Current Technologies for Detection of COVID-19: Biosensors, Artificial Intelligence and Internet of Medical Things (IoMT): Review

Classification of H. pylori Infection from Histopathological Images Using Deep Learning

Helicobacter pylori (H. pylori) is a widespread pathogenic bacterium, impacting over 4 billion individuals globally. It is primarily linked to gastric diseases, including gastritis, peptic ulcers, and cancer. The current histopathological method for diagnosing H. pylori involves labour-intensive examination of endoscopic biopsies by trained pathologists. However, this process can be time-consuming and may occasionally result in the oversight of small bacterial quantities. Our study explored the potential of five pre-trained models for binary classification of 204 histopathological images, distinguishing between H. pylori-positive and H. pylori-negative cases. These models include EfficientNet-b0, DenseNet-201, ResNet-101, MobileNet-v2, and Xception. To evaluate the models' performance, we conducted a five-fold cross-validation, ensuring the models' reliability across different subsets of the dataset. After extensive evaluation and comparison of the models, ResNet101 emerged as the most promising. It achieved an average accuracy of 0.920, with impressive scores for sensitivity, specificity, positive predictive value, negative predictive value, F1 score, Matthews's correlation coefficient, and Cohen's kappa coefficient. Our study achieved these robust results using a smaller dataset compared to previous studies, highlighting the efficacy of deep learning models even with limited data. These findings underscore the potential of deep learning models, particularly ResNet101, to support pathologists in achieving precise and dependable diagnostic procedures for H. pylori. This is particularly valuable in scenarios where swift and accurate diagnoses are essential.

Expert consensus on One Health for establishing an enhanced and integrated surveillance system for key infectious diseases

China has been continuously improving its monitoring methods and strategies to address key infectious diseases (KIDs). After the severe acute respiratory syndrome epidemic in 2003, China established a comprehensive reporting system for infectious diseases (IDs) and public health emergencies. The relatively lagging warning thresholds, limited warning information, and outdated warning technology are insufficient to meet the needs of comprehensive monitoring for modern KIDs. Strengthening early monitoring and warning capabilities to enhance the public health system has become a top priority, with increasing demand for early warning thresholds, information, and techniques, thanks to constant innovation and development in molecular biology, bioinformatics, artificial intelligence, and other identification and analysis technologies. A panel of 31 experts has recommended a fourth-generation comprehensive surveillance system targeting KIDs (41 notifiable diseases and emerging IDs). The aim of this surveillance system is to systematically monitor the epidemiology and causal pathogens of KIDs in hosts such as humans, animals, and vectors, along with associated environmental pathogens. By integrating factors influencing epidemic spread and risk assessment, the surveillance system can serve to detect, predict, and provide early warnings for the occurrence, development, variation, and spread of known or novel KIDs. Moreover, we recommend comprehensive ID monitoring based on the fourth-generation surveillance system, along with a data-integrated monitoring and early warning platform and a consortium pathogen detection technology system. This series of considerations is based on systematic and comprehensive monitoring across multiple sectors, dimensions, factors, and pathogens that is supported by data integration and connectivity. This expert consensus will provides an opportunity for collaboration in various fields and relies on interdisciplinary application to enhance comprehensive monitoring, prediction, and early warning capabilities for the next generation of ID surveillance. This expert consensus will serve as a reference for ID prevention and control as well as other related activities.

Recent Advances of Food Hazard Detection Based on Artificial Nanochannel Sensors

Food quality and safety are related to the health and safety of people, and food hazards are important influencing factors affecting food safety. It is strongly necessary to develop food safety rapid detection technology to ensure food safety. As a new detection technology, artificial nanochannel-based electrochemical and other methods have the advantages of being real-time, simple, and sensitive and are widely used in the detection of food hazards. In this paper, we review artificial nanochannel sensors as a new detection technology in food safety for different types of food hazards: biological hazards (bacteria, toxins, viruses) and chemical hazards (heavy metals, organic pollutants, food additives). At the same time, we critically discuss the advantages and disadvantages of artificial nanochannel sensor detection, as well as the restrictions and solutions of detection, and finally look forward to the challenges and development prospects of food safety detection technology based on the limitations of artificial nanochannel detection. We expect to provide a theoretical basis and inspiration for the development of rapid real-time detection technology for food hazards and the production of portable detection equipment in the future.

Green Synthesis of Ceria Nanoparticles from Cassava Tubers for Electrochemical Aptasensor Detection of SARS-CoV-2 on a Screen-Printed Carbon Electrode

Green synthesis approaches for making nanosized ceria using starch from cassava as template molecules to control the particle size are reported. The results of the green synthesis of ceria with an optimum calcination temperature of 800 °C shows a size distribution of each particle of less than 30 nm with an average size of 9.68 nm, while the ratio of Ce3+ to Ce4+ was 25.6%. The green-synthesized nanoceria are applied to increase the sensitivity and attach biomolecules to the electrode surface of the electrochemical aptasensor system for coronavirus disease (COVID-19). The response of the aptasensor to the receptor binding domain of the virus was determined with the potassium ferricyanide redox system. The screen-printed carbon electrode that has been modified with green-synthesized nanoceria shows 1.43 times higher conductivity than the bare electrode, while those modified with commercial ceria increase only 1.18 times. Using an optimized parameter for preparing the aptasensors, the detection and quantification limits were 1.94 and 5.87 ng·mL-1, and the accuracy and precision values were 98.5 and 89.1%. These results show that green-synthesized ceria could be a promising approach for fabricating an electrochemical aptasensor.

Smartphone-based device for point-of-care diagnostics of pulmonary inflammation using convolutional neural networks (CNNs)

In pulmonary inflammation diseases, like COVID-19, lung involvement and inflammation determine the treatment regime. Respiratory inflammation is typically arisen due to the cytokine storm and the leakage of the vessels for immune cells recruitment. Currently, such a situation is detected by the clinical judgment of a specialist or precisely by a chest CT scan. However, the lack of accessibility to the CT machines in many poor medical centers as well as its expensive service, demands more accessible methods for fast and cheap detection of lung inflammation. Here, we have introduced a novel method for tracing the inflammation and lung involvement in patients with pulmonary inflammation, such as COVID-19, by a simple electrolyte detection in their sputum samples. The presence of the electrolyte in the sputum sample results in the fern-like structures after air-drying. These fern patterns are different in the CT positive and negative cases that are detected by an AI application on a smartphone and using a low-cost and portable mini-microscope. Evaluating 160 patient-derived sputum sample images, this method demonstrated an interesting accuracy of 95%, as confirmed by CT-scan results. This finding suggests that the method has the potential to serve as a promising and reliable approach for recognizing lung inflammatory diseases, such as COVID-19.

COVID-19 Severity Prediction from Chest X-ray Images Using an Anatomy-Aware Deep Learning Model

The COVID-19 pandemic has been adversely affecting the patient management systems in hospitals around the world. Radiological imaging, especially chest x-ray and lung Computed Tomography (CT) scans, plays a vital role in the severity analysis of hospitalized COVID-19 patients. However, with an increasing number of patients and a lack of skilled radiologists, automated assessment of COVID-19 severity using medical image analysis has become increasingly important. Chest x-ray (CXR) imaging plays a significant role in assessing the severity of pneumonia, especially in low-resource hospitals, and is the most frequently used diagnostic imaging in the world. Previous methods that automatically predict the severity of COVID-19 pneumonia mainly focus on feature pooling from pre-trained CXR models without explicitly considering the underlying human anatomical attributes. This paper proposes an anatomy-aware (AA) deep learning model that learns the generic features from x-ray images considering the underlying anatomical information. Utilizing a pre-trained model and lung segmentation masks, the model generates a feature vector including disease-level features and lung involvement scores. We have used four different open-source datasets, along with an in-house annotated test set for training and evaluation of the proposed method. The proposed method improves the geographical extent score by 11% in terms of mean squared error (MSE) while preserving the benchmark result in lung opacity score. The results demonstrate the effectiveness of the proposed AA model in COVID-19 severity prediction from chest X-ray images. The algorithm can be used in low-resource setting hospitals for COVID-19 severity prediction, especially where there is a lack of skilled radiologists.

Smart Graphene-Based Electrochemical Nanobiosensor for Clinical Diagnosis: Review

The technological improvement in the field of physics, chemistry, electronics, nanotechnology, biology, and molecular biology has contributed to the development of various electrochemical biosensors with a broad range of applications in healthcare settings, food control and monitoring, and environmental monitoring. In the past, conventional biosensors that have employed bioreceptors, such as enzymes, antibodies, Nucleic Acid (NA), etc., and used different transduction methods such as optical, thermal, electrochemical, electrical and magnetic detection, have been developed. Yet, with all the progresses made so far, these biosensors are clouded with many challenges, such as interference with undesirable compound, low sensitivity, specificity, selectivity, and longer processing time. In order to address these challenges, there is high need for developing novel, fast, highly sensitive biosensors with high accuracy and specificity. Scientists explore these gaps by incorporating nanoparticles (NPs) and nanocomposites (NCs) to enhance the desired properties. Graphene nanostructures have emerged as one of the ideal materials for biosensing technology due to their excellent dispersity, ease of functionalization, physiochemical properties, optical properties, good electrical conductivity, etc. The Integration of the Internet of Medical Things (IoMT) in the development of biosensors has the potential to improve diagnosis and treatment of diseases through early diagnosis and on time monitoring. The outcome of this comprehensive review will be useful to understand the significant role of graphene-based electrochemical biosensor integrated with Artificial Intelligence AI and IoMT for clinical diagnostics. The review is further extended to cover open research issues and future aspects of biosensing technology for diagnosis and management of clinical diseases and performance evaluation based on Linear Range (LR) and Limit of Detection (LOD) within the ranges of Micromolar µM (10^-6), Nanomolar nM (10^-9), Picomolar pM (10^-12), femtomolar fM (10^-15), and attomolar aM (10^-18).