Jose-Maria Blanc, Isabel Jimeno-Sanz, Valentín Hernández-Barrera
et al.
Herpes zoster (HZ) is a vaccine-preventable disease with increasing incidence and hospitalization burden, particularly among older adults and immunocompromised individuals, who have an increased risk. In 2021, Spain introduced systematic vaccination with the recombinant zoster vaccine (RZV). We conducted a retrospective, descriptive study using hospital discharge data from the Spanish Minimum Basic DataSet (MBDS) for the years 2022–2023. Hospitalization rates (HR), mortality rates (MR), case fatality rates (CFR), length of stay, comorbidities, and costs were analyzed nationally and for the region of Madrid. A total of 16,277 HZ-related hospitalizations were recorded in Spain, with 80% occurring in individuals aged ≥65 y. The HR was 16.85 per 100,000 inhabitants, and the CFR was 7.44%. In Madrid, 3263 hospitalizations were recorded, with a higher HR (23.73 per 100,000) and CFR (6.41%) compared to the national average. Complicated HZ cases accounted for over 64% of hospitalizations nationally and 69% in Madrid. Total hospitalization costs were €98.1 million in Spain and €21.4 million in Madrid. This is the first study to assess HZ hospitalization burden in Spain and Madrid following the introduction of RZV. The findings highlight the substantial toll of HZ on older and immunocompromised populations. Future studies with longer follow-up are needed to assess vaccine impact.
Md. Ehsanul Haque, Md. Saymon Hosen Polash, Rakib Hasan Ovi
et al.
Grapes are among the most economically and culturally significant fruits on a global scale, and table grapes and wine are produced in significant quantities in Europe and Asia. The production and quality of grapes are significantly impacted by grape diseases such as Bacterial Rot, Downy Mildew, and Powdery Mildew. Consequently, the sustainable management of a vineyard necessitates the early and precise identification of these diseases. Current automated methods, particularly those that are based on the YOLO framework, are often computationally costly and lack interpretability that makes them unsuitable for real-world scenarios. This study proposes grape leaf disease classification using Optimized DenseNet 121. Domain-specific preprocessing and extensive connectivity reveal disease-relevant characteristics, including veins, edges, and lesions. An extensive comparison with baseline CNN models, including ResNet18, VGG16, AlexNet, and SqueezeNet, demonstrates that the proposed model exhibits superior performance. It achieves an accuracy of 99.27%, an F1 score of 99.28%, a specificity of 99.71%, and a Kappa of 98.86%, with an inference time of 9 seconds. The cross-validation findings show a mean accuracy of 99.12%, indicating strength and generalizability across all classes. We also employ Grad-CAM to highlight disease-related regions to guarantee the model is highlighting physiologically relevant aspects and increase transparency and confidence. Model optimization reduces processing requirements for real-time deployment, while transfer learning ensures consistency on smaller and unbalanced samples. An effective architecture, domain-specific preprocessing, and interpretable outputs make the proposed framework scalable, precise, and computationally inexpensive for detecting grape leaf diseases.
Imaging and genomic data offer distinct and rich features, and their integration can unveil new insights into the complex landscape of diseases. In this study, we present a novel approach utilizing radiogenomic data including structural MRI images and gene expression data, for Alzheimer's disease detection. Our framework introduces a novel heterogeneous bipartite graph representation learning featuring two distinct node types: genes and images. The network can effectively classify Alzheimer's disease (AD) into three distinct stages:AD, Mild Cognitive Impairment (MCI), and Cognitive Normal (CN) classes, utilizing a small dataset. Additionally, it identified which genes play a significant role in each of these classification groups. We evaluate the performance of our approach using metrics including classification accuracy, recall, precision, and F1 score. The proposed technique holds potential for extending to radiogenomic-based classification to other diseases.
Demographic attributes are universally present in electronic health records. They are the most widespread information across populations and diseases, and serve as vital predictors in clinical risk stratification and treatment decisions. Despite their significance, these attributes are often treated as auxiliaries in model design, with limited attention being paid to learning their representations. This study explored the development of a General Demographic Pre-trained (GDP) model as a foundational model tailored to demographic attributes, focusing on age and gender. The model is pre-trained and evaluated using datasets with diverse diseases and populations compositions from different geographic regions. The composition of GDP architecture was explored through examining combinations of ordering approaches and encoding methods to transform tabular demographic inputs into effective latent embeddings. Results demonstrate the feasibility of GDP to generalize across task, diseases, and populations. In detailed composition, the sequential ordering substantially improves model performance in discrimination, calibration, and the corresponding information gain at each decision tree split, particularly in diseases where age and gender contribute significantly to risk stratification. Even in datasets where demographic attributes hold relatively low predictive value, GDP enhances the representational importance, increasing their influence in downstream gradient boosting models. The findings suggest that foundation models for tabular demographic attributes offer a promising direction for improving predictive performance in healthcare applications.
ObjectiveThis study employed Mendelian Randomization (MR) to investigate the causal relationships among immune cells, COPD, and potential metabolic mediators.MethodsUtilizing summary data from genome-wide association studies, we analyzed 731 immune cell phenotypes, 1,400 plasma metabolites, and COPD. Bidirectional MR analysis was conducted to explore the causal links between immune cells and COPD, complemented by two-step mediation analysis and multivariable MR to identify potential mediating metabolites.ResultsCausal relationships were identified between 41 immune cell phenotypes and COPD, with 6 exhibiting reverse causality. Additionally, 21 metabolites were causally related to COPD. Through two-step MR and multivariable MR analyses, 8 cell phenotypes were found to have causal relationships with COPD mediated by 8 plasma metabolites (including one unidentified), with 1-methylnicotinamide levels showing the highest mediation proportion at 26.4%.ConclusionWe have identified causal relationships between 8 immune cell phenotypes and COPD, mediated by 8 metabolites. These findings contribute to the screening of individuals at high risk for COPD and offer insights into early prevention and the precocious diagnosis of Pre-COPD.
Georgia Véras de Araújo Gueiros Lira,1,2 Giselia Alves Pontes da Silva,2 Patricia Gomes de Matos Bezerra,3 Emanuel SC Sarinho1,2 1Allergy and Immunology Research Centre, Federal University of Pernambuco, Recife, PE, Brazil; 2Department of Paediatrics, Federal University of Pernambuco, Recife, PE, Brazil; 3Department of Pediatric Pulmonology, Instituto de Medicina Integral Prof. Fernando Figueira, Recife, PE, BrazilCorrespondence: Georgia Véras de Araújo Gueiros Lira, Allergy and Immunology Research Centre, Federal University of Pernambuco, Av. Prof. Morais Rego, 1235 – University City, Recife, PE, CEP: 50670-901, Brazil, Tel +81 2126-8000 ; +81 3268-9336, Email georgiaveras@uol.com.brAbstract: Much is known about the role of aeroallergens in asthma, but little is described about the damage caused by inhaled pollutants and irritants to the respiratory epithelium. In this context, the most frequent pollutants and irritants inhaled in the home environment were identified, describing the possible repercussions that may occur in the respiratory tract of the pediatric population with asthma and highlighting the role of the caregiver in environmental control through a salutogenic perspective. Searches were carried out in the MEDLINE/PubMed, Web of Science, Lilacs and Scopus databases for articles considered relevant for the theoretical foundation of this integrative review, in which interactions between exposure to pollutants and inhaled irritants and lung involvement. Articles published in the last 10 years that used the following descriptors were considered: air pollution; tobacco; particulate matter; disinfectants; hydrocarbons, fluorinated; odorants; chloramines; pesticide; asthma; and beyond Antonovsky’s sense of coherence. Exposure to smoke and some substances found in cleaning products, such as benzalkonium chloride, ethylenediaminetetraacetic acid and monoethanolamine, offer potential risks for sensitization and exacerbation of asthma. The vast majority of the seven main inhaled products investigated provoke irritative inflammatory reactions and oxidative imbalance in the respiratory epithelium. In turn, the caregiver’s role is essential in health promotion and the clinical control of paediatric asthma. From a salutogenic point of view, pollutants and irritants inhaled at home should be carefully investigated in the clinical history so that strategies to remove or reduce exposures can be used by caregivers of children and adolescents with asthma.Keywords: air pollution, tobacco, particulate matter, disinfectants, asthma, sense of coherence
The advances in computer vision made possible by deep learning technology are increasingly being used in precision agriculture to automate the detection and classification of plant diseases. Symptoms of plant diseases are often seen on their leaves. The leaf images in existing datasets have been collected either under controlled conditions or in the field. The majority of previous studies have focused on identifying leaf diseases using images captured in controlled laboratory settings, often achieving high performance. However, methods aimed at detecting and classifying leaf diseases in field images have generally exhibited lower performance. The objective of this study is to evaluate the impact of a data augmentation approach that involves removing complex backgrounds from leaf images on the classification performance of apple leaf diseases in images captured under real world conditions. To achieve this objective, the lightweight pre-trained MobileNetV2 deep learning model was fine-tuned and subsequently used to evaluate the impact of expanding the training dataset with background-removed images on classification performance. Experimental results show that this augmentation strategy enhances classification accuracy. Specifically, using the Adam optimizer, the proposed method achieved a classification accuracy of 98.71% on the Plant Pathology database, representing an approximately 3% improvement and outperforming state-of-the-art methods. This demonstrates the effectiveness of background removal as a data augmentation technique for improving the robustness of disease classification models in real-world conditions.
Abdelmalik Ouamane, Ammar Chouchane, Yassine Himeur
et al.
Machine learning has revolutionized the field of agricultural science, particularly in the early detection and management of plant diseases, which are crucial for maintaining crop health and productivity. Leveraging advanced algorithms and imaging technologies, researchers are now able to identify and classify plant diseases with unprecedented accuracy and speed. Effective management of tomato diseases is crucial for enhancing agricultural productivity. The development and application of tomato disease classification methods are central to this objective. This paper introduces a cutting-edge technique for the detection and classification of tomato leaf diseases, utilizing insights from the latest pre-trained Convolutional Neural Network (CNN) models. We propose a sophisticated approach within the domain of tensor subspace learning, known as Higher-Order Whitened Singular Value Decomposition (HOWSVD), designed to boost the discriminatory power of the system. Our approach to Tensor Subspace Learning is methodically executed in two phases, beginning with HOWSVD and culminating in Multilinear Discriminant Analysis (MDA). The efficacy of this innovative method was rigorously tested through comprehensive experiments on two distinct datasets, namely PlantVillage and the Taiwan dataset. The findings reveal that HOWSVD-MDA outperforms existing methods, underscoring its capability to markedly enhance the precision and dependability of diagnosing tomato leaf diseases. For instance, up to 98.36\% and 89.39\% accuracy scores have been achieved under PlantVillage and the Taiwan datasets, respectively.
Christof Naumzik, Alice Kongsted, Werner Vach
et al.
Clinical data informs the personalization of health care with a potential for more effective disease management. In practice, this is achieved by subgrouping, whereby clusters with similar patient characteristics are identified and then receive customized treatment plans with the goal of targeting subgroup-specific disease dynamics. In this paper, we propose a novel mixture hidden Markov model for subgrouping patient trajectories from chronic diseases. Our model is probabilistic and carefully designed to capture different trajectory phases of chronic diseases (i.e., "severe", "moderate", and "mild") through tailored latent states. We demonstrate our subgrouping framework based on a longitudinal study across 847 patients with non-specific low back pain. Here, our subgrouping framework identifies 8 subgroups. Further, we show that our subgrouping framework outperforms common baselines in terms of cluster validity indices. Finally, we discuss the applicability of the model to other chronic and long-lasting diseases.
The emergence or adaptation of pathogens may lead to epidemics, highlighting the need for a thorough understanding of pathogen evolution. The tradeoff hypothesis suggests that virulence evolves to reach an optimal transmission intensity relative to the mortality caused by the disease. This study introduces a mathematical model that incorporates key factors such as recovery times and mortality rates, focusing on the diminishing effects of parasite growth on transmission, with a focus on vector-borne diseases. The analysis reveals conditions under which heightened virulence occurs in hosts, indicating that these factors can support vector-host transmission of a pathogen, even if the host-only component is insufficient for sustainable transmission. This insight helps explain the significant presence of pathogens with high fatality rates, such as those in vector-borne diseases. The findings underscore an elevated risk for future outbreaks involving such diseases. Enhanced surveillance of mortality rates and techniques to monitor pathogen evolution are vital to effectively control future epidemics. This study provides essential insights for epidemic preparedness and highlights the need for ongoing research into pathogen evolution.
Christo Morison, Małgorzata Fic, Thomas Marcou
et al.
Cooperation arises in nature at every scale, from within cells to entire ecosystems. In the framework of evolutionary game theory, public goods games (PGGs) are used to analyse scenarios where individuals can cooperate or defect, and can predict when and how these behaviours emerge. However, too few examples motivate the transferal of knowledge from one application of PGGs to another. Here, we focus on PGGs arising in disease modelling of cancer evolution and the spread of infectious diseases. We use these two systems as case studies for the development of the theory and applications of PGGs, which we succinctly review and compare. We also posit that applications of evolutionary game theory to decision-making in cancer, such as interactions between a clinician and a tumour, can learn from the PGGs studied in epidemiology, where cooperative behaviours such as quarantine and vaccination compliance have been more thoroughly investigated. Furthermore, instances of cellular-level cooperation observed in cancers point to a corresponding area of potential interest for modellers of other diseases, be they viral, bacterial or otherwise. We aim to demonstrate the breadth of applicability of PGGs in disease modelling while providing a starting point for those interested in quantifying cooperation arising in healthcare.
Anne N. Shapiro, Lesley Scott, Harry Moultrie
et al.
AbstractThe National Health Laboratory Service (NHLS) collects all public health laboratory test results in South Africa, providing a cohort from which to identify groups, by age, sex, HIV, and viral suppression status, that would benefit from increased tuberculosis (TB) testing. Using NHLS data (2012–2016), we assessed levels and trends over time in TB diagnostic tests performed (count and per capita) and TB test positivity. Estimates were stratified by HIV status, viral suppression, age, sex, and province. We used logistic regression to estimate the odds of testing positive for TB by viral suppression status. Nineteen million TB diagnostic tests were conducted during period 2012–2016. Testing per capita was lower among PLHIV with viral suppression than those with unsuppressed HIV (0.08 vs 0.32) but lowest among people without HIV (0.03). Test positivity was highest among young adults (aged 15–35 years), males of all age groups, and people with unsuppressed HIV. Test positivity was higher for males without laboratory evidence of HIV than those with HIV viral suppression, despite similar individual odds of TB. Our results are an important national baseline characterizing who received TB testing in South Africa. People without evidence of HIV, young adults, and males would benefit from increased TB screening given their lower testing rates and higher test positivity. These high-test positivity groups can be used to guide future expansions of TB screening.
BackgroundThe quantitative level and kinetics of neutralizing antibodies (NAbs) in individuals with Omicron breakthrough infections may differ from those of vaccinated individuals without infection. Therefore, we aimed to evaluate the difference in NAb levels to distinguish the breakthrough cases from the post-immunized population to identify early infected person in an outbreak epidemic when nasal and/or pharyngeal swab nucleic acid real-time PCR results were negative.MethodsWe collected 1077 serum samples from 877 individuals, including 189 with Omicron BA.2 breakthrough infection and 688 post-immunized participants. NAb titers were detected using the surrogate virus neutralization test, and were log(2)-transformed to normalize prior to analysis using Student’s unpaired t-tests. Geometric mean titers (GMT) were calculated with 95% confidence intervals (CI). Linear regression models were used to identify factors associated with NAb levels. We further conducted ROC curve analysis to evaluate the NAbs’ ability to identify breakthrough infected individuals in the vaccinated population.ResultsThe breakthrough infection group had a consistently higher NAb levels than the post-immunized group according to time since the last vaccination. NAb titers in the breakthrough infection group were 6.4-fold higher than those in the post-immunized group (GMT: 40.72 AU/mL and 6.38 AU/mL, respectively; p<0.0001). In the breakthrough infection group, the NAbs in the convalescent phase were 10.9-fold higher than in the acute phase (GMT: 200.48 AU/mL and 18.46 AU/mL, respectively; p<0.0001). In addition, the time since infection, booster vaccination, and the time since last vaccination were associated with log(2)-transformed NAb levels in the breakthrough infection group. ROC curve analysis showed that ROC area was largest (0.728) when the cut-off value of log(2)-transformed NAb was 6, which indicated that NAb levels could identify breakthrough infected individuals in the vaccinated population.ConclusionOur study demonstrates that the NAb titers of Omicron BA.2 variant breakthrough cases are higher than in the post-immunized group. The difference in NAb levels could be used to identify cases of breakthrough infection from the post-immunized population in an outbreak epidemic.
Juliette Ferrant, Juliette Ferrant, Adeline Pontis
et al.
Sjögren syndrome (SjS) is an autoimmune disease characterized by the destruction of the exocrine gland epithelia, causing a dryness of mucosa called sicca symptoms, and whose main life-threatening complication is lymphoma. There is a need for new biomarkers in this disease, notably diagnostic biomarkers for patients with genuine sicca symptoms that do not meet current criteria, and prognostic biomarkers for patients at risk of lymphoma. Plasma extracellular vesicles (EVs) are promising biomarker candidates in several diseases, but their potential has not yet been explored in SjS. In this proof-of-concept study, we characterized EVs from primary SjS patients (pSS, n=12) at the phenotypic and proteomic levels, compared to EVs from healthy donor (HD, n=8) and systemic lupus erythematosus patients (SLE, n=12). Specific plasma EVs subpopulations, derived from neutrophils, endothelial, and epithelial cells, were found increased in pSS. We also identified a pSS proteomic signature in plasma EVs, including neutrophil-, epithelial-, and endothelial-related proteins, such as integrin alpha M (ITGAM), olfactomedin-4 (OLFM4), Ras-related protein RAB10, and CD36. Overall, our results support the relevance of plasma EVs as biomarkers in SjS.
Most people around the globe are dying due to heart disease. The main reason behind the rapid increase in the death rate due to heart disease is that there is no infrastructure developed for the healthcare department that can provide a secure way of data storage and transmission. Due to redundancy in the patient data, it is difficult for cardiac Professionals to predict the disease early on. This rapid increase in the death rate due to heart disease can be controlled by monitoring and eliminating some of the key attributes in the early stages such as blood pressure, cholesterol level, body weight, and addiction to smoking. Patient data can be monitored by cardiac Professionals (Cp) by using the advanced framework in the healthcare departments. Blockchain is the world's most reliable provider. The use of advanced systems in the healthcare departments providing new ways of dealing with diseases has been developed as well. In this article Machine Learning (ML) algorithm known as a sine-cosine weighted k-nearest neighbor (SCA-WKNN) is used for predicting the Hearth disease with the maximum accuracy among the existing approaches. Blockchain technology has been used in the research to secure the data throughout the session and can give more accurate results using this technology. The performance of the system can be improved by using this algorithm and the dataset proposed has been improved by using different resources as well.
Md. Hamjajul Ashmafee, Tasnim Ahmed, Sabbir Ahmed
et al.
Correct identification and categorization of plant diseases are crucial for ensuring the safety of the global food supply and the overall financial success of stakeholders. In this regard, a wide range of solutions has been made available by introducing deep learning-based classification systems for different staple crops. Despite being one of the most important commercial crops in many parts of the globe, research proposing a smart solution for automatically classifying apple leaf diseases remains relatively unexplored. This study presents a technique for identifying apple leaf diseases based on transfer learning. The system extracts features using a pretrained EfficientNetV2S architecture and passes to a classifier block for effective prediction. The class imbalance issues are tackled by utilizing runtime data augmentation. The effect of various hyperparameters, such as input resolution, learning rate, number of epochs, etc., has been investigated carefully. The competence of the proposed pipeline has been evaluated on the apple leaf disease subset from the publicly available `PlantVillage' dataset, where it achieved an accuracy of 99.21%, outperforming the existing works.
Tea leaf diseases are a major challenge to agricultural productivity, with far-reaching implications for yield and quality in the tea industry. The rise of machine learning has enabled the development of innovative approaches to combat these diseases. Early detection and diagnosis are crucial for effective crop management. For predicting tea leaf disease, several automated systems have already been developed using different image processing techniques. This paper delivers a systematic review of the literature on machine learning methodologies applied to diagnose tea leaf disease via image classification. It thoroughly evaluates the strengths and constraints of various Vision Transformer models, including Inception Convolutional Vision Transformer (ICVT), GreenViT, PlantXViT, PlantViT, MSCVT, Transfer Learning Model & Vision Transformer (TLMViT), IterationViT, IEM-ViT. Moreover, this paper also reviews models like Dense Convolutional Network (DenseNet), Residual Neural Network (ResNet)-50V2, YOLOv5, YOLOv7, Convolutional Neural Network (CNN), Deep CNN, Non-dominated Sorting Genetic Algorithm (NSGA-II), MobileNetv2, and Lesion-Aware Visual Transformer. These machine-learning models have been tested on various datasets, demonstrating their real-world applicability. This review study not only highlights current progress in the field but also provides valuable insights for future research directions in the machine learning-based detection and classification of tea leaf diseases.
Allergen immunotherapy is highly effective in selected patients with allergic rhinitis, allergic asthma, and Hymenoptera venom allergy. Unlike anti-allergic drugs, both subcutaneous and sublingual immunotherapies have been shown to modify the underlying cause of the disease, with proved long-term clinical benefits after treatment cessation. In this review, we analyzed 10 randomized, double-blind, placebo controlled clinical trials of allergen immunotherapy that included blinded follow-up for at least 1 year after treatment withdrawal. Three studies of pollen subcutaneous immunotherapy provided evidence that a sustained, tolerogenic effect of subcutaneous immunotherapy can be achieved after 3 years of treatment. Six trials of sublingual immunotherapy provided robust evidence for long-term clinical benefit and persistent immunologic changes after grass pollen, house-dust mite, or Japanese cedar immunotherapy, whereas a clinical trial of both sublingual and subcutaneous grass pollen immunotherapies showed that 2 years of immunotherapy were efficacious but insufficient to induce long-term tolerance. These studies strongly supported international guidelines that recommend at least 3 years of allergen immunotherapy of proven value to achieve disease modification and sustained clinical and immunologic tolerance.