Identification Of Disease Research Articles

Potato disease detection and control measure recommendation using CNN

Potato cultivation will continue to be a crucial agricultural endeavor, significantly enrich to global food supply. and economic prosperity. However, the ongoing vulnerability of potatoes to diseases, particularly named early Blight and late Blight, will persist as a substantial threat to crop yield and quality. Traditional disease identification methods, reliant on expert visual inspection, are expected to remain time-consuming, error-prone, and inadequate for timely intervention. This paper will outline to find Potato diseases and recommend effective control measures using convolutional Neural-Networks (CNN). The project will adopt an object-oriented methodology to ensure modularity and maintainability, leveraging TensorFlow for comprehensive dataset collection, data cleaning, and model training. TensorFlow Lite will be applied to optimize and quantify the developed model, enhancing the efficiency of the deployment process. The frontend will be crafted with React Native to facilitate user accessibility and seamless interaction. The resulting deep learning technique is anticipated to exhibit high accuracy in identifying early-blight and late-blight in potato plants, enabling users to receive prompt and reliable disease predictions and actionable control suggestions. This innovative approach aims to downgrade crop losses, improve productivity, and foster sustainable agricultural practices, thereby bolstering global food security in the future.

Real-Time Identification of Strawberry Pests and Diseases Using an Improved YOLOv8 Algorithm

Strawberry crops are susceptible to a wide range of pests and diseases, some of which are insidious and diverse due to the shortness of strawberry plants, and they pose significant challenges to accurate detection. Although deep learning-based techniques to detect crop pests and diseases are effective in addressing these challenges, determining how to find the optimal balance between accuracy, speed, and computation remains a key issue for real-time detection. In this paper, we propose a series of improved algorithms based on the YOLOv8 model for strawberry disease detection. These include improvements to the Convolutional Block Attention Module (CBAM), Super-Lightweight Dynamic Upsampling Operator (DySample), and Omni-Dimensional Dynamic Convolution (ODConv). In experiments, the accuracy of these methods reached 97.519%, 98.028%, and 95.363%, respectively, and the F1 evaluation values reached 96.852%, 97.086%, and 95.181%, demonstrating significant improvement compared to the original YOLOv8 model. Among the three improvements, the improved model based on CBAM has the best performance in training stability and convergence, and the change in each index is relatively smooth. The model is accelerated by TensorRT, which achieves fast inference through highly optimized GPU computation, improving the real-time identification of strawberry diseases. The model has been deployed in the cloud, and the developed client can be accessed by calling the API. The feasibility and effectiveness of the system have been verified, providing an important reference for the intelligent research and application of strawberry disease identification.

Identification of Grape Plant Diseases Based on the Leaves using Naïve Bayes

Identification of Grape Plant Diseases Based on the Leaves using Naïve Bayes

Chemical sensors: From fundamentals to the future—A review

<p>Chemical sensors bridge the gap between the chemical and electrical/optical domains, offering a powerful tool for analyzing our environment. These ingenious devices, with detection limits reaching parts-per-billion (ppb) for some analytes, rely on interactions between a specific material and the target molecule. This interaction, which can involve changes in electrical current, light emission, or mass, is translated into a measurable signal. This review delves into the core working principles of various sensor types, highlighting their diverse applications. From environmental monitoring (tracking air and water pollutants at concentrations as low as 10 ppb) to medical diagnostics (detecting biomarkers for early disease identification), chemical sensors play a crucial role in shaping a safer and healthier future. Recent advancements, such as miniaturization and integration with nanomaterials, promise even greater sensitivity, portability, and affordability, paving the way for a new era of sensor-driven innovation. This review article explores these advancements and their potential impact on various fields, inspiring further development and exploration of this transformative technology.</p>

Machine Learning-based Prediction of African Swine Fever (ASF) in Pigs

African Swine Fever (ASF) is a contiguous viral disease of the pig with serious economic threats to the pork industry. Early identification of ASF infection is important to support sustainable developments in the ASF industry. There is also a need for a solution to identify the ASF infection as early as possible based on apparent symptoms of ASF to screen the infected animals, that are not targeted in the existing literature. Many machine learning (ML) solutions have been proposed in recent years for the prediction and identification of human, animal, and plant diseases. To deal with ASF in pigs ML-assisted model is proposed for the early identification of ASF infection without medical diagnosis and expert opinion. The data regarding apparent symptoms are collected from Chinese small pig farms. The loss of appetite, weakness, diarrhea, vomiting, coughing, skin redness, and breathing difficulty levels are taken as major apparent symptoms of ASF infection. Moreover, different ML models are also evaluated for their performance in the prediction of ASF infection based on selected apparent symptoms of ASF infection. In this regard, Support Vector Machine (SVM), K-Nearest Neighbor (k-NN), Decision Tree (DT), Random Forests (RF), and Gaussian Naïve Bayes ML models are evaluated for ASF infection prediction. The implementation of the proposed solution reveals that the GNB model is more accurate as compared to the other evaluated models for the identification of ASF infection from the apparent ASF symptoms in infected pig animals, with 94.31\% accuracy. The proposed solution would be very effective in the early screening of ASF-infected pig animals without medical diagnosis and expert judgment.

Unraveling the Relationship between Soil Nutrients and Maize Leaf Disease Occurrences in Mopani District Municipality, Limpopo Province, South Africa

Maize is a staple crop important for food security that millions globally depend upon as an energy source, primarily due to its high starch and fat content. For growth and disease resistance, maize production requires a balanced intake of essential nutrients, including nitrogen (N), phosphorus (P) and potassium (K). This study investigated the relationship between soil nutrient levels and maize disease occurrences in the Mopani District Municipality, Limpopo Province, South Africa. Soil and maize leaves were collected using a systematic sampling approach. Grids of 10 × 10 m were created, covering a maize field. Forty soil samples were collected a day before the planting date and sent to the laboratory for analysis of N, P and K. During the tasseling stage of the maize plant, 40 maize leaf samples were collected and sent to the laboratory for disease identification. Maize leaves were classified as healthy, southern corn leaf blight (Bipolaris maydis), northern corn leaf blight (Exserohilum turcicum), maize streak disease (Maize streak virus), nitrogen-deficient or phosphorus-deficient. Generalized Linear Models (GLMs) with a corrected Akaike Information Criterion (AICc) showed a significant relationship between low soil nutrient levels of N, P and K and maize disease occurrence (p < 0.0001). The interaction of the N*P*K model had the lowest AIC value (AICc = 28.53), indicating the necessity of considering synergistic effects in maize disease management. All the model performances had a delta AICc = 0. These findings highlight the significance of comprehensive soil management strategies in enhancing the disease resistance, well-being and yields of maize crops.

Cognitive impairments in autoimmune encephalitis: the role of autoimmune antibodies and oligoclonal bands.

The presence of oligoclonal bands (OCBs) in cerebrospinal fluid (CSF) is a pivotal diagnostic marker for multiple sclerosis (MS). These bands play a crucial role in the diagnosis and understanding of a wide array of immune diseases. In this study, we explore the relationship between the cognitive profile of autoimmune encephalitis (AIE) and the presence of OCBs in CSF, with a particular emphasis on NMDA receptor antibodies. We studied a cohort of 21 patients across five tertiary centers, segregated into two distinct categories. One group comprised individuals who tested positive only for autoimmune encephalitis antibodies indicative of encephalitis, while the other group included patients whose CSF was positive for both autoimmune encephalitis antibodies and OCBs. Our investigation focused primarily on cognitive functions and behavioral alterations, supplemented by auxiliary diagnostic assessments such as CSF cell count, magnetic resonance imaging (MRI), and electroencephalogram (EEG) results, evaluated for the two patient groups. To validate our findings, we employed statistical analyses such as Fisher's exact test with Benjamini-Hochberg correction. Our study included 21 patients, comprising 14 who were presented with only autoimmune encephalitis antibodies, and 7 who were dual-positive. Among these patients, we focused on those with NMDA receptor antibodies. Of these, five were dual positive, and nine were positive only for NMDA receptor antibodies. The dual-positive NMDA group, with an average age of 27 ± 16.47 years, exhibited significantly higher CSF cell counts (p=0.0487) and more pronounced language and attention deficits (p= 0.0264). MRI and EEG results did not differ significantly between the groups. Our results point to OCBs as an additional marker of disease severity in AIE, especially in NMDA receptor-antibody positive patients, possibly indicating a broader inflammatory process, as reflected in elevated CSF lymphocytes. Regular testing for OCBs in cases of suspected AIE may aid in disease prognosis and identification of patients more prone to language and attention disorders, improving diagnosis and targeting treatment for these cognitive aspects.

Population Heterogeneity and Selection of Coronary Artery Disease Polygenic Scores.

The identification of coronary artery disease (CAD) high-risk individuals is a major clinical need for timely diagnosis and intervention. Many different polygenic scores (PGSs) for CAD risk are available today to estimate the genetic risk. It is necessary to carefully choose the score to use, in particular for studies on populations, which are not adequately represented in the large datasets of European biobanks, such as the Italian one. This work aimed to analyze which PGS had the best performance within the Italian population. We used two Italian independent cohorts: the EPICOR case-control study (576 individuals) and the Atherosclerosis, Thrombosis, and Vascular Biology (ATVB) Italian study (3359 individuals). We evaluated 266 PGS for cardiovascular disease risk from the PGS Catalog, selecting 51 for CAD. Distributions between patients and controls were significantly different for 49 scores (p-value < 0.01). Only five PGS have been trained and tested for the European population specifically. PGS003727 demonstrated to be the most accurate when evaluated independently (EPICOR AUC = 0.68; ATVB AUC = 0.80). Taking into account the conventional CAD risk factors further enhanced the performance of the model, particularly in the ATVB study (p-value = 0.0003). European CAD PGS could have different risk estimates in peculiar populations, such as the Italian one, as well as in various geographical macro areas. Therefore, further evaluation is recommended for clinical applicability.

Analysis of existing techniques for image-based recognition of agricultural crops diseases

An analysis of existing methods for processing and identifying the disease of agricultural crops was carried out. Other methods for identifying informative regions, including Fourier transformation, k-means clustering, Histogram Equalization, Scale-Invariant Feature Transform (SIFT), Local Binary Patterns (LBP), Histogram of Oriented Gradients (HOG) algorithms, as well as their combinations were reviewed. The studied approaches demonstrated high accuracy in the identification and classification of various plant diseases. The study examined hybrid models, such as, for example, logistic regression with decision trees and Extreme Learning Machines (ELM). The accuracy of the Support Vector Machine (SVM), ELM, and Decision Trees algorithms were compared, convinced, that the importance of choosing the right parameters and fine-tuning to improve accuracy is important. The methods of deep learning such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) and their usage in the scope of the image recognition, which are also used for disease recognition, were examined. The recognition accuracy of several CNN models was compared: DenseNet121, MobileNetV2, NASNetMobile and EfficientNetB0, and the last demonstrated the best results. The modification of ready-made architectures, including the architecture of the EfficientNetB0 neural network, has been analyzed as a way of adapting existing models to specific recognition requirements.

Real-time field disease identification based on a lightweight model

In the field of agricultural technology, rapid and accurate diagnosis of crop diseases is crucial for ensuring crop health and yield. However, most methods for automatic diagnosis of plant diseases are primarily based on high-computational-performance server platforms, which limits their application in real-world environments. This paper establishes a crop disease dataset collected from real field scenarios, which is utilized for training, validating the proposed models, and enhancing model generalization in existing research. It provides an accurate and practical database for future research endeavors. The key innovation of this study lies in the development of a lightweight convolutional neural network architecture with high real-time capabilities, characterized by its high precision and efficiency. The network abandons traditional deep convolution, adopting partial convolution and point-wise convolution techniques instead. This approach significantly reduces computational complexity while maintaining high accuracy, making the model highly suitable for application in resource-constrained real-time environments. The proposed method achieved an accuracy of 99.04 % on the open-source PlantVillage dataset and 92.82 % accuracy on a dataset with complex backgrounds constructed. Additionally, this paper also investigates the deployment of the proposed method and other mature technologies on mobile platforms. The focus of this evaluation is to compare the real-time performance on devices with limited computational resources, thereby verifying the model’s applicability in the real world.

In Vivo Raman Spectroscopy of Muscle Is Highly Sensitive for Detection of Healthy Muscle and Highly Specific for Detection of Disease.

Raman spectroscopy of muscle provides a molecular fingerprint to identify the disease. Previous work has demonstrated effectiveness in differentiating between two groups of equal sizes (e.g., healthy vs disease) but imbalanced multiclass scenarios are more common in medicine. We performed in vivo Raman spectroscopy in a total of 151 mice across four different histopathologies (healthy, acute myopathy, chronic myopathy, neurogenic), with variable numbers in each (class "imbalance"). Using hierarchical modeling and synthetic data generation, we demonstrate high sensitivity (94%) for detection of healthy muscle and high specificity (≥97%) for disease. Further, we demonstrate the potential for unique biomarker development by demonstrating variations in the protein structure across different pathologies. The findings demonstrate the potential of Raman spectroscopy to provide accurate disease identification and unique molecular insights.

Implementing Stacking with Cross - Validation for Heart Disease Prediction.

The objective of this work is to apply machine learning techniques for the prediction and early identification of cardiovascular disease, a major worldwide health problem. XGBoost, K-nearest neighbors (KNN), decision tree (DT), support vector machine (SVM), and StackingCVClassifier were among the ensemble algorithms used to anticipate cardiac disease using a dataset that came from the UCI ML database. To improve the quality of the data, an exploratory data analysis was performed on the dataset using methods including outlier identification and missing value imputation. Stacking CV Classifier attained the best accuracy rate of 92.20%, according to a comparative examination of pre-processing and post-processing findings. When compared to previous approaches, the suggested strategies performed better in terms of accuracy, recall, and f1-score. Moreover, the flexibility of the model indicates its possible application to other illnesses with comparable features.

Shared decision-making and detection of comorbidities in an online acromegaly consultation with and without the Acromegaly Disease Activity Tool ACRODAT® using the simulated person approach

ObjectiveA patient-centered approach to the management of acromegaly includes disease activity control, shared decision-making and identification of comorbidities. The Acromegaly Disease Activity Tool (ACRODAT®) is intended to assist physicians in providing such holistic management. The present study investigated this claim using the simulated person (SP) approach.MethodsWe studied patient-doctor interaction via online video consultation in a randomized prospective study design with SPs trained to simulate a specific acromegaly profile. We analyzed the proportion of conversation time devoted to health content and the specific acromegaly and comorbidity relevant categories mentioned in the conversation. We collected physicians’ feedback on the usefulness of ACRODAT®, SPs subjective perception of the quality of the conversation and compared consultations with and without ACRODAT® using a qualitative approach.ResultsThe sample (N = 30) consisted of endocrinologists treating patients with acromegaly in Germany. For SP-physician interactions (N = 60), the proportion of time spent on conversation content (e.g. IGF-I, quality of life) was distributed according to the focus of the patient profile. Comorbidities were less well identified than the need for a change in therapy. Only 18.3% of the SPs were actively asked to participate in the decision-making process. ACRODAT® did not lead to any significant differences in the course of the discussion.ConclusionsShared decision-making was underrepresented in this SP-physician interaction in acromegaly management. Physicians adapted the content of the discussion to the SP’s needs, but did not adequately address comorbidities. According to the analysis criteria used, ACRODAT® did not contribute to a more holistic patient management in the present study.

Effect of Intranasal Insulin on Olfactory Recovery in Patients with Anosmia .

Olfactory dysfunction, defined as either a complete or partial impairment of smell, is a common condition that may substantially affect a person’s quality of life and is frequently difficult to treat. Physical activity, heredity, nutrition, smoking, head trauma, medical treatments, and virus exposure all influence one’s capacity to smell. Hyposmia or anosmia, or loss of smell, affects 3% to 20% of the population. Intranasal insulin can improve cognitive performance, reduce food intake, and boost olfactory thresholds in healthy individuals. As people age, they are more likely to experience olfactory dysfunction, which may be affected by a variety of reasons, such as acute and chronic sino-nasal illness, upper respiratory infections, toxic chemical exposure, and degenerative diseases. About ten percent of those over 65 develop olfactory impairment, which can range from mild loss to total anosmia. Insulin resistance in the central nervous system has been linked to conditions like type II diabetes, Alzheimer’s disease, obesity, and poor odor identification. Reduced odor perception may contribute to reduced olfactory function in anosmic patients.

Plant Disease Identification Based on Encoder–Decoder Model

Plant Disease Identification Based on Encoder–Decoder Model

EarMonitor: Non-clinical Assessment of Ear Health Conditions Using a Low-cost Endoscope Camera on Smartphones

Hearing loss affects 20% of the global population, a rate that is increasing dramatically as the world's population ages. Early prevention and identification of ear diseases can significantly reduce the risk of becoming disabled with hearing impairment. We propose EarMonitor, an interactive, vision-based ear health monitoring system that enables users to examine their ear conditions with a low-cost hand-held endoscope. EarMonitor can detect six ear health conditions suitable for self-assessment. It can particularly recognize complications from ear diseases, helping users better understand the results. In the wild, our computer vision algorithm achieves a detection sensitivity of 0.949 for earwax buildup and blockage in 100 external auditory canal photos; our deep learning model achieves an average detection sensitivity of 0.861 for the other five conditions considering complications in 350 tympanic membrane photos. We validated EarMonitor 's effectiveness through a user study involving 17 participants and two experts, leading to valuable insights regarding the design and interpretation of non-clinical assessment devices.

Chinese expert consensus on cardiac biomarkers for monitoring and management of cardiovascular toxicity in cancer therapy (2024 edition)

In recent years, the treatment of malignant tumors has continually advanced, significantly extending the survival period of cancer patients. Tumors are increasingly present as chronic diseases over the long term, and the cardiovascular toxicity associated with cancer treatment has become increasingly prominent, severely affecting the effective treatment and survival of cancer patients. As a result, cardio-oncology has gained considerable attention as an emerging discipline. However, cardiovascular diseases in cancer patients often have an insidious onset, and early identification and treatment are frequently overlooked. Throughout the course of cancer treatment, it is crucial to reasonably apply cardiac biomarkers for risk stratification, early identification, and screening of cardiovascular diseases in patients, as well as to improve the early diagnosis and treatment levels of cardiovascular diseases in cancer patients. To this end, Cardio-Oncology Group, Chinese Society of Cardiology in conjunction with Cardiovascular Expert Committee, China Medical Doctor Association of Laboratory Medicine, organized experts in relevant fields to compile this consensus. It aims to provide a basis for clinicians to standardize the screening and management of cardiovascular toxicity related to cancer treatment through the reasonable application of cardiac biomarkers.

Research on a Method for Identification of Peanut Pests and Diseases Based on a Lightweight LSCDNet Model.

Timely and accurate identification of peanut pests and diseases, coupled with effective countermeasures, is pivotal for ensuring high-quality and efficient peanut production. Despite the prevalence of pests and diseases in peanut cultivation, challenges such as minute disease spots, the elusive nature of pests, and intricate environmental conditions often lead to diminished identification accuracy and efficiency. Moreover, continuous monitoring of peanut health in real-world agricultural settings demands solutions that are computationally efficient. Traditional deep learning models often require substantial computational resources, limiting their practical applicability. In response to these challenges, we introduce LSCDNet (Lightweight Sandglass and Coordinate Attention Network), a streamlined model derived from DenseNet. LSCDNet preserves only the transition layers to reduce feature map dimensionality, simplifying the model's complexity. The inclusion of a sandglass block bolsters features extraction capabilities, mitigating potential information loss due to dimensionality reduction. Additionally, the incorporation of coordinate attention addresses issues related to positional information loss during feature extraction. Experimental results showcase that LSCDNet achieved impressive metrics with accuracy, precision, recall, and Fl score of 96.67, 98.05, 95.56, and 96.79%, respectively, while maintaining a compact parameter count of merely 0.59 million. When compared with established models such as MobileNetV1, MobileNetV2, NASNetMobile, DenseNet-121, InceptionV3, and X-ception, LSCDNet outperformed with accuracy gains of 2.65, 4.87, 8.71, 5.04, 6.32, and 8.2%, respectively, accompanied by substantially fewer parameters. Lastly, we deployed the LSCDNet model on Raspberry Pi for practical testing and application and achieved an average recognition accuracy of 85.36%, thereby meeting real-world operational requirements.

Exploring a role for community pharmacists in the identification of alcohol-related liver disease: a qualitative interview study with professionals, patients, and the public.

To explore the views and attitudes of professionals, patients and the public to a role for community pharmacists in the identification of alcohol-related liver disease (ArLD). Semi-structured interviews were conducted with a purposive sample of patients with ArLD, members of the public, pharmacy staff, and clinicians managing patients with ArLD across the Wessex region of south England. The interviews explored experiences of alcohol, ArLD and health advice in pharmacies and elicited views of what a pharmacist role in identifying ArLD could entail and factors influencing this. Transcripts were analysed using reflexive thematic analysis. Twenty-six participants were interviewed and three themes were generated: (i) acknowledging, seeking help and engaging with a hidden problem; (ii) professional roles, boundaries and attributes; (iii) communication, relationships, collaboration and support. Participants reported key challenges to identifying people at-risk of ArLD. Offering testing for ArLD was perceived to motivate engagement but there were concerns about pharmacists performing this. A role was mostly seen to be finding people at-risk and engaging them with further care such as referral to liver services. This was perceived to require developing interprofessional collaborations, remuneration and training for pharmacy staff, and community-based liver testing. Professionals, patient and public participants recognized a role for pharmacists in the identification of ArLD. This was envisaged to incorporate educating pharmacy users about ArLD risk, and identifying and directly engaging those at-risk with liver and support services through development of interprofessional collaborations. The findings of this study support and can inform future work to develop this role.

Post-transcriptional regulation of IFI16 promotes inflammatory endothelial pathophenotypes observed in pulmonary arterial hypertension.

Pulmonary arterial hypertension (PAH) is a progressive disease driven by endothelial cell inflammation and dysfunction, resulting in the pathological remodeling of the pulmonary vasculature. Innate immune activation has been linked to PAH development; however, the regulation, propagation, and reversibility of the induction of inflammation in PAH is poorly understood. Here, we demonstrate a role for interferon inducible protein 16 (IFI16), an innate immune sensor, as a modulator of endothelial inflammation in pulmonary hypertension, utilizing human pulmonary artery endothelial cells (PAECs). Inflammatory stimulus of PAECs with IL-1β up-regulates IFI16 expression, inducing proinflammatory cytokine up-regulation and cellular apoptosis. IFI16 mRNA stability is regulated by post-transcriptional m6A modification, mediated by Wilms' tumor 1-associated protein (WTAP), a structural stabilizer of the methyltransferase complex, via regulation of m6A methylation of IFI16. Additionally, m6A levels are increased in the peripheral blood mononuclear cells of PAH patients compared to control, indicating that quantifying this epigenetic change in patients may hold potential as a biomarker for disease identification. In summary, our study demonstrates IFI16 mediates inflammatory endothelial pathophenotypes seen in pulmonary arterial hypertension.