Covid-19 classification using CNN with radiography image data set

COVID-19 is a novel coronavirus disease that has been reported in Wuhan, China since late December 2019 and has subsequently spread around the world. In severe cases of illness, there may be no option but to die due to substantial alveolar damage and progressive respiratory failure. Testing with RT-PCR, for instance, is the gold standard for clinical diagnosis, but it is possible for the tests to produce false negatives. Further, the lack of resources for conducting RT-PCR testing may deter the next clinical decision and treatment under the pandemic situation. As a result, chest CT imaging has become a valuable tool for diagnostic and prognostic purposes in COVID-19 patients. Detection of COVID-19 early enables the development of prevention plans and a disease control plan. Through this experimentation, the main objective is to utilize transfer learning to leverage pre-trained weights from CNNs. We propose the ResNet50 architecture based on the ImageNet pre-trained weights to detect the Covid-19. The proposed model is evaluated on X-ray images of COVID-19 chests and on images taken with a Computerized Tomography scanner. Using the 746 images of covid and non-covid patient datasets are bifurcated into train and test datasets for training and validate our model and achieved 84.90 % model accuracy. The Accuracy, precision, recall and F1-Scores are presented along with the receiver operating characteristic (ROC) curve, the precision-recall curve, the average prediction, and the confusion matrix of three distinct models. © 2022 IEEE.

Detection of SARS-CoV-2 by RT-LAMP assay in Human COVID-19 patients

Background: The novel COVID-19 outbreak has infected human population all around the world. Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) diagnosis in a rapid manner remains challenging for health care professionals. Currently, RT-qPCR technique is extensively practiced in SARS-CoV-2 diagnosis and is considered as gold standard. The constraints of RT-qPCR, high cost and need for trained technician, longer detection time, highlighted the need for alternate healthcare diagnostic approaches. They follow the WHO assured standard and offer the health-care sector optimism. One of them is the Loop Mediated isothermal amplification system (LAMP). There is no need for costly equipment like thermal cycler since LAMP assay is performed at a fixed temperature. It can also be implemented as a point of care testing device. RT-LAMP is one of the extensively used isothermal amplification system in pathogen diagnostics.Aims: The current study aims to validate and standardize RT-LAMP assay for rapid diagnosis of SARS-CoV-2 in both lab and field conditions. The reactions can be carried out using a heating vessel including the use of a water bath and end-point detection by colorimetry. A rising middle ground of tiny, more portable technology, that provides most of the capability at less cost and time.Methods and Results: 20 Samples were taken from COVID-19 positive patients. RNA extraction from COVID-19 samples was followed up by one-step reverse transcription and loop-mediated isothermal amplification (LAMP). LAMP primers were designed to amplify the conserved regions of SARS-COV-2 specific genes. The target regions for primer design were selected after genome-wide sequence alignment of SARS-CoV-2 strains isolated in various regions of the world i.e., Europe, Africa, Asia, and North America. RT-LAMP assays were performed at the specific incubation temperature (60°C) for 50 minutes. Assay was optimized as per consumable compatibility, COVID template integrity, primer concentration, template concentration, primer ratio, testing time etc. Sensitivity and specificity of the assay was elucidated. Finally, different end-point analysis i.e., Agarose Gel Electrophoresis and Colorimetry have been used to interpret the results.Conclusion: RT-LAMP assay has shown to be a quick and accurate diagnostic method that can be put to use for SARS-CoV-2 detection in laboratories and Point-of- Care settings. © 2022 IEEE.

A New Low-Cost and Accurate Diagnostic mHealth System for Patients with COVID-19 Pneumonia

Over the last two years, COVID-19 pneumonia has killed more than six million people worldwide. To self-triage pneumonia patients, many mobile Health (mHealth) solutions have been developed. Some of these solutions only provide guidelines and trace outbreaks. Others collect inaccurate vitals and/or are considered costly. To address these challenges, a cost-effective and accurate mHealth system was designed in this paper. The system consists of several biosensors (e.g., oxygen saturation) as they are considered significant for the disease assessment. In addition, a new mobile application was developed to collect biometric vitals and transmit them to a HIPPA compliant server. Our real-world experiments demonstrated that the new system was strongly correlated with the gold standard systems in terms of pulse rate and temperature (e.g., 90%). Moreover, the difference in the rate of change between the two systems for the measurements were mostly insignificant (e.g., p-value ≈ 0.77). Lastly, the prototype cost is approximately 20 USD. © 2022 IEEE.

PCR, Tropical Arithmetic, and Group Testing

Polymerase chain reaction (PCR) testing is the gold standard for diagnosing COVID-19. Unfortunately, the outputs of these tests are imprecise and therefore quantitative group testing methods, which rely on precise measurements, are not applicable. Motivated by the ever-increasing demand to identify individuals infected with SARS-CoV-19, we propose a new model that leverages tropical arithmetic to characterize the PCR testing process. In many cases, some of which are highlighted in this work, tropical group testing is provably more powerful than traditional binary group testing in that it requires fewer tests than classical approaches, while additionally providing a mechanism to identify the viral load of each infected individual. © 2022 IEEE.

A Question-Answering System on COVID-19 Scientific Literature

The vast amount of COVID-19 research literature has made it difficult for medical experts, clinical scientists, and researchers to keep up with the latest research findings. We present two datasets for COVID-19 in this work: (1) first, we create a dataset from the up-to-date scientific publications on COVID-19, and (2) second, we build a gold-standard dataset of question-answering pairs annotated by volunteer biomedical experts on COVID-19 related scientific articles. We develop a question-answering (QA) pipeline that uses the first dataset to provide answers related to COVID-19 questions;we fine-tune MPNet (a Transformer model) on our gold-standard dataset and use it in the QA pipeline to enhance its reading capability. We also use this gold-standard dataset to evaluate the QA pipeline. The proposed MPNet version on the gold-standard dataset outperformed previous datasets and models, achieving an Exact Match/Fl score of 69.72/78.50 %, respectively © 2022 IEEE.

ULTRASENSITIVE AND RAPID DETECTION OF COVID-19 VIRUS USING DUAL-CLAMPED SURFACE-ENHANCED-RAMAN-SCATTERING NANOSENSORS

The COVID-19 outbreak spreads around world, accumulated to more than 27 million confirmed cases and 800k deaths. Polymerase Chain Reaction (PCR), a gold-standard diagnostic method, were labor intensive, time-consuming and costly, which restricted its application to widespread screening. Herein, this study purposes a one-pot and non-washing method to rapidly detect virus by dual-clamped surface-enhanced Raman scattering (SERS) mechanism. COVID Antigens were captured by SERS nanoparticles and novel SERS substrate simultaneously to achieve 6 order enhancements within 20 minutes. The dual-SERS sensors have reached a detection limit of 1 ng/ml in clinical samples for recognizing nucleocapsid & Spike proteins of COVID-19, which is comparable with PCR results. © 2021 MicroTAS 2021 - 25th International Conference on Miniaturized Systems for Chemistry and Life Sciences. All rights reserved.

Optimized Fusion of CNNs to Diagnose Pulmonary Diseases on Chest X-Rays

Since the beginning of the COVID-19 pandemic, more than 350 million cases and 5 million deaths have occurred. Since day one, multiple methods have been provided to diagnose patients who have been infected. Alongside the gold standard of laboratory analyses, deep learning algorithms on chest X-rays (CXR) have been developed to support the COVID-19 diagnosis. The literature reports that convolutional neural networks (CNNs) have obtained excellent results on image datasets when the tests are performed in cross-validation, but such models fail to generalize to unseen data. To overcome this limitation, we exploit the strength of multiple CNNs by building an ensemble of classifiers via an optimized late fusion approach. To demonstrate the system’s robustness, we present different experiments on open source CXR datasets to simulate a real-world scenario, where scans of patients affected by various lung pathologies and coming from external datasets are tested. Promising performances are obtained both in cross-validation and in external validation, obtaining an average accuracy of 93.02% and 91.02%, respectively. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

An Analysis of Tweet Relevance, Twitter Activity and Student Preferences for Universities

Due to Covid-19 outbreak the competition for attracting new students to university programs has never been as technologically intense as it is now. Accordingly, the researchers in this study utilized Neural Network, Logistic Regression and Linear Term Counting algorithms to distinguish relevant tweets from irrelevant ones in terms of building-up and promoting the brand of universities to attract prospective students. Human subjects were used as Gold Standards to measure the accuracy of machine learning predictions. After collecting over half a million tweets that mention the full names of the universities in the Australian Capital Territory and New South Wales between 2017 and 2021, researchers found out that the total count of tweets and global ranking of universities were positively associated with student preferences for these universities and this association was strengthened by the status of their Group of Eight membership. © 2021 IEEE.

Clinical validation of SERS metasurface SARS-CoV-2 biosensor

The real-Time polymerase chain reaction (RT-PCR) analysis using nasal swab samples is the gold standard approach for COVID-19 diagnosis. However, due to the high false-negative rate at lower viral loads and complex test procedure, PCR is not suitable for fast mass screening. Therefore, the need for a highly sensitive and rapid detection system based on easily collected fluids such as saliva during the pandemic has emerged. In this study, we present a surface-enhanced Raman spectroscopy (SERS) metasurface optimized with genetic algorithm (GA) to detect SARS-CoV-2 directly using unprocessed saliva samples. During the GA optimization, the electromagnetic field profiles were used to calculate the field enhancement of each structure and the fitness values to determine the performance of the generated substrates. The obtained design was fabricated using electron beam lithography, and the simulation results were compared with the test results using methylene blue fluorescence dye. After the performance of the system was validated, the SERS substrate was tested with inactivated SARS-CoV-2 virus for virus detection, viral load analysis, cross-reactivity, and variant detection using machine learning models. After the inactivated virus tests are completed, with 36 PCR positive and 33 negative clinical samples, we were able to detect the SARS-CoV-2 positive samples from Raman spectra with 95.2% sensitivity and specificity. © COPYRIGHT SPIE. Downloading of the is permitted for personal use only.

Studying the accuracy of infrared thermography for measuring core body temperature

The purpose of this study was to investigate the accuracy of infrared thermography for measuring body temperature. We compared a commercially available infrared thermal imaging camera (FLIR One) with a medical-grade oral thermometer (Welch-Allyn) as a gold standard. Measurements using the thermal imaging camera were taken from both a short distance (10cm) and long distance (50cm) from the subject. Thirty young healthy adults participated in a study that manipulated body temperature. After establishing a baseline, participants lowered their body temperature by placing their feet in a cold-water bath for 30 minutes while consuming cold water. Feet were then removed and covered with a blanket for 30 minutes as body temperature returned to baseline. During the course of the 70-minute experiment, body temperature was recorded at a 10-minute interval. The thermal imaging camera demonstrated a significant temperature difference from the gold standard from both close range (mean error: +0.433°C) and long range (mean error: +0.522°C). Despite demonstrating potential as a fast and non-invasive method for temperature screening, our results indicate that infrared thermography does not provide an accurate measurement of body temperature. As a result, infrared thermography is not recommended for use as a fever screening device. © COPYRIGHT SPIE. Downloading of the is permitted for personal use only.

A Machine Learning Approach in Evaluating Symptom Screening in Predicting COVID-19

COVID-19 is a disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) that, to date, has over 245 million confirmed cases and claimed almost 5 million lives. This disease attacks the respiratory system and comes with a number of symptoms. The US Center for Disease Control and Prevention presents a set of symptoms. However, these symptoms only begin to manifest after a number of days, which prevents early detection of this disease. This absence of symptoms during the early stages is what is considered by many to be the very factor that caused the virus into becoming a pandemic. Nonetheless, symptoms checking has been used in practice by commercial and business establishments as an initial screening for COVID-19. The bothersome process of symptom checking are still in place at the entrances of malls and airports. In this study, we determine whether or not symptom screening is an effective system to be employed to assess individuals for COVID-19. Specifically, it aims to determine whether or not one or a set of symptoms are effective predictors of the RT-PCR test results, the gold standard in Covid-19 testing, using machine learning. Using data from the Philippine Red Cross, classification models are developed using LightGBM, AdaBoost, Gaussian Naïve-Bayes, MultiLayer Perceptron, Quadratic Discriminant Analysis and Decision Tree. These models were evaluated using the following metrics: precision, sensitivity, specificity and the type II error rate. Furthermore, for explainability, symptoms are analyzed as to whether or not they are relatively influential on the predicting whether or not a patient has COVID-19. The high type II error rate, low sensitivity and low relative predictor scores of the most significant predictor symptoms clearly show that symptoms do not correlate with the RT-PCR testing results. Thus, we conclude that symptom screening is not a medically suitable process for determining whether an individual has COVID-19. In fact, it even exposes us to the risk of viral transmission as people congregate at the entrances and lobbies of establishments. © 2022 IEEE.

COVID-19 Detection in Chest X-Rays Using Inception Resnet-v2

Screening for COVID-19 is a vital part of the triage process. The current COVID-19 gold standard, the RT-PCR test, is regarded to be costly and time consuming. Artificial intelligence can be utilized to identify COVID-19 in radiographic pictures to overcome the limitations of existing testing methods. This study describes how the Inception-ResNet-v2 architecture was used to categorize pictures into three categories using transfer learning (Normal, Viral Pneumonia, and COVID-19,). Despite only running for 29 epochs, the resultant model had an accuracy of 0.966. This demonstrates the utility of AI in the diagnosis of illnesses. © 2021 IEEE.

An XGBoost Model for Age Prediction from COVID-19 Blood Test

COVID-19 was declared a pandemic by the World Health Organization (WHO) in January 2020. Many studies found that some specific age groups of people have a higher risk of contracting the disease. The gold standard test for the disease is a condition-specific test based on Reverse-Transcriptase Polymerase Chain Reaction (RT-PCR). We have previously shown that the results of a standard suite of non-specific blood tests can be used to indicate the presence of a COVID-19 infection with a high likelihood. We continue our research in this area with a study of the connection between the patients' routine blood test results and their age. Predicting a person's age from blood chemistry is not new in health science. Most often, such results are used to detect the signs of diseases associated with aging and develop new medications. The experiment described here shows that the XGBoost algorithm can be used to predict the patients' age from their routine blood tests. The performance evaluation is very satisfactory, with R

COVID-19 Detection Model on Chest CT Scan and X-ray Images Using VGG16 Convolutional Neural Network

In this pandemic of COVID-19, many people's lives are highly affected in various kinds of aspects. Tests are conducted due to the rising number of infected people, with the PCR test as the current gold standard for many. However, many experts consider the PCR test inaccurate due to the resulting false negative and false positive test results. In order to solve the problem, through this paper, the use of a deep learning model is proposed based on a customized VGG16 CNN as a way to identify the presence COVID-19 virus. The biomarkers used in this paper are X-ray and CT scan images of the lungs. At the end of the research, it can be concluded that both CT scan and X-ray images can be used to detect COVID-19 by using VGG16. However, by comparing the performance of the proposed X-ray and CT scan biomarker-based models, it can be inferred that the X-ray biomarker-based model obtained a higher accuracy score of 97% compared to the CT scan-based model with 93% accuracy. This research proved that the X-ray model got a better score and is a better alternative than CT scan, although both have potential and can be considered accurate alternatives to the PCR tests. © 2021 IEEE.

Covid-19 and Artificial Intelligence: Potential and Challenges

The COVID-19 has the potential to cause serious pneumonia and is predicted to cost the healthcare sector a lot of money. Early detection is essential for proper treatment and, as a result, for lowering healthcare system tension. The most popular imaging methods for checking pneumonia are chest X-rays (CXR) and Computed Tomography (CT) scans. CXRs are still important despite the fact that CT scans are the gold standard since they are less expensive, faster, and more readily available. The use of Artificial Intelligence (AI) to detect early coronavirus infections and track the health of infected patients is a promising new strategy. The development of effective algorithms will vastly enhance treatment continuity and decision-making. Not only in the safe keeping of COVID-19 patients, as well as in the continuous monitoring of patient wellbeing, AI is effective. It can monitor the COVID-19 spread on such a large scale, inclusion of biochemical, medical and epidemiological application. By analyzing data, it is also advantageous to encourage virus analysis. AI can assist in the development of successful effective treatment therapies, protection strategies, as well as the development of drugs and vaccines. This paper will examine the efficacy and diagnostic results of CXR and CT scan imaging to test for pneumonia caused due to COVID-19, and the ability of AI to determine doctors' ability to discern COVID-19 patients from healthy people. © 2021 IEEE.

A Novel Internet of Medical Things Model to Progress COVID-19 Testing

The COVID-19 pandemic has devastated the public health infrastructure of the globe. The crucial strategy has been to carry out aggressive testing, which could be the only way to get back to normalcy. The COVID-19 testing is carried out through the Reverse Transcriptase Polymerase Chain Reaction (RT-PCR), which is considered to be the gold standard. However, these tests are sometimes known to provide inaccurate results which might be due to improper sample storage and transportation techniques. The swab samples transported in a viral transport medium need to be maintained under optimum environmental conditions. The proposed model involves tagging humidity and thermologger devices with the sample container box. This would record the real-time temperature and humidity, which would be stored in the cloud server. This would predict any breakage in the cold chain using AI-powered pattern analysis techniques. This would intimate the authorities of a possible cold chain breakage, thereby assuring the quality of the samples. This would drastically reduce the possibility of false outcomes. This would help the healthcare workers to trace, isolate and treat the right affected individuals, preventing the further spread of the disease. This model could also be used for distribution of COVID-19 vaccines whenever they are available. This could preserve the potency of the vaccines, thereby significantly reducing the wastage of vaccines. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Choosing Units of Analysis in Temporal Discourse

Despite the promise of quantitative ethnographic approaches for visualizing the trajectories of change over time (temporal analysis) further work is needed to develop strategies for accurately representing phenomena. This holds especially true for identifying the relational context of discourse, which includes the creation of time units that group lines of data for the purpose of interpretation. While in-depth interpretive review of discourse may serve as the ‘gold standard’ for identification of thematic time units, this approach is tedious and may not be appropriate for larger datasets. Incremental approaches, such as creating a new unit for every ten lines of chronological data, are functional for larger datasets, but may lack nuance. This work introduces the Knowledge Building Discourse Explorer (KBDeX), which computationally identifies relational units using socio-semantic network analysis, allowing for the identification of time units based on characteristics of the discourse that can be systematically applied to larger datasets. To examine the utility of each approach, epistemic networks of COVID-19 press releases from seven countries were created with time units derived from the incremental and computational approaches, which were then compared to the interpretive approach. Results indicated that KBDeX and incremental network means were closer to the ‘gold standard’ interpretive approach in some instances. Two countries’ trajectories are examined in greater depth to understand when each approach might be most appropriate. The work concludes with a discussion of the affordances and constraints of each approach, and contexts in which they may be useful. © 2022, Springer Nature Switzerland AG.

Evaluation of Convolutional Neural Networks for COVID-19 Classification on Chest X-Rays

Early identification of patients with COVID-19 is essential to enable adequate treatment and to reduce the burden on the health system. The gold standard for COVID-19 detection is the use of RT-PCR tests. However, due to the high demand for tests, these can take days or even weeks in some regions of Brazil. Thus, an alternative for detecting COVID-19 is the analysis of Digital Chest X-rays (XR). Changes due to COVID-19 can be detected in XR, even in asymptomatic patients. In this context, models based on deep learning have great potential to be used as support systems for diagnosis or as screening tools. In this paper, we propose the evaluation of convolutional neural networks to identify pneumonia due to COVID-19 in XR. The proposed methodology consists of a preprocessing step of the XR, data augmentation, and classification by the convolutional architectures DenseNet121, InceptionResNetV2, InceptionV3, MovileNetV2, ResNet50, and VGG16 pre-trained with the ImageNet dataset. The obtained results for our methodology demonstrate that the VGG16 architecture presented a superior performance in the classification of XR, with an Accuracy of 85.11 %, Sensitivity of 85.25 %, Specificity of 85.16 %, F1-score of 85.03 %, and an AUC of 0.9758. © 2021, Springer Nature Switzerland AG.

Surface temperature distribution aluminum block with cone tube profile calculated using ANSYS fluent

Thermal Cycler is the main part of the Polymerase Chain Reaction (PCR), which becoming a gold standard for Covid-19 diagnosis. The virus multiplication in an order to a detectable concentration is done by placing the virus solution at a deterministic temperature cycle. The solution is placed in a small tube inserted in a temperature block. Temperature distribution of the thermal block is important to make all the tube with sample treated at the same at desired target temperature. Study on the thermal block made of aluminium 7075 was simulated using fluid dynamic finite element method. Heating and colling to the target temperature was done by providing heat source and heat absorber. The temperature distribution on the surface was mapped. The temperature gradient perpendicular to the heat source was calculated. Assuming the environment of the thermal block was still air, the heating and cooling speed at given heat source and heat removal were calculated using the model. The temperature gradient from the top surface to the bottom surface is less than 2.5?. The temperature difference among point at the surface is less than 0.1?. © Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence.