Diana Susan Joseph, Pranav M Pawar, Raja Muthalagu
et al.
Performing a timely and accurate identification of crop diseases is vital to maintain agricultural productivity and food security. The current work presents a hybrid few-shot learning model that integrates Explainable Artificial Intelligence (XAI) and Few-Shot Learning (FSL) to address the challenge of identifying and classifying the stages of disease of the diseases of maize, rice, and wheat leaves under limited annotated data conditions. The proposed model integrates Siamese and Prototypical Networks within an episodic training paradigm to effectively learn discriminative disease features from a few examples. To ensure model transparency and trustworthiness, Gradient-weighted Class Activation Mapping (Grad-CAM) is employed for visualizing key decision regions in the leaf images, offering interpretable insights into the classification process. Experimental evaluations on custom few-shot datasets developed in the study prove that the model consistently achieves high accuracy, precision, recall, and F1-scores, frequently exceeding 92% across various disease stages. Comparative analyses against baseline FSL models further confirm the superior performance and explainability of the proposed approach. The framework offers a promising solution for real-world, data-constrained agricultural disease monitoring applications.
Amy D. Burris, Nichole Diaz, Jon B. Meddings
et al.
ABSTRACT Background Human milk provides an infant one of the first routes of exposure to dietary antigens. A better understanding of the levels and functional capacity of maternal dietary proteins in human milk (HM) and their impact on infant food allergy (FA) is needed. Objective To measure the quantity and biologic activity of maternal dietary proteins in HM and determine factors associated with their presence. Methods HM samples from mothers of infants with or without FA were collected before and serially after consumption of a meal with prespecified amounts of peanut, egg, and cow's milk protein. Ara h 2 from peanut, egg ovalbumin, and bovine β‐lactoglobulin in HM was detected using ELISA. IgE‐crosslinking capacity of Ara h 2 was assessed by the basophil activation test (BAT). Maternal intestinal permeability was measured with the lactulose/mannitol test. Results Thirty‐nine mothers were included and 69% had measurable Ara h 2 in HM. Secretion of food allergens was variable between different mothers and across allergens, but did not correlate with intestinal permeability. Atopic mothers' milk had a higher peak Ara h 2 concentration (median 246 pg/mL, range 2.0–1634) than nonatopic mothers (median 0 pg/mL, range 0–135, p = 0.017). In samples with the most BAT reactivity, there was a significant correlation between BAT reactivity and Ara h 2 level ( R = 0.72, p = 2 × 10 −8 ). Multiple monoclonal antibodies directed at different epitopes detected Ara h 2 at similar levels. Conclusion Ara h 2 is secreted in HM as intact protein or significant parts of it that are capable of IgE‐crosslinking, found in higher levels in atopic mothers. HM levels of peanut lack correlation with other dietary proteins, which suggests antigen specificity of the secretion of dietary protein into HM.
Chronic diseases are long-term, manageable, yet typically incurable conditions, highlighting the need for effective preventive strategies. Machine learning has been widely used to assess individual risk for chronic diseases. However, many models rely on medical test data (e.g. blood results, glucose levels), which limits their utility for proactive self-assessment. Additionally, to gain public trust, machine learning models should be explainable and transparent. Although some research on self-assessment machine learning models includes explainability, their explanations are not validated against established medical literature, reducing confidence in their reliability. To address these issues, we develop deep learning models that predict the risk of developing 13 chronic diseases using only personal and lifestyle factors, enabling accessible, self-directed preventive care. Importantly, we use SHAP-based explainability to identify the most influential model features and validate them against established medical literature. Our results show a strong alignment between the models' most influential features and established medical literature, reinforcing the models' trustworthiness. Critically, we find that this observation holds across 13 distinct diseases, indicating that this machine learning approach can be broadly trusted for chronic disease prediction. This work lays the foundation for developing trustworthy machine learning tools for self-directed preventive care. Future research can explore other approaches for models' trustworthiness and discuss how the models can be used ethically and responsibly.
Vivek Chetia, Abdul Taher Khan, Rahish Gogoi
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.
BackgroundPeople living with HIV(PLWH) are a high-risk population for cancer. We conducted a pioneering study on the gut microbiota of PLWH with various types of cancer, revealing key microbiota.MethodsWe collected stool samples from 54 PLWH who have cancer (PLWH-C), including Kaposi’s sarcoma (KS, n=7), lymphoma (L, n=22), lung cancer (LC, n=12), and colorectal cancer (CRC, n=13), 55 PLWH who do not have cancer (PLWH-NC), and 49 people living without HIV (Ctrl). The gut microbiota in fecal samples was analyzed using 16S rRNA sequencing. We compared the microbial diversity among groups and identified key microbiota and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways using random forest. Furthermore, we analyzed the correlation between microbiota and KEGG pathways and constructed microbiota Receiver Operating Characteristic (ROC) diagnostic models.ResultsCompared with PLWH-NC and Ctrl, PLWH with any type of cancer exhibited significantly lower alpha diversity and significant alterations in beta diversity of the gut microbiota. The significantly decreased abundance of Bacteroides and Bacteroides vulgatus in PLWH-C showed a negative correlation with the Pathways in cancer pathway, and a positive correlation with Choline metabolism in cancer, Central carbon metabolism in cancer, and Proteoglycans in cancer pathways. Bacteroides (AUC≥0.84) and Bacteroides vulgatus (AUC≥0.78) exhibited discriminatory diagnostic capabilities for PLWH-C in patients with different cancers compared with PLWH-NC and Ctrl.DiscussionWe confirmed a more severe dysbiosis of the gut microbiota in PLWH with KS, L, LC, or CRC. Bacteroides may be associated with disruptions in cancer-related metabolic pathways and serve as diagnostic biomarkers for PLWH with various cancers.
Clarissa A. Seidler, Vera A. Spanke, Jakob Gamper
et al.
The Observed Antibody Space provides the most abundant collection of annotated paired antibody variable domain sequences, thus offering a unique platform for the systematic investigation of the factors governing the pairing of antibody heavy and light chains. By examining a range of characteristics, including amino acid conservation, structural features, charge distribution, and interface residue identity, we challenge the prevailing assumption that pairing is random. Our findings indicate that specific physicochemical properties of single amino acid residues may influence the compatibility and affinity of heavy and light chain combinations. Further structural analyses based on antibody Fv fragments deposited in the Protein Data Bank (PDB) provide insights into the underlying structural features driving these pairing preferences, including a novel definition for the residues constituting the VH-VL interface, based on a collection of over 3500 structures. These results have significant implications for understanding antibody assembly and may guide the rational design of therapeutic antibodies with desired properties. Moreover, we provide a complete description and reference characterizing the various human germlines.
Scott Pezanowski, Etien Luc Koua, Joseph C Okeibunor
et al.
Objectives: Our research adopts computational techniques to analyze disease outbreaks weekly over a large geographic area while maintaining local-level analysis by incorporating relevant high-spatial resolution cultural and environmental datasets. The abundance of data about disease outbreaks gives scientists an excellent opportunity to uncover patterns in disease spread and make future predictions. However, data over a sizeable geographic area quickly outpace human cognition. Our study area covers a significant portion of the African continent (about 17,885,000 km2). The data size makes computational analysis vital to assist human decision-makers. Methods: We first applied global and local spatial autocorrelation for malaria, cholera, meningitis, and yellow fever case counts. We then used machine learning to predict the weekly presence of these diseases in the second-level administrative district. Lastly, we used machine learning feature importance methods on the variables that affect spread. Results: Our spatial autocorrelation results show that geographic nearness is critical but varies in effect and space. Moreover, we identified many interesting hot and cold spots and spatial outliers. The machine learning model infers a binary class of cases or none with the best F1 score of 0.96 for malaria. Machine learning feature importance uncovered critical cultural and environmental factors affecting outbreaks and variations between diseases. Conclusions: Our study shows that data analytics and machine learning are vital to understanding and monitoring disease outbreaks locally across vast areas. The speed at which these methods produce insights can be critical during epidemics and emergencies.
Disease prediction holds considerable significance in modern healthcare, because of its crucial role in facilitating early intervention and implementing effective prevention measures. However, most recent disease prediction approaches heavily rely on laboratory test outcomes (e.g., blood tests and medical imaging from X-rays). Gaining access to such data for precise disease prediction is often a complex task from the standpoint of a patient and is always only available post-patient consultation. To make disease prediction available from patient-side, we propose Personalized Medical Disease Prediction (PoMP), which predicts diseases using patient health narratives including textual descriptions and demographic information. By applying PoMP, patients can gain a clearer comprehension of their conditions, empowering them to directly seek appropriate medical specialists and thereby reducing the time spent navigating healthcare communication to locate suitable doctors. We conducted extensive experiments using real-world data from Haodf to showcase the effectiveness of PoMP.
Recent studies have shown that local injection of secukinumab can achieve positive therapeutic effects when applied in the treatment of nail psoriasis. At present, there have been no other studies on the use of biological agents in the treatment of pediatric nail psoriasis. Three children were included in the study to evaluate the efficacy and safety of periungual injection and long-term injection of secukinumab in the treatment of nail psoriasis in children. It was found that local injection did not achieve a remarkable therapeutic effect. The nail lesions were improved continuously by subcutaneous injection once a month.
Saverio La Bella, Armando Di Ludovico, Giulia Di Donato
et al.
The activation of the pyrin inflammasome represents a highly intriguing mechanism employed by the innate immune system to effectively counteract pathogenic agents. Despite its key role in innate immunity, pyrin has also garnered significant attention due to its association with a range of autoinflammatory diseases (AIDs) including familial Mediterranean fever caused by disruption of the MEFV gene, or in other genes involved in its complex regulation mechanisms. Pyrin activation is strictly dependent on homeostasis-altering molecular processes, mostly consisting of the disruption of the small Ras Homolog Family Member A (RhoA) GTPases by pathogen toxins. The downstream pathways are regulated by the phosphorylation of specific pyrin residues by the kinases PKN1/2 and the binding of the chaperone 14-3-3. Furthermore, a key role in pyrin activation is played by the cytoskeleton and gasdermin D, which is responsible for membrane pores in the context of pyroptosis. In addition, recent evidence has highlighted the role of steroid hormone catabolites and alarmins S100A8/A9 and S100A12 in pyrin-dependent inflammation. The aim of this article is to offer a comprehensive overview of the most recent evidence on the pyrin inflammasome and its molecular pathways to better understand the pathogenesis behind the significant group of pyrin-related AIDs.
Tzvi Y. Pollock, Víctor R. Vázquez Marrero, Igor E. Brodsky
et al.
The inflammatory cytokine tumor necrosis factor (TNF) is necessary for host defense against many intracellular pathogens, including Legionella pneumophila. Legionella causes the severe pneumonia Legionnaires’ disease and predominantly affects individuals with a suppressed immune system, including those receiving therapeutic TNF blockade to treat autoinflammatory disorders. TNF induces pro-inflammatory gene expression, cellular proliferation, and survival signals in certain contexts, but can also trigger programmed cell death in others. It remains unclear, however, which of the pleiotropic functions of TNF mediate control of intracellular bacterial pathogens like Legionella. In this study, we demonstrate that TNF signaling licenses macrophages to die rapidly in response to Legionella infection. We find that TNF-licensed cells undergo rapid gasdermin-dependent, pyroptotic death downstream of inflammasome activation. We also find that TNF signaling upregulates components of the inflammasome response, and that the caspase-11-mediated non-canonical inflammasome is the first inflammasome to be activated, with caspase-1 and caspase-8 mediating delayed pyroptotic death. We find that all three caspases are collectively required for optimal TNF-mediated restriction of bacterial replication in macrophages. Furthermore, caspase-8 is required for control of pulmonary Legionella infection. These findings reveal a TNF-dependent mechanism in macrophages for activating rapid cell death that is collectively mediated by caspases-1, -8, and -11 and subsequent restriction of Legionella infection.
Streptococcus pneumoniae is an opportunistic pathogen that colonizes the upper respiratory tract asymptomatically and, upon invasion, can lead to severe diseases including otitis media, sinusitis, meningitis, bacteremia, and pneumonia. One of the first lines of defense against pneumococcal invasive disease is inflammation, including the recruitment of neutrophils to the site of infection. The invasive pneumococcus can be cleared through the action of serine proteases generated by neutrophils. It is less clear how serine proteases impact non-invasive pneumococcal colonization, which is the key first step to invasion and transmission. One significant aspect of pneumococcal biology and adaptation in the respiratory tract is its natural competence, which is triggered by a small peptide CSP. In this study, we investigate if serine proteases are capable of degrading CSP and the impact this has on pneumococcal competence. We found that CSP has several potential sites for trypsin-like serine protease degradation and that there were preferential cleavage sites recognized by the proteases. Digestion of CSP with two different trypsin-like serine proteases dramatically reduced competence in a dose-dependent manner. Incubation of CSP with mouse lung homogenate also reduced recombination frequency of the pneumococcus. These ex vivo experiments suggested that serine proteases in the lower respiratory tract reduce pneumococcal competence. This was subsequently confirmed measuring in vivo recombination frequencies after induction of protease production via poly (I:C) stimulation and via co-infection with influenza A virus, which dramatically lowered recombination events. These data shed light on a new mechanism by which the host can modulate pneumococcal behavior and genetic exchange via direct degradation of the competence signaling peptide.
I. Doña, N. Pérez‐Sánchez, I. Eguiluz-Gracia
et al.
Nonsteroidal anti‐inflammatory drugs (NSAIDs), the medications most commonly used for treating pain and inflammation, are the main triggers of drug hypersensitivity reactions. The latest classification of NSAIDs hypersensitivity by the European Academy of Allergy and Clinical Immunology (EAACI) differentiates between cross‐hypersensitivity reactions (CRs), associated with COX‐1 inhibition, and selective reactions, associated with immunological mechanisms. Three phenotypes fill into the first group: NSAIDs‐exacerbated respiratory disease, NSAIDs‐exacerbated cutaneous disease and NSAIDs‐induced urticaria/angioedema. Two phenotypes fill into the second one: single‐NSAID‐induced urticaria/angioedema/anaphylaxis and single‐NSAID‐induced delayed reactions. Diagnosis of NSAIDs hypersensitivity is hampered by different factors, including the lack of validated in vitro biomarkers and the uselessness of skin tests. The advances achieved over recent years recommend a re‐evaluation of the EAACI classification, as it does not consider other phenotypes such as blended reactions (coexistence of cutaneous and respiratory symptoms) or food‐dependent NSAID‐induced anaphylaxis. In addition, it does not regard the natural evolution of phenotypes and their potential interconversion, the development of tolerance over time or the role of atopy. Here, we address these topics. A state of the art on the underlying mechanisms and on the approaches for biomarkers discovery is also provided, including genetic studies and available information on transcriptomics and metabolomics.
The current COVID-19 pandemic influences many areas of social life, medical treatments and the way allergy is performed. Allergen-specific immunotherapy (AIT) is one of the most important treatment options for IgE-mediated allergies and is based on immunological effects on the diseased patient.
Gastrointestinal diseases pose significant healthcare chall-enges as they manifest in diverse ways and can lead to potential complications. Ensuring precise and timely classification of these diseases is pivotal in guiding treatment choices and enhancing patient outcomes. This paper introduces a novel approach on classifying gastrointestinal diseases by leveraging cost-sensitive pre-trained deep convolutional neural network (CNN) architectures with supervised contrastive learning. Our approach enables the network to learn representations that capture vital disease-related features, while also considering the relationships of similarity between samples. To tackle the challenges posed by imbalanced datasets and the cost-sensitive nature of misclassification errors in healthcare, we incorporate cost-sensitive learning. By assigning distinct costs to misclassifications based on the disease class, we prioritize accurate classification of critical conditions. Furthermore, we enhance the interpretability of our model by integrating gradient-based techniques from explainable artificial intelligence (AI). This inclusion provides valuable insights into the decision-making process of the network, aiding in understanding the features that contribute to disease classification. To assess the effectiveness of our proposed approach, we perform extensive experiments on a comprehensive gastrointestinal disease dataset, such as the Hyper-Kvasir dataset. Through thorough comparisons with existing works, we demonstrate the strong classification accuracy, robustness and interpretability of our model. We have made the implementation of our proposed approach publicly available at https://github.com/dibya404/Gastrointestinal-Disease-Classification-through-Explainable-and-Cost-Sensitive-DNN-with-SCL
The COVID-19 pandemic has highlighted the need for innovative solutions to monitor and control the spread of infectious diseases. With the potential for future pandemics and the risk of outbreaks particularly in academic institutions, there is a pressing need for effective approaches to monitor and manage such diseases. Contact tracing using Global Positioning Systems (GPS) has been found to be the most prevalent method to detect and tackle the extent of outbreaks during the pandemic. However, these services suffer from the inherent problems of infringement of data privacy that creates hindrance in adoption of the technology. Non-cellular wireless technologies on the other hand are well-suited to provide secure contact tracing methods. Such approaches integrated with the Internet of Things (IoT) have a great potential to aid in the fight against any type of infectious diseases. In response, we present a unique approach that utilizes an IoT based generic framework to identify individuals who may have been exposed to the virus, using contact tracing methods, without compromising the privacy aspect. We develop the architecture of our platform, including both the frontend and backend components, and demonstrate its effectiveness in identifying potential COVID-19 exposures (as a test case) through a proof-of-concept implementation. We also implement and verify a prototype of the device. Our framework is easily deployable and can be scaled up as needed with the existing infrastructure.
Raghav Singhal, Mukund Sudarshan, Anish Mahishi
et al.
Early detection of many life-threatening diseases (e.g., prostate and breast cancer) within at-risk population can improve clinical outcomes and reduce cost of care. While numerous disease-specific "screening" tests that are closer to Point-of-Care (POC) are in use for this task, their low specificity results in unnecessary biopsies, leading to avoidable patient trauma and wasteful healthcare spending. On the other hand, despite the high accuracy of Magnetic Resonance (MR) imaging in disease diagnosis, it is not used as a POC disease identification tool because of poor accessibility. The root cause of poor accessibility of MR stems from the requirement to reconstruct high-fidelity images, as it necessitates a lengthy and complex process of acquiring large quantities of high-quality k-space measurements. In this study we explore the feasibility of an ML-augmented MR pipeline that directly infers the disease sidestepping the image reconstruction process. We hypothesise that the disease classification task can be solved using a very small tailored subset of k-space data, compared to image reconstruction. Towards that end, we propose a method that performs two tasks: 1) identifies a subset of the k-space that maximizes disease identification accuracy, and 2) infers the disease directly using the identified k-space subset, bypassing the image reconstruction step. We validate our hypothesis by measuring the performance of the proposed system across multiple diseases and anatomies. We show that comparable performance to image-based classifiers, trained on images reconstructed with full k-space data, can be achieved using small quantities of data: 8% of the data for detecting multiple abnormalities in prostate and brain scans, and 5% of the data for knee abnormalities. To better understand the proposed approach and instigate future research, we provide an extensive analysis and release code.
BackgroundOrally administered small-molecule drugs including tyrosine kinase 2 (TYK2) inhibitors and phosphodiesterase 4 (PDE4) inhibitors are new candidates for systemic therapy in plaque psoriasis. However, no previous articles evaluated the benefit and risk profile of TYK2 and PDE4 inhibitors in psoriasis.ObjectivesThe objective of this study was to compare the efficacy and safety of oral small-molecule drugs, including TYK2 and PDE4 inhibitors, in treating moderate-to-severe plaque psoriasis.MethodsPubMed, Embase, and Cochrane library were searched for eligible randomized clinical trials (RCTs). Response rates for a 75% reduction from baseline in Psoriasis Area and Severity Index (PASI-75) and Physician’s Global Assessment score of 0 or 1 (PGA 0/1) were used for efficacy assessment. Safety was evaluated with the incidence of adverse events (AEs). A Bayesian multiple treatment network meta-analysis (NMA) was performed.ResultsIn total, 13 RCTs (five for TYK2 inhibitors and eight for PDE4 inhibitors) involving 5274 patients were included. The study found that deucravacitinib at any dose (except for 3 mg QOD), ropsacitinib (200 and 400 mg QD), and apremilast (20 and 30 mg BID) had higher PASI and PGA response rates than placebo. In addition, deucravacitinib (3 mg BID, 6 mg QD, 6 mg BID, and 12 mg QD), and ropsacitinib (400 mg QD) showed superior efficacy than apremilast (30 mg BID). In terms of safety, deucravacitinib or ropsacitinib at any dose did not lead to a higher incidence of AEs than apremilast (30 mg BID). The ranking analysis of efficacy revealed that deucravacitinib 12 mg QD and deucravacitinib 3 mg BID had the highest chance of being the most effective oral treatment, followed by deucravacitinib 6 mg BID and ropsacitinib 400 mg QD.ConclusionsOral TYK2 inhibitors demonstrated satisfactory performance in treating psoriasis, surpassing apremilast at certain doses. More large-scale, long-term studies focusing on novel TYK2 inhibitors are needed.Systematic review registrationPROSPERO (ID: CRD42022384859), available from: https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022384859, identifier CRD42022384859.