Nguemaïm N Flore, Nyong H Ndukong, Farikou Oumarou
et al.
ABSTRACT Consumption of raw fruits and vegetables constitute a potential source of spread for various parasitic infections. The level of contamination and the various species of parasites found are based on climatic, ecological, and human factors. The purpose of this study was to determine local data about the contamination status of raw fruits and vegetables commonly sold in markets at the Bamenda municipality and the predisposing factors, for better control of parasitic diseases. A cross-sectional study was conducted from May to July 2023 on fruits and vegetables collected from local markets of Bamenda town. A total of 200 samples were purchased from four main markets located at center town. The samples were microscopically examined for detection of different parasitic forms and determine the level of parasitic contamination using standardized parasitological techniques for protozoans and helminthes. The difference between prevalence of intestinal parasites among different categories was compared using Pearson chi-square test. Univariate logistic regression was used to assess factors associated with parasitic contamination of fruits and vegetables. The result was considered statistically significant when p value was less than 0.05 at 95% confidence level. A total of 123 individual parasites were found representing 61.5% of the infection in total produce. Ten (10) protozoa parasites were detected and Cryptosporidium spp (25.0%) were more represented followed by Entamoeba histolytica (12.5%) while Entamoeba coli (2.0%), Isospora belli (2.0%) and Balantidium coli (2.0%) have the least rate. Six (6) species of helminth parasites were identified and Hookworms (3,5%) were more present. The overall prevalence of parasitic contamination was 47.0%. Washing of the fruits and vegetables before display for selling was significantly associated with decreased parasitic contamination ( p < 0.05). The overall prevalence of parasitic contamination was 47.0%. Different parasites were identified in mono and or in polyinfection. C. pavum and E. histolytica were protozoa more common, while A. lumbricoïdes and Hookworms were the most frequent helminths. The act of washing fruits and vegetables before displaying for sale, the sources of water used for washing, the means of display for selling and their duration in the market appeared to be factors associated with parasitic contamination.
Stanislava Yordanova, Yuliana Atanasova, Ana Baykova
et al.
Tuberculosis is caused by closely related mycobacterial species, designated as M.tuberculosis complex (MTBC), which includes : M.tuberculosis sensu stricto, M.africanum, M.canettii, M.bovis, M.caprae, M. microti. There is an increase in human TB cases caused by M.bovis or M.caprae in the EU. Although Bulgaria is not a bovine TB-free country, the species identification inside the MTBC is not routinely performed for human isolates and the presumably animal related pathogens could not be distinguished. This study aimed to reveal the presence of M.bovis/M.caprae as an aetiological agent on the territory of Bulgaria. For the period from 2022 to 2025, a total of 175 MTBC strains were further examined to differentiate the species. GenoType MTBC VER 1.X was used as a reliable identification tool. Almost all cases were found to be M.tuberculosis/M.canettii (n=173; 98.85%). The prevalence of Mycobacterium bovis was 0.57%. M.bovis BCG also was represented by a single isolate (0.57%). M.africanum, M.microti, or M.caprae have not been detected so far. Species identification in the MTBC is an essential step in order to limit the transmission from animal to human and to refine the treatment of the affected individuals.
Nabajyoti Borah, Raju Moni Borah, Bandan Boruah
et al.
The proposed solution is Deep Learning Technique that will be able classify three types of tea leaves diseases from which two diseases are caused by the pests and one due to pathogens (infectious organisms) and environmental conditions and also show the area damaged by a disease in leaves. Namely Red Rust, Helopeltis and Red spider mite respectively. In this paper we have evaluated two models namely SSD MobileNet V2 and Faster R-CNN ResNet50 V1 for the object detection. The SSD MobileNet V2 gave precision of 0.209 for IOU range of 0.50:0.95 with recall of 0.02 on IOU 0.50:0.95 and final mAP of 20.9%. While Faster R-CNN ResNet50 V1 has precision of 0.252 on IOU range of 0.50:0.95 and recall of 0.044 on IOU of 0.50:0.95 with a mAP of 25%, which is better than SSD. Also used Mask R-CNN for Object Instance Segmentation where we have implemented our custom method to calculate the damaged diseased portion of leaves. Keywords: Tea Leaf Disease, Deep Learning, Red Rust, Helopeltis and Red Spider Mite, SSD MobileNet V2, Faster R-CNN ResNet50 V1 and Mask RCNN.
Modeling disease progression through multiple stages is critical for clinical decision-making for chronic diseases, e.g., cancer, diabetes, chronic kidney diseases, and so on. Existing approaches often model the disease progression as a uniform trajectory pattern at the population level. However, chronic diseases are highly heterogeneous and often have multiple progression patterns depending on a patient's individual genetics and environmental effects due to lifestyles. We propose a personalized disease progression model to jointly learn the heterogeneous progression patterns and groups of genetic profiles. In particular, an end-to-end pipeline is designed to simultaneously infer the characteristics of patients from genetic markers using a variational autoencoder and how it drives the disease progressions using an RNN-based state-space model based on clinical observations. Our proposed model shows improvement on real-world and synthetic clinical data.
Aquaculture is pivotal for global food security but faces significant challenges from infectious diseases, particularly those caused by Streptococcus species such as Streptococcus iniae and Streptococcus agalactiae. These pathogens induce severe systemic infections in various fish species, resulting in high morbidity and mortality rates. This review consolidates current knowledge on the epidemiology, pathogenesis, and clinical manifestations of these infections in fish and provides a comprehensive analysis of multifaceted control and prebention strategies. Advancements in genetic engineering and selective breeding are highlighted, demonstrating significant potential in developing disease-resistant fish strains through technologies like CRISPR-Cas9 and genomic selection. We examine the impact of farming practices on disease prevalence, emphasizing the roles of stocking density, feeding regimes, and biosecurity measures. The integration of big data analytics and IoT technologies is shown to revolutionize disease monitoring and management, enabling real-time surveillance and predictive modeling for timely interventions. Progress in vaccine development, including subunit, DNA, and recombinant protein vaccines, highlights the importance of tailored immunoprophylactic strategies. Furthermore, this review emphasizes the One-Health approach and the essential collaboration among industry, academia, and government to address the interconnected health of humans, animals, and the environment. This holistic strategy, supported by advanced technologies and collaborative efforts, promises to enhance the sustainability and productivity of aquaculture systems. Future research directions advocate for continued innovation and interdisciplinary partnerships to overcome the persistent challenges of streptococcal infections in aquaculture.
A. K. M. Shoriful Islam, Md. Rakib Hassan, Macbah Uddin
et al.
Poultry farming is a vital component of the global food supply chain, yet it remains highly vulnerable to infectious diseases such as coccidiosis, salmonellosis, and Newcastle disease. This study proposes a lightweight machine learning-based approach to detect these diseases by analyzing poultry fecal images. We utilize multi-color space feature extraction (RGB, HSV, LAB) and explore a wide range of color, texture, and shape-based descriptors, including color histograms, local binary patterns (LBP), wavelet transforms, and edge detectors. Through a systematic ablation study and dimensionality reduction using PCA and XGBoost feature selection, we identify a compact global feature set that balances accuracy and computational efficiency. An artificial neural network (ANN) classifier trained on these features achieved 95.85% accuracy while requiring no GPU and only 638 seconds of execution time in Google Colab. Compared to deep learning models such as Xception and MobileNetV3, our proposed model offers comparable accuracy with drastically lower resource usage. This work demonstrates a cost-effective, interpretable, and scalable alternative to deep learning for real-time poultry disease detection in low-resource agricultural settings.
Gastrointestinal diseases have one of the highest incidence rates worldwide. Klebsiella spp., which is a part of the large family Enterobacterales, isolated from fecal samples is considered as a part of the normal intestinal flora, even when it presents as a monoculture. The transmission of virulent plasmids from E. coli strains to Klebsiella spp., raises the question whether those bacteria can be an etiological factor for severe diarrhoea. By using PCR methods, the lth gene which is coding heat-labile enterotoxin (LT) was presented in the plasmids of Klebsiella spp. strains, and its expression was assessed.by measuring the cytopathic effect induced by the LT toxin.
Plant disease recognition is a critical task that ensures crop health and mitigates the damage caused by diseases. A handy tool that enables farmers to receive a diagnosis based on query pictures or the text description of suspicious plants is in high demand for initiating treatment before potential diseases spread further. In this paper, we develop a multimodal plant disease image retrieval system to support disease search based on either image or text prompts. Specifically, we utilize the largest in-the-wild plant disease dataset PlantWild, which includes over 18,000 images across 89 categories, to provide a comprehensive view of potential diseases relating to the query. Furthermore, cross-modal retrieval is achieved in the developed system, facilitated by a novel CLIP-based vision-language model that encodes both disease descriptions and disease images into the same latent space. Built on top of the retriever, our retrieval system allows users to upload either plant disease images or disease descriptions to retrieve the corresponding images with similar characteristics from the disease dataset to suggest candidate diseases for end users' consideration.
Many social and biological networks periodically change over time with daily, weekly, and other cycles. Thus motivated, we formulate and analyze susceptible-infectious-susceptible (SIS) epidemic models over temporal networks with periodic schedules. More specifically, we assume that the temporal network consists of a cycle of alternately used static networks, each with a given duration. We observe a phenomenon in which two static networks are individually above the epidemic threshold but the alternating network composed of them renders the dynamics below the epidemic threshold, which we refer to as a Parrondo paradox for epidemics. We find that network structure plays an important role in shaping this phenomenon, and we study its dependence on the connectivity between and number of subpopulations in the network. We associate such paradoxical behavior with anti-phase oscillatory dynamics of the number of infectious individuals in different subpopulations.
Catarina Botelho, Alberto Abad, Tanja Schultz
et al.
Speech is a rich biomarker that encodes substantial information about the health of a speaker, and thus it has been proposed for the detection of numerous diseases, achieving promising results. However, questions remain about what the models trained for the automatic detection of these diseases are actually learning and the basis for their predictions, which can significantly impact patients' lives. This work advocates for an interpretable health model, suitable for detecting several diseases, motivated by the observation that speech-affecting disorders often have overlapping effects on speech signals. A framework is presented that first defines "reference speech" and then leverages this definition for disease detection. Reference speech is characterized through reference intervals, i.e., the typical values of clinically meaningful acoustic and linguistic features derived from a reference population. This novel approach in the field of speech as a biomarker is inspired by the use of reference intervals in clinical laboratory science. Deviations of new speakers from this reference model are quantified and used as input to detect Alzheimer's and Parkinson's disease. The classification strategy explored is based on Neural Additive Models, a type of glass-box neural network, which enables interpretability. The proposed framework for reference speech characterization and disease detection is designed to support the medical community by providing clinically meaningful explanations that can serve as a valuable second opinion.
Men who have sex with men and people living with HIV are disproportionately affected in the 2022 multi-country monkeypox epidemic. The smallpox vaccine can induce cross-reactive antibodies against the monkeypox virus (MPXV) and reduce the risk of infection. Data on antibodies against MPXV induced by historic smallpox vaccination in people with HIV are scarce. In this observational study, plasma samples were collected from people living with and without HIV in Shenzhen, China. We measured antibodies binding to two representative proteins of vaccinia virus (VACV; A27L and A33R) and homologous proteins of MPXV (A29L and A35R) using an enzyme-linked immunosorbent assay. We compared the levels of these antibodies between people living with and without HIV. Stratified analyses were performed based on the year of birth of 1981 when the smallpox vaccination was stopped in China. Plasma samples from 677 people living with HIV and 746 people without HIV were tested. A consistent pattern was identified among the four antibodies, regardless of HIV status. VACV antigen-reactive and MPXV antigen-reactive antibodies induced by historic smallpox vaccination were detectable in the people born before 1981, and antibody levels reached a nadir during or after 1981. The levels of smallpox vaccine-induced antibodies were comparable between people living with HIV and those without HIV. Our findings suggest that the antibody levels against MPXV decreased in both people living with and without HIV due to the cessation of smallpox vaccination.
Sean A. Locke, Dana M. Calhoun, José M. Valencia Cruz
et al.
Members of the genus Scaphanocephalus mature in accipitrids, particularly osprey, Pandion haliaetus, with metacercaria causing Black Spot Syndrome in reef fishes. In most of the world, only the type species, Scaphanocephalus expansus (Creplin, 1842) has been reported. Recent molecular studies in the Western Atlantic, Mediterranean and Persian Gulf reveal multiple species of Scaphanocephalus, but have relied on 28S rDNA, mainly from metacercariae, which limits both morphological identification and resolution of closely related species. Here we combine nuclear rDNA with mitochondrial sequences from adult worms collected in osprey across North America and the Caribbean to describe species and elucidate life cycles in Scaphanocephalus. A new species described herein can be distinguished from S. expansus based on overall body shape and size. Phylogenetic analysis of the whole mitochondrial genome of Scaphanocephalus indicates a close relationship with Cryptocotyle. We conclude that at least 3 species of Scaphanocephalus are present in the Americas and 2 others are in the Old World. Specimens in the Americas have similar or identical 28S to those in the Mediterranean and Persian Gulf, but amphi-Atlantic species are unlikely in light of divergence in cytochrome c oxidase I and the lack of amphi-Atlantic avian and fish hosts. Our results provide insight into the geographic distribution and taxonomy of a little-studied trematode recently linked to an emerging pathology in ecologically important reef fishes.
Background: The effectiveness and safety of recently implemented COVID-19 vaccine platforms are often compared since the launch of the mass vaccination campaign worldwide. The aim of the present study is to assess the prevalence of adverse events (AEs) occurring after vaccination with the two viral vector-based vaccines authorized in the European Union to prevent COVID-19. Materials and methods: A survey was carried out among adults who have completed vaccination with either of the viral vector-based vaccine approved for use in Bulgaria ChAdOx1-S nCoV-19 vaccine (commonly known as Astra Zeneca or Vaxzevria) or Ad26.COV2S vaccine (commonly known as Janssen or JCOVDEN). For the data analysis, standard descriptive statistics was used. Quantitative variables are presented by the mean and standard deviation (mean ± SD) or median (25th percentile; 75th percentile). Qualitative variables are presented as numbers absolute/relative frequencies totals and percentages. The Kolmogorov-Smirnov test was used to obtain information regarding the distribution of the sampled patients. The chi-square test for independence was used to determine whether differences between observed and theoretical distributions existed. Results: In total 314 respondents took part in the study. Of them, 273 (86.9%) reported at least one local AE after the first dose of a vaccine, and the prevalence among the ChAdOx1-S vaccine group was significantly higher (88.5%) than in the Ad26.COV2.S vaccine group (59.2%) (Pearson χ2 test=19.942, p=0.000). The most common systemic AEs after administration of a viral vector-based vaccine were chills (77.3% for ChAdOx1-S and 25.9% for Ad26. COV2.S.) fatigue (76.3% for ChAdOx1-S and 25.9% for Ad26.COV2.S.), and headache (62.3% for ChAdOx1-S and 25.9% for Ad26.COV2.S.). Those adverse events appeared significantly more often in participants vaccinated with the ChAdOx1-S vaccine. Conclusion: The analysis of the collected data proves that although common, AEs following vaccination with vector-based products are classified as mild and usually resolve within 48 hours of dose administration.
The agricultural sector plays an essential role in the economic growth of a country. Specifically, in an Indian context, it is the critical source of livelihood for millions of people living in rural areas. Plant Disease is one of the significant factors affecting the agricultural sector. Plants get infected with diseases for various reasons, including synthetic fertilizers, archaic practices, environmental conditions, etc., which impact the farm yield and subsequently hinder the economy. To address this issue, researchers have explored many applications based on AI and Machine Learning techniques to detect plant diseases. This research survey provides a comprehensive understanding of common plant leaf diseases, evaluates traditional and deep learning techniques for disease detection, and summarizes available datasets. It also explores Explainable AI (XAI) to enhance the interpretability of deep learning models' decisions for end-users. By consolidating this knowledge, the survey offers valuable insights to researchers, practitioners, and stakeholders in the agricultural sector, fostering the development of efficient and transparent solutions for combating plant diseases and promoting sustainable agricultural practices.
Simon Bilik, Daniel Batrakhanov, Tuomas Eerola
et al.
Phytoplankton parasites are largely understudied microbial components with a potentially significant ecological impact on phytoplankton bloom dynamics. To better understand their impact, we need improved detection methods to integrate phytoplankton parasite interactions in monitoring aquatic ecosystems. Automated imaging devices usually produce high amount of phytoplankton image data, while the occurrence of anomalous phytoplankton data is rare. Thus, we propose an unsupervised anomaly detection system based on the similarity of the original and autoencoder-reconstructed samples. With this approach, we were able to reach an overall F1 score of 0.75 in nine phytoplankton species, which could be further improved by species-specific fine-tuning. The proposed unsupervised approach was further compared with the supervised Faster R-CNN based object detector. With this supervised approach and the model trained on plankton species and anomalies, we were able to reach the highest F1 score of 0.86. However, the unsupervised approach is expected to be more universal as it can detect also unknown anomalies and it does not require any annotated anomalous data that may not be always available in sufficient quantities. Although other studies have dealt with plankton anomaly detection in terms of non-plankton particles, or air bubble detection, our paper is according to our best knowledge the first one which focuses on automated anomaly detection considering putative phytoplankton parasites or infections.
Currently intelligent diagnosis systems lack the ability of continually learning to diagnose new diseases once deployed, under the condition of preserving old disease knowledge. In particular, updating an intelligent diagnosis system with training data of new diseases would cause catastrophic forgetting of old disease knowledge. To address the catastrophic forgetting issue, an Adapter-based Continual Learning framework called ACL is proposed to help effectively learn a set of new diseases at each round (or task) of continual learning, without changing the shared feature extractor. The learnable lightweight task-specific adapter(s) can be flexibly designed (e.g., two convolutional layers) and then added to the pretrained and fixed feature extractor. Together with a specially designed task-specific head which absorbs all previously learned old diseases as a single "out-of-distribution" category, task-specific adapter(s) can help the pretrained feature extractor more effectively extract discriminative features between diseases. In addition, a simple yet effective fine-tuning is applied to collaboratively fine-tune multiple task-specific heads such that outputs from different heads are comparable and consequently the appropriate classifier head can be more accurately selected during model inference. Extensive empirical evaluations on three image datasets demonstrate the superior performance of ACL in continual learning of new diseases. The source code is available at https://github.com/GiantJun/CL_Pytorch.
Heart disease is the major cause of non-communicable and silent death worldwide. Heart diseases or cardiovascular diseases are classified into four types: coronary heart disease, heart failure, congenital heart disease, and cardiomyopathy. It is vital to diagnose heart disease early and accurately in order to avoid further injury and save patients' lives. As a result, we need a system that can predict cardiovascular disease before it becomes a critical situation. Machine learning has piqued the interest of researchers in the field of medical sciences. For heart disease prediction, researchers implement a variety of machine learning methods and approaches. In this work, to the best of our knowledge, we have used the dataset from IEEE Data Port which is one of the online available largest datasets for cardiovascular diseases individuals. The dataset isa combination of Hungarian, Cleveland, Long Beach VA, Switzerland & Statlog datasets with important features such as Maximum Heart Rate Achieved, Serum Cholesterol, Chest Pain Type, Fasting blood sugar, and so on. To assess the efficacy and strength of the developed model, several performance measures are used, such as ROC, AUC curve, specificity, F1-score, sensitivity, MCC, and accuracy. In this study, we have proposed a framework with a stacked ensemble classifier using several machine learning algorithms including ExtraTrees Classifier, Random Forest, XGBoost, and so on. Our proposed framework attained an accuracy of 92.34% which is higher than the existing literature.
Santiago Sanchez-Pardo, Sebastián Mackenzie-Martinez, Samuel Martinez-Vernaza
et al.
Human melioidosis is a serious infectious disease commonly known by being endemic in southeast Asia and northern Australia. It is caused by Burkholderia pseudomallei a non-spore forming gram negative bacillus. Here we present the case of a 66-year-old woman with a history of stage IV lung adenocarcinoma that presented to the ER with 3 days of fever and altered mental status. Isolation from CSF culture was obtained confirming Burkholderia pseudomallei. Despite adequate antimicrobial treatment the patient continued to deteriorate and finally died 15 days after admission. To our knowledge there is only one additional reported case of Burkholderia pseudomallei meningitis in South America and the first one to be reported in Colombia.
Adam Eckart, Amir Bhochhibhoya, James Stavitz
et al.
Background: Some individuals adopt vegetarian or plant-based diets to improve their health. Observational evidence suggests diets composed of higher amounts of animal-source foods (ASFs) are associated with increased risk for disease and early mortality. In many of these studies, those who ate fewer animal-source foods reported fewer disease risk factors and unhealthy behaviors, which could indicate bias. Purpose: This study aims to examine the relationships between ASF consumption, health behaviors, and cardiovascular disease (CVD) prevalence in a population-representative sample of U.S. civilians controlling for confounders. Methods: Respondent data were collected from the National Health and Nutrition Examination Survey (NHANES) 2013–2016 collection years. Collected data included demographics, ASF intake, healthy lifestyle variables, body mass index, and blood lipids. Results: There was a higher proportion of those with CVD history who consumed red meat (61.3%; C.I. 41.7%–77.8%), but the proportion was lower for white (23.3%; C.I. 12.6%–39.0%) and processed meat (15.4%; C.I. 6.5%–32.3%). When adjusted for sex, the odds of CVD history increased for red meat compared to processed meat consumption (OR 2.95; C.I. 1.14–7.66). Unhealthy lifestyle increased the odds of CVD history by nearly 8-fold (OR 7.8; C.I. 3.44–17.7). Individual factors including age, smoking history, body mass index, and blood lipids, and demographic factors, including education level, race, and income, were also associated with increased odds for CVD history. ROC analysis revealed 77.2% AUC for CVD history classified by individual factors (BMI ≥30 kg/m**2, ≤ 30 min moderate physical activity, smoker, fiber intake ≤25 g, dental visit more than two years ago, and age above 60 years). Three or more factors moderately predicted CVD history when optimized for sensitivity (73.4%) and specificity (71%). Adjusted for sex, the relationship between CVD and moderate physical activity became stronger possibly reflecting lifestyle changes. Despite evidence of lifestyle changes, modifiable risk factors persisted in the CVD group. CVD diagnosis in males was substantially delayed compared to females concerning the sex-specific age cutoff associated with higher risk. The healthy lifestyle group was characterized by earlier CVD diagnosis and fewer overall risk factors compared to the unhealthy lifestyle group. Conclusion: CVD history was strongly associated with demographic, lifestyle, and dietary factors. Future research should focus on multidimensional models for disease risk stratification and prevention, including individual, behavioral, and sociodemographic factors.
Measles virus causes an acute infectious disease with high contagiousness. It is possible to limit the spread of measles virus only with a sufficiently wide coverage of the population by vaccination. Despite the success of measles elimination programs, many countries have seen an increase in the incidence of measles in recent years, making early diagnosis increasingly important. The importance of laboratory diagnosis is related to the difficulties of clinical differential diagnosis of measles in the early stages of the disease. This review is devoted to an analysis of existing methods for diagnosing measles. It demonstrates the limitations of the most commonly used method, the enzyme immunoassay, and the need to develop and implement alternative diagnostic methods. Particular attention in the review is paid to molecular diagnostic methods, the sensitivity of which is reviewed for different types of biological sampled at different stages of the disease. Characteristics of the measles virus that are of key importance in the development of PCR tests are described. Studies evaluating the significance of introducing PCR in the routine diagnosis of measles are presented. The main advantages of molecular methods are the possibility of early detection of the virus and the possibility of simultaneous detection of several pathogens, which allows differential diagnosis of diseases with a similar clinical presentation. The development and implementation of rapid and accurate approaches based on molecular diagnostic methods into the health care system is an urgent need in the implementation of global and local programs for the elimination of measles.