision therapy and assistance in preimplantation genetic diagnosis. However, existing methods often fall short of clinical standards or depend on extensive datasets to build pretrained machine learning models. To address this, we introduce an innovative LLM-Driven multi-agent debate system (MD2GPS) with natural language explanations of the diagnostic results. It utilizes a language model to transform results from data-driven and knowledge-driven agents into natural language, then fostering a debate between these two specialized agents. This system has been tested on 1,185 samples across four independent datasets, enhancing the TOP1 accuracy from 42.9% to 66% on average. Additionally, in a challenging cohort of 72 cases, MD2GPS identified potential pathogenic genes in 12 patients, reducing the diagnostic time by 90%. The methods within each module of this multi-agent debate system are also replaceable, facilitating its adaptation for diagnosing and researching other complex diseases.
Wheat yellow rust, caused by the fungus Puccinia striiformis, is a critical disease affecting wheat crops across Britain, leading to significant yield losses and economic consequences. Given the rapid environmental changes and the evolving virulence of pathogens, there is a growing need for innovative approaches to predict and manage such diseases over the long term. This study explores the feasibility of using deep learning models to predict outbreaks of wheat yellow rust in British fields, offering a proactive approach to disease management. We construct a yellow rust dataset with historial weather information and disease indicator acrossing multiple regions in England. We employ two poweful deep learning models, including fully connected neural networks and long short-term memory to develop predictive models capable of recognizing patterns and predicting future disease outbreaks.The models are trained and validated in a randomly sliced datasets. The performance of these models with different predictive time steps are evaluated based on their accuracy, precision, recall, and F1-score. Preliminary results indicate that deep learning models can effectively capture the complex interactions between multiple factors influencing disease dynamics, demonstrating a promising capacity to forecast wheat yellow rust with considerable accuracy. Specifically, the fully-connected neural network achieved 83.65% accuracy in a disease prediction task with 6 month predictive time step setup. These findings highlight the potential of deep learning to transform disease management strategies, enabling earlier and more precise interventions. Our study provides a methodological framework for employing deep learning in agricultural settings but also opens avenues for future research to enhance the robustness and applicability of predictive models in combating crop diseases globally.
Zhuangzhuang Jia, Hyuk Park, Gökçe Dayanıklı
et al.
Infectious diseases pose major public health challenges to society, highlighting the importance of designing effective policies to reduce economic loss and mortality. In this paper, we propose a framework for sequential decision-making under uncertainty to design fairness-aware disease mitigation policies that incorporate various measures of unfairness. Specifically, our approach learns equitable vaccination and lockdown strategies based on a stochastic multi-group SIR model. To address the challenges of solving the resulting sequential decision-making problem, we adopt the path integral control algorithm as an efficient solution scheme. Through a case study, we demonstrate that our approach effectively improves fairness compared to conventional methods and provides valuable insights for policymakers.
Given the severe challenges confronting the global growth security of economic crops, precise identification and prevention of plant diseases has emerged as a critical issue in artificial intelligence-enabled agricultural technology. To address the technical challenges in plant disease recognition, including small-sample learning, leaf occlusion, illumination variations, and high inter-class similarity, this study innovatively proposes a Dynamic Dual-Stream Fusion Network (DS_FusionNet). The network integrates a dual-backbone architecture, deformable dynamic fusion modules, and bidirectional knowledge distillation strategy, significantly enhancing recognition accuracy. Experimental results demonstrate that DS_FusionNet achieves classification accuracies exceeding 90% using only 10% of the PlantDisease and CIFAR-10 datasets, while maintaining 85% accuracy on the complex PlantWild dataset, exhibiting exceptional generalization capabilities. This research not only provides novel technical insights for fine-grained image classification but also establishes a robust foundation for precise identification and management of agricultural diseases.
This comprehensive review explores food data in the Semantic Web, highlighting key nutritional resources, knowledge graphs, and emerging applications in the food domain. It examines prominent food data resources such as USDA, FoodOn, FooDB, and Recipe1M+, emphasizing their contributions to nutritional data representation. Special focus is given to food entity linking and recognition techniques, which enable integration of heterogeneous food data sources into cohesive semantic resources. The review further discusses food knowledge graphs, their role in semantic interoperability, data enrichment, and knowledge extraction, and their applications in personalized nutrition, ingredient substitution, food-drug and food-disease interactions, and interdisciplinary research. By synthesizing current advancements and identifying challenges, this work provides insights to guide future developments in leveraging semantic technologies for the food domain.
Coconut tree diseases are a serious risk to agricultural yield, particularly in developing countries where conventional farming practices restrict early diagnosis and intervention. Current disease identification methods are manual, labor-intensive, and non-scalable. In response to these limitations, we come up with DeepSeqCoco, a deep learning based model for accurate and automatic disease identification from coconut tree images. The model was tested under various optimizer settings, such as SGD, Adam, and hybrid configurations, to identify the optimal balance between accuracy, minimization of loss, and computational cost. Results from experiments indicate that DeepSeqCoco can achieve as much as 99.5% accuracy (achieving up to 5% higher accuracy than existing models) with the hybrid SGD-Adam showing the lowest validation loss of 2.81%. It also shows a drop of up to 18% in training time and up to 85% in prediction time for input images. The results point out the promise of the model to improve precision agriculture through an AI-based, scalable, and efficient disease monitoring system.
Our research is motivated by the urgent global issue of a large population affected by retinal diseases, which are evenly distributed but underserved by specialized medical expertise, particularly in non-urban areas. Our primary objective is to bridge this healthcare gap by developing a comprehensive diagnostic system capable of accurately predicting retinal diseases solely from fundus images. However, we faced significant challenges due to limited, diverse datasets and imbalanced class distributions. To overcome these issues, we have devised innovative strategies. Our research introduces novel approaches, utilizing hybrid models combining deeper Convolutional Neural Networks (CNNs), Transformer encoders, and ensemble architectures sequentially and in parallel to classify retinal fundus images into 20 disease labels. Our overarching goal is to assess these advanced models' potential in practical applications, with a strong focus on enhancing retinal disease diagnosis accuracy across a broader spectrum of conditions. Importantly, our efforts have surpassed baseline model results, with the C-Tran ensemble model emerging as the leader, achieving a remarkable model score of 0.9166, surpassing the baseline score of 0.9. Additionally, experiments with the IEViT model showcased equally promising outcomes with improved computational efficiency. We've also demonstrated the effectiveness of dynamic patch extraction and the integration of domain knowledge in computer vision tasks. In summary, our research strives to contribute significantly to retinal disease diagnosis, addressing the critical need for accessible healthcare solutions in underserved regions while aiming for comprehensive and accurate disease prediction.
Abstract Acute myocardial infarction (AMI) and related cardiovascular disease complications are the leading causes of mortality worldwide. Brown adipose tissue (BAT) is thermogenic and characterized by the uncoupling protein expression. Recent studies have found that in cardiovascular diseases, activated BAT can effectively improve the prognosis of AMI and concurrent heart failure through intercellular communication. However, a clear and systematic understanding of the myocardial protective mechanism of BAT after AMI is lacking, especially in the endocrine function of BAT. This review describes the effects of BAT on various cells in the heart after AMI. BAT plays a protective role on cardiac cells and fibroblasts during ischemia/reperfusion (I/R), myocardial remodeling, and myocardial fibrosis. This review also discusses the changes caused by BAT activation in different stages of heart failure. Finally, this review summarizes the treatment methods that target BAT to improve AMI. Further in-depth researches are still needed to clarify the underlying mechanism of the connection between BAT and different cells in cardiac tissue in order to identify potential therapeutic targets.
Purpose: The right way to measure obesity is still a matter of debate. This study will look at the prevalence of obesity, anthropometrics, and body composition as screening tools for obesity and adiposity among adult women in urban Prayagraj (Allahabad), Uttar Pradesh, India. It will also try to figure out exactly what level of obesity is linked to a metabolic risk. Methods: A Cross-sectional study comprising 570 urban women of Prayagraj (Allahabad), Uttar Pradesh, India aged 20–49 years were examined for anthropometry, body composition analysis, blood pressure, random blood sugar, and haemoglobin. Results: Except for total body water (TBW), all measures of obesity and health markers increased with age (p < 0.000, 95% CI-confidence interval). Appropriate cutoffs calculated with model for adult women for body fat (%), muscle mass (kg), total body water (%), and visceral fat (kg) were 33.5, 34.5, 46.5, and 4.5 respectively. Using stepwise logistic regression, two models eliminating waist circumference (WC) and wait to hip ratio (WHR), respectively, were created. Age, WHR, and visceral fat (VF) for systolic blood pressure; age and TBW for diastolic blood pressure; age and VF for random blood sugar; WHR, body fat% (BF %), Muscle mass (MM), and age for haemoglobin, were all significantly associated with the presence of metabolic risk variables in Model 1. In model 2, only age was significant for predicting systolic blood pressure; age, TBW, and WC for diastolic blood pressure; age and VF for random blood sugar; BF%, WC, and age for haemoglobin were shown to be significantly associated with metabolic risk variables. Conclusions: Two basic models for predicting metabolic risk in Asian Indians were studied. Both models can be used to assess metabolic risk in them.
Nutrition. Foods and food supply, Nutritional diseases. Deficiency diseases
Utilizing natural history data as external control plays an important role in the clinical development of rare diseases, since placebo groups in double-blind randomization trials may not be available due to ethical reasons and low disease prevalence. This article proposed an innovative approach for utilizing natural history data to support rare disease clinical development by constructing reference centile charts. Due to the deterioration nature of certain rare diseases, the distributions of clinical endpoints can be age-dependent and have an absorbing state of zero, which can result in censored natural history data. Existing methods of reference centile charts can not be directly used in the censored natural history data. Therefore, we propose a new calibrated zero-inflated kernel quantile (ZIKQ) estimation to construct reference centile charts from censored natural history data. Using the application to Duchenne Muscular Dystrophy drug development, we demonstrate that the reference centile charts using the ZIKQ method can be implemented to evaluate treatment efficacy and facilitate a more targeted patient enrollment in rare disease clinical development.