Sazzad Hossain, Saiful Islam, Muhammad Ibrahim
et al.
Skin diseases are a major public health concern worldwide, and their detection is often challenging without access to dermatological expertise. In countries like Bangladesh, which is highly populated, the number of qualified skin specialists and diagnostic instruments is insufficient to meet the demand. Due to the lack of proper detection and treatment of skin diseases, that may lead to severe health consequences including death. Common properties of skin diseases are, changing the color, texture, and pattern of skin and in this era of artificial intelligence and machine learning, we are able to detect skin diseases by using image processing and computer vision techniques. In response to this challenge, we develop a publicly available dataset focused on common skin disease detection using machine learning techniques. We focus on five prevalent skin diseases in Bangladesh: Contact Dermatitis, Vitiligo, Eczema, Scabies, and Tinea Ringworm. The dataset consists of 1612 images (of which, 250 are distinct while others are augmented), collected directly from patients at the outpatient department of Faridpur Medical College, Faridpur, Bangladesh. The data comprises of 302, 381, 301, 316, and 312 images of Dermatitis, Eczema, Scabies, Tinea Ringworm, and Vitiligo, respectively. Although the data are collected regionally, the selected diseases are common across many countries especially in South Asia, making the dataset potentially valuable for global applications in machine learning-based dermatology. We also apply several machine learning and deep learning models on the dataset and report classification performance. We expect that this research would garner attention from machine learning and deep learning researchers and practitioners working in the field of automated disease diagnosis.
Background: Allergy immunotherapy targets the immunological cause of allergic rhinoconjunctivitis and allergic asthma and has the potential to alter the natural course of allergic disease. Objective: The primary objective was to investigate the effect of the SQ grass sublingual immunotherapy tablet compared with placebo on the risk of developing asthma. Methods: A total of 812 children (5‐12 years), with a clinically relevant history of grass pollen allergic rhinoconjunctivitis and no medical history or signs of asthma, were included in the randomized, double‐blind, placebo‐controlled trial, comprising 3 years of treatment and 2 years of follow‐up. Results: There was no difference in time to onset of asthma, defined by prespecified asthma criteria relying on documented reversible impairment of lung function (primary endpoint). Treatment with the SQ grass sublingual immunotherapy tablet significantly reduced the risk of experiencing asthma symptoms or using asthma medication at the end of trial (odds ratio = 0.66, P < .036), during the 2‐year posttreatment follow‐up, and during the entire 5‐year trial period. Also, grass allergic rhinoconjunctivitis symptoms were 22% to 30% reduced (P < .005 for all 5 years). At the end of the trial, the use of allergic rhinoconjunctivitis pharmacotherapy was significantly less (27% relative difference to placebo, P < .001). Total IgE, grass pollen–specific IgE, and skin prick test reactivity to grass pollen were all reduced compared to placebo. Conclusions: Treatment with the SQ grass sublingual immunotherapy tablet reduced the risk of experiencing asthma symptoms and using asthma medication, and had a positive, long‐term clinical effect on rhinoconjunctivitis symptoms and medication use but did not show an effect on the time to onset of asthma. Graphical abstract Figure. No caption available.
In Bangladesh, tomatoes are a staple vegetable, prized for their versatility in various culinary applications. However, the cultivation of tomatoes is often hindered by a range of diseases that can significantly reduce crop yields and quality. Early detection of these diseases is crucial for implementing timely interventions and ensuring the sustainability of tomato production. Traditional manual inspection methods, while effective, are labor-intensive and prone to human error. To address these challenges, this research paper sought to develop an automated disease detection system using Convolutional Neural Networks (CNNs). A comprehensive dataset of tomato leaves was collected from the Brahmanbaria district, preprocessed to enhance image quality, and then applied to various deep learning models. Comparative performance analysis was conducted between YOLOv5, MobileNetV2, ResNet18, and our custom CNN model. In our study, the Custom CNN model achieved an impressive accuracy of 95.2%, significantly outperforming the other models, which achieved an accuracy of 77%, 89.38% and 71.88% respectively. While other models showed solid performance, our Custom CNN demonstrated superior results specifically tailored for the task of tomato leaf disease detection. These findings highlight the strong potential of deep learning techniques for improving early disease detection in tomato crops. By leveraging these advanced technologies, farmers can gain valuable insights to detect diseases at an early stage, allowing for more effective management practices. This approach not only promises to boost tomato yields but also contributes to the sustainability and resilience of the agricultural sector, helping to mitigate the impact of plant diseases on crop production.
Multi-disease diagnosis using multi-modal data like electronic health records and medical imaging is a critical clinical task. Although existing deep learning methods have achieved initial success in this area, a significant gap persists for their real-world application. This gap arises because they often overlook unavoidable practical challenges, such as modality missingness, noise, temporal asynchrony, and evidentiary inconsistency across modalities for different diseases. To overcome these limitations, we propose HGDC-Fuse, a novel framework that constructs a patient-centric multi-modal heterogeneous graph to robustly integrate asynchronous and incomplete multi-modal data. Moreover, we design a heterogeneous graph learning module to aggregate multi-source information, featuring a disease correlation-guided attention layer that resolves the modal inconsistency issue by learning disease-specific modality weights based on disease correlations. On the large-scale MIMIC-IV and MIMIC-CXR datasets, HGDC-Fuse significantly outperforms state-of-the-art methods.
Faika Fairuj Preotee, Shuvashis Sarker, Shamim Rahim Refat
et al.
Leaf diseases are harmful conditions that affect the health, appearance and productivity of plants, leading to significant plant loss and negatively impacting farmers' livelihoods. These diseases cause visible symptoms such as lesions, color changes, and texture variations, making it difficult for farmers to manage plant health, especially in large or remote farms where expert knowledge is limited. The main motivation of this study is to provide an efficient and accessible solution for identifying plant leaf diseases in Bangladesh, where agriculture plays a critical role in food security. The objective of our research is to classify 21 distinct leaf diseases across six plants using deep learning models, improving disease detection accuracy while reducing the need for expert involvement. Deep Learning (DL) techniques, including CNN and Transfer Learning (TL) models like VGG16, VGG19, MobileNetV2, InceptionV3, ResNet50V2 and Xception are used. VGG19 and Xception achieve the highest accuracies, with 98.90% and 98.66% respectively. Additionally, Explainable AI (XAI) techniques such as GradCAM, GradCAM++, LayerCAM, ScoreCAM and FasterScoreCAM are used to enhance transparency by highlighting the regions of the models focused on during disease classification. This transparency ensures that farmers can understand the model's predictions and take necessary action. This approach not only improves disease management but also supports farmers in making informed decisions, leading to better plant protection and increased agricultural productivity.
Symptom Checkers (SCs) provide medical information tailored to user symptoms. A critical challenge in SC development is preventing unexpected performance degradation for individual diseases, especially rare diseases, when updating algorithms. This risk stems from the lack of practical pre-deployment evaluation methods. For rare diseases, obtaining sufficient evaluation data from user feedback is difficult. To evaluate the impact of algorithm updates on the diagnostic performance for individual rare diseases before deployment, this study proposes and validates a novel Synthetic Vignette Simulation Approach. This approach aims to enable this essential evaluation efficiently and at a low cost. To estimate the impact of algorithm updates, we generated synthetic vignettes from disease-phenotype annotations in the Human Phenotype Ontology (HPO), a publicly available knowledge base for rare diseases curated by experts. Using these vignettes, we simulated SC interviews to predict changes in diagnostic performance. The effectiveness of this approach was validated retrospectively by comparing the predicted changes with actual performance metrics using the R-squared ($R^2$) coefficient. Our experiment, covering eight past algorithm updates for rare diseases, showed that the proposed method accurately predicted performance changes for diseases with phenotype frequency information in HPO (n=5). For these updates, we found a strong correlation for both Recall@8 change ($R^2$ = 0.83,$p$ = 0.031) and Precision@8 change ($R^2$ = 0.78,$p$ = 0.047). Our proposed method enables the pre-deployment evaluation of SC algorithm changes for individual rare diseases. This evaluation is based on a publicly available medical knowledge database created by experts, ensuring transparency and explainability for stakeholders. Additionally, SC developers can efficiently improve diagnostic performance at a low cost.
With the worldwide spread of the novel severe acute respiratory syndrome coronavirus‐2 (SARS‐CoV‐2) resulting in declaration of a pandemic by the World Health Organization (WHO) on March 11, 2020, the SARS‐CoV‐2‐induced coronavirus disease‐19 (COVID‐19) has become one of the main challenges of our times. The high infection rate and the severe disease course led to major safety and social restriction measures worldwide. There is an urgent need of unbiased expert knowledge guiding the development of efficient treatment and prevention strategies. This report summarizes current immunological data on mechanisms associated with the SARS‐CoV‐2 infection and COVID‐19 development and progression to the most severe forms. We characterize the differences between adequate innate and adaptive immune response in mild disease and the deep immune dysfunction in the severe multiorgan disease. The similarities of the human immune response to SARS‐CoV‐2 and the SARS‐CoV and MERS‐CoV are underlined. We also summarize known and potential SARS‐CoV‐2 receptors on epithelial barriers, immune cells, endothelium and clinically involved organs such as lung, gut, kidney, cardiovascular, and neuronal system. Finally, we discuss the known and potential mechanisms underlying the involvement of comorbidities, gender, and age in development of COVID‐19. Consequently, we highlight the knowledge gaps and urgent research requirements to provide a quick roadmap for ongoing and needed COVID‐19 studies.
Analysis of pre-existing immunity and its effects on acute infection often focus on memory responses associated with a prior infectious exposure. However, memory responses occur in the context of the overall immune state and leukocytes must interact with their microenvironment and other immune cells. Thus, it is important to also consider non-antigen-specific factors which shape the composite basal state and functional capacity of the immune system, termed here as I0 (‘I naught’). In this review, we discuss the determinants of I0. Utilizing influenza virus as a model, we then consider the effect of I0 on susceptibility to infection and disease severity. Lastly, we outline a mathematical framework and demonstrate how researchers can build and tailor models to specific needs. Understanding how diverse factors uniquely and collectively impact immune competence will provide valuable insights into mechanisms of immune variation, aid in screening for high-risk populations, and promote the development of broadly applicable prophylactic and therapeutic treatments.
Kristina K. Gonzales-Wartz, Juliana M. Sá, Kevin Lee
et al.
Abstract Background Aedes and Anopheles mosquitoes are responsible for tremendous global health burdens from their transmission of pathogens causing malaria, lymphatic filariasis, dengue, and yellow fever. Innovative vector control strategies will help to reduce the prevalence of these diseases. Mass rearing of mosquitoes for research and support of these strategies presently depends on meals of vertebrate blood, which is subject to acquisition, handling, and storage issues. Various blood-free replacements have been formulated for these mosquitoes, but none of these replacements are in wide use, and little is known about their potential impact on competence of the mosquitoes for Plasmodium infection. Methods Colonies of Aedes aegypti and Anopheles stephensi were continuously maintained on a blood-free replacement (SkitoSnack; SS) or bovine blood (BB) and monitored for engorgement and hatch rates. Infections of Ae. aegypti and An. stephensi were assessed with Plasmodium gallinaceum and P. falciparum, respectively. Results Replicate colonies of mosquitoes were maintained on BB or SS for 10 generations of Ae. aegypti and more than 63 generations of An. stephensi. The odds of engorgement by SS- relative to BB-maintained mosquitoes were higher for both Ae. aegypti (OR = 2.6, 95% CI 1.3–5.2) and An. stephensi (OR 2.7, 95% CI 1.4–5.5), while lower odds of hatching were found for eggs from the SS-maintained mosquitoes of both species (Ae. aegypti OR = 0.40, 95% CI 0.26–0.62; An. stephensi OR = 0.59, 95% CI 0.36–0.96). Oocyst counts were similar for P. gallinaceum infections of Ae. aegypti mosquitoes maintained on SS or BB (mean ratio = [mean on SS]/[mean on BB] = 1.11, 95% CI 0.85–1.49). Similar oocyst counts were also observed from the P. falciparum infections of SS- or BB-maintained An. stephensi (mean ratio = 0.76, 95% CI 0.44–1.37). The average counts of sporozoites/mosquito showed no evidence of reductions in the SS-maintained relative to BB-maintained mosquitoes of both species. Conclusions Aedes aegypti and An. stephensi can be reliably maintained on SS over multiple generations and are as competent for Plasmodium infection as mosquitoes maintained on BB. Use of SS alleviates the need to acquire and preserve blood for mosquito husbandry and may support new initiatives in fundamental and applied research, including novel manipulations of midgut microbiota and factors important to the mosquito life cycle and pathogen susceptibility. Graphical Abstract
Darlyn Buenaño Vera, Byron Oviedo, Washington Chiriboga Casanova
et al.
The early identification of diseases in cocoa pods is an important task to guarantee the production of high-quality cocoa. The use of artificial intelligence techniques such as machine learning, computer vision and deep learning are promising solutions to help identify and classify diseases in cocoa pods. In this paper we introduce the development and evaluation of a deep learning computational model applied to the identification of diseases in cocoa pods, focusing on "monilia" and "black pod" diseases. An exhaustive review of state-of-the-art of computational models was carried out, based on scientific articles related to the identification of plant diseases using computer vision and deep learning techniques. As a result of the search, EfficientDet-Lite4, an efficient and lightweight model for object detection, was selected. A dataset, including images of both healthy and diseased cocoa pods, has been utilized to train the model to detect and pinpoint disease manifestations with considerable accuracy. Significant enhancements in the model training and evaluation demonstrate the capability of recognizing and classifying diseases through image analysis. Furthermore, the functionalities of the model were integrated into an Android native mobile with an user-friendly interface, allowing to younger or inexperienced farmers a fast and accuracy identification of health status of cocoa pods
Branko Mitic, Philipp Seeböck, Jennifer Straub
et al.
Fast detection of emerging diseases is important for containing their spread and treating patients effectively. Local anomalies are relevant, but often novel diseases involve familiar disease patterns in new spatial distributions. Therefore, established local anomaly detection approaches may fail to identify them as new. Here, we present a novel approach to detect the emergence of new disease phenotypes exhibiting distinct patterns of the spatial distribution of lesions. We first identify anomalies in lung CT data, and then compare their distribution in a continually acquired new patient cohorts with historic patient population observed over a long prior period. We evaluate how accumulated evidence collected in the stream of patients is able to detect the onset of an emerging disease. In a gram-matrix based representation derived from the intermediate layers of a three-dimensional convolutional neural network, newly emerging clusters indicate emerging diseases.
Organ transplantation is the most effective treatment for end stage organ failure, but there are not enough organs to meet burgeoning demand. One potential solution to this organ shortage is xenotransplantation using pig tissues. Decades of progress in xenotransplantation, accelerated by the development of rapid genome editing tools, particularly the advent of CRISPR-Cas9 gene editing technologies, have enabled remarkable advances in kidney and heart xenotransplantation in pig-to-nonhuman primates. These breakthroughs in large animal preclinical models laid the foundation for three recent pig-to-human transplants by three different groups: two kidney xenografts in brain dead recipients deemed ineligible for transplant, and one heart xenograft in the first clinical grade study of pig-to-human transplantation. However, despite tremendous progress, recent data including the first clinical case suggest that gene-modification alone will not overcome all xenogeneic immunologic barriers, and thus an active and innovative immunologic strategy is required for successful xenotransplantation. This review highlights xenogeneic immunologic barriers, advances in gene editing, and tolerance-inducing strategies in pig-to-human xenotransplantation.
Shivangi Rastogi, Sarah Ellinwood, Jacques Augenstreich
et al.
Mycobacterium tuberculosis (Mtb) has evolved to evade host innate immunity by interfering with macrophage functions. Interleukin-1β (IL-1β) is secreted by macrophages after the activation of the inflammasome complex and is crucial for host defense against Mtb infections. We have previously shown that Mtb is able to inhibit activation of the AIM2 inflammasome and subsequent pyroptosis. Here we show that Mtb is also able to inhibit host cell NLRP3 inflammasome activation and pyroptosis. We identified the serine/threonine kinase PknF as one protein of Mtb involved in the NLRP3 inflammasome inhibition, since the pknF deletion mutant of Mtb induces increased production of IL-1β in bone marrow-derived macrophages (BMDMs). The increased production of IL-1β was dependent on NLRP3, the adaptor protein ASC and the protease caspase-1, as revealed by studies performed in gene-deficient BMDMs. Additionally, infection of BMDMs with the pknF deletion mutant resulted in increased pyroptosis, while the IL-6 production remained unchanged compared to Mtb-infected cells, suggesting that the mutant did not affect the priming step of inflammasome activation. In contrast, the activation step was affected since potassium efflux, chloride efflux and the generation of reactive oxygen species played a significant role in inflammasome activation and subsequent pyroptosis mediated by the Mtb pknF mutant strain. In conclusion, we reveal here that the serine/threonine kinase PknF of Mtb plays an important role in innate immune evasion through inhibition of the NLRP3 inflammasome.
Abstract Introduction The HIV Prevention Trials Network (HPTN) 074 study demonstrated a positive effect of an integrated systems navigation and psychosocial counseling intervention on HIV treatment initiation, viral suppression, medication assisted treatment (MAT) enrollment, and risk of death among people who inject drugs (PWID). In this sub-study, we analyzed the incidence, causes, and predictors of death among HIV-infected and uninfected participants. Methods The HPTN 074 randomized clinical trial was conducted in Indonesia, Ukraine, and Vietnam. HIV-infected PWID with unsuppressed viral load (indexes) were recruited together with at least one of their HIV-negative injection partners. Indexes were randomized in a 1:3 ratio to the intervention or standard of care. Results The trial enrolled 502 index and 806 partner participants. Overall, 13% (66/502) of indexes and 3% (19/806) of partners died during follow-up (crude mortality rates 10.4 [95% CI 8.1–13.3] and 2.1 [1.3–3.3], respectively). These mortality rates were for indexes nearly 30 times and for partners 6 times higher than expected in a population of the same country, age, and gender (standardized mortality ratios 30.7 [23.7–39.0] and 5.8 [3.5–9.1], respectively). HIV-related causes, including a recent CD4 < 200 cells/μL, accounted for 50% of deaths among indexes. Among partners, medical conditions were the most common cause of death (47%). In the multivariable Cox model, the mortality among indexes was associated with sex (male versus female aHR = 4.2 [1.5–17.9]), CD4 count (≥ 200 versus < 200 cells/μL aHR = 0.3 [0.2–0.5]), depression (moderate-to-severe versus no/mild aHR = 2.6 [1.2–5.0]) and study arm (intervention versus control aHR = 0.4 [0.2–0.9]). Among partners, the study arm of the index remained the only significant predictor (intervention versus control aHR = 0.2 [0.0–0.9]) while controlling for the effect of MAT (never versus ever receiving MAT aHR = 2.4 [0.9–7.4]). Conclusions The results confirm that both HIV-infected and uninfected PWID remain at a starkly elevated risk of death compared to general population. Mortality related to HIV and other causes can be significantly reduced by scaling-up ART and MAT. Access to these life-saving treatments can be effectively improved by flexible integrated interventions, such as the one developed and tested in HPTN 074.
Sumaya Mustofa, Md Mehedi Hasan Munna, Yousuf Rayhan Emon
et al.
Leaf disease is a common fatal disease for plants. Early diagnosis and detection is necessary in order to improve the prognosis of leaf diseases affecting plant. For predicting leaf disease, several automated systems have already been developed using different plant pathology imaging modalities. This paper provides a systematic review of the literature on leaf disease-based models for the diagnosis of various plant leaf diseases via deep learning. The advantages and limitations of different deep learning models including Vision Transformer (ViT), Deep convolutional neural network (DCNN), Convolutional neural network (CNN), Residual Skip Network-based Super-Resolution for Leaf Disease Detection (RSNSR-LDD), Disease Detection Network (DDN), and YOLO (You only look once) are described in this review. The review also shows that the studies related to leaf disease detection applied different deep learning models to a number of publicly available datasets. For comparing the performance of the models, different metrics such as accuracy, precision, recall, etc. were used in the existing studies.
Ning Zhu, MD, Shanhong Lin, MD, Hang Yu, MD
et al.
Objective: This study was to evaluate the prognostic value of the Naples prognostic score (NPS) in adult patients with asthma. Methods: Data on 44 601 participants from the 1999–2018 National Health and Nutrition Examination Survey (NHANES) were analyzed. The NPS was calculated based on serum albumin, total cholesterol, neutrophil-to-lymphocyte ratio (NLR), and lymphocyte-to-monocyte ratio (LMR), and participants were divided into 3 groups. Self-administered questionnaires were used to collect information on asthma, and mortality was identified using the National Death Index through December 31, 2019. Multiple logistic regressions were used to analyze the relationship between NPS and its components and the prevalence of asthma. Kaplan-Meier survival analysis, Cox proportional regressions, and the random survival forest (RSF) were used to assess the significance of NPS and its components in predicting all-cause and cause-specific (cardiovascular, cancer, and respiratory diseases) mortality in asthma patients. Results: The mean age of the participants was 47.59 ± 0.18 years, and 48.47% were male. The prevalence of asthma was 13.11%. The participants were categorized into 3 groups: 8306 (18.6%) participants were in group 0 (NPS 0), 30 842 (69.2%) were in group 1 (NPS 1 or 2), and 5453 (11.2%) were in group 2 (NPS 3 or 4). Compared to the reference group, participants in group 2 had a higher prevalence of asthma (odds ratio [OR] = 1.40 [1.24–1.56]). Participants with asthma in group 2 had a significantly increased risk of all-cause mortality (hazard ratio [HR] = 2.42 [1.67–3.50]), cardiovascular mortality (HR = 2.68 [1.50–4.79]), cancer mortality (HR = 2.10 [1.00–4.45]), and respiratory disease mortality (HR = 3.00 [1.18–7.65]) compared to those with asthma in group 0. The RSF showed that NPS had the highest value in predicting all-cause mortality in adults with asthma, compared to its components. Conclusions: The results of this study indicate that the NPS is a powerful prognostic indicator for outcomes in asthma patients.
Abstract Objective This study mainly observes changes in perioperative mineral bone metabolism‐related indicators and inflammatory factors in patients with secondary hyperparathyroidism (SHPT), and analyzed the correlation between mineral bone metabolism‐related indicators and inflammatory factors. Methods Clinical data were collected. The study detects mineral bone metabolism‐related indicators and inflammatory factor of perioperative patients with SHPT before and 4 days after operation. The production of high‐sensitivity c‐reactive protein (hs‐CRP) in human hepatocytes cells (LO2 cells) stimulated by different concentrations of parathyroid hormone‐associated protein was detected by enzyme‐linked immunosorbent assay, reverse‐transcription polymerase chain reaction (RT‐PCR), and western blot. Results The levels of mineral bone metabolism‐related indicators and hs‐CRP in SHPT group were significantly higher than those of control group. After operation, serum calcium, serum phosphorus, iPTH, FGF‐23 decreased, and the level of osteoblast active biomarkers increased, while the level of osteoclast active biomarkers decreased. The levels of hs‐CRP decreased significantly after operation. With the increase of PTHrP concentration, hs‐CRP level in supernatant of LO2 cells decreased first and then increased. RT‐PCR and western blot shows the same trend. Conclusion Parathyroidectomy can significantly improve bone resorption and inflammation in SHPT patients. We speculate that there may be an optimal range of PTH concentrations to minimize inflammation in the body.
The continuous emergence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variants with increased transmissibility and profound immune-escape capacity makes it an urgent need to develop broad-spectrum therapeutics. Nanobodies have recently attracted extensive attentions due to their excellent biochemical and binding properties. Here, we report two high-affinity nanobodies (Nb-015 and Nb-021) that target non-overlapping epitopes in SARS-CoV-2 S-RBD. Both nanobodies could efficiently neutralize diverse viruses of SARS-CoV-2. The neutralizing mechanisms for the two nanobodies are further delineated by high-resolution nanobody/S-RBD complex structures. In addition, an Fc-based tetravalent nanobody format is constructed by combining Nb-015 and Nb-021. The resultant nanobody conjugate, designated as Nb-X2-Fc, exhibits significantly enhanced breadth and potency against all-tested SARS-CoV-2 variants, including Omicron sub-lineages. These data demonstrate that Nb-X2-Fc could serve as an effective drug candidate for the treatment of SARS-CoV-2 infection, deserving further in-vivo evaluations in the future.