Multi-center sparse learning and decision fusion for automatic COVID-19 diagnosis

The coronavirus disease 2019 (COVID-19) pandemic caused by the novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has led to a sharp increase in hospitalized patients with multi-organ disease pneumonia. Early and automatic diagnosis of COVID-19 is essential to slow down the spread of this epidemic and reduce the mortality of patients infected with SARS-CoV-2. In this paper, we propose a joint multi-center sparse learning (MCSL) and decision fusion scheme exploiting chest CT images for automatic COVID-19 diagnosis. Specifically, considering the inconsistency of data in multiple centers, we first convert CT images into histogram of oriented gradient (HOG) images to reduce the structural differences between multi-center data and enhance the generalization performance. We then exploit a 3-dimensional convolutional neural network (3D-CNN) model to learn the useful information between and within 3D HOG image slices and extract multi-center features. Furthermore, we employ the proposed MCSL method that learns the intrinsic structure between multiple centers and within each center, which selects discriminative features to jointly train multi-center classifiers. Finally, we fuse these decisions made by these classifiers. Extensive experiments are performed on chest CT images from five centers to validate the effectiveness of the proposed method. The results demonstrate that the proposed method can improve COVID-19 diagnosis performance and outperform the state-of-the-art methods.

Stacked-autoencoder-based model for COVID-19 diagnosis on CT images

With the outbreak of COVID-19, medical imaging such as computed tomography (CT) based diagnosis is proved to be an effective way to fight against the rapid spread of the virus. Therefore, it is important to study computerized models for infectious detection based on CT imaging. New deep learning-based approaches are developed for CT assisted diagnosis of COVID-19. However, most of the current studies are based on a small size dataset of COVID-19 CT images as there are less publicly available datasets for patient privacy reasons. As a result, the performance of deep learning-based detection models needs to be improved based on a small size dataset. In this paper, a stacked autoencoder detector model is proposed to greatly improve the performance of the detection models such as precision rate and recall rate. Firstly, four autoencoders are constructed as the first four layers of the whole stacked autoencoder detector model being developed to extract better features of CT images. Secondly, the four autoencoders are cascaded together and connected to the dense layer and the softmax classifier to constitute the model. Finally, a new classification loss function is constructed by superimposing reconstruction loss to enhance the detection accuracy of the model. The experiment results show that our model is performed well on a small size COVID-2019 CT image dataset. Our model achieves the average accuracy, precision, recall, and F1-score rate of 94.7%, 96.54%, 94.1%, and 94.8%, respectively. The results reflect the ability of our model in discriminating COVID-19 images which might help radiologists in the diagnosis of suspected COVID-19 patients.

Emerging Biosensors to Detect Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2): A Review

Coronavirus disease (COVID-19) is a global health crisis caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Real-time reverse transcriptase-polymerase chain reaction (RT-PCR) is the gold standard test for diagnosing COVID-19. Although it is highly accurate, this lab test requires highly-trained personnel and the turn-around time is long. Rapid and inexpensive immuno-diagnostic tests (antigen or antibody test) are available, but these point of care (POC) tests are not as accurate as the RT-PCR test. Biosensors are promising alternatives to these rapid POC tests. Here we review three types of recently developed biosensors for SARS-CoV-2 detection: surface plasmon resonance (SPR)-based, electrochemical and field-effect transistor (FET)-based biosensors. We explain the sensing principles and discuss the advantages and limitations of these sensors. The accuracies of these sensors need to be improved before they could be translated into POC devices for commercial use. We suggest potential biorecognition elements with highly selective target-analyte binding that could be explored to increase the true negative detection rate. To increase the true positive detection rate, we suggest two-dimensional materials and nanomaterials that could be used to modify the sensor surface to increase the sensitivity of the sensor.

Laboratory diagnosis and management of COVID-19 cases: creating a safe testing environment

Background

COVID-19 disease has had a profound impact worldwide since it was discovered in Wuhan, China, in December 2019. Laboratory testing is crucial to prompt identification of positive cases, initiation of treatment and management strategies. However, medical scientists are vulnerable to infection due to the risk of exposure in the laboratory and the community. This study sought to determine the awareness of laboratory safety measures, assess the personal efforts of medical scientists in creating a safe laboratory environment for testing and examine the laboratory safety enabling factors.

Methods

The data used for the study were generated among medical scientists in Nigeria through an internet-broadcasted questionnaire and were analyzed using IBM SPSS Statistics (version 25).

Results

The majority of the respondents had a high awareness of laboratory safety measures (60.3%) and demonstrated good personal efforts in creating a safe laboratory testing environment (63%). The level of awareness of laboratory safety measures was significantly associated with respondents’ level of education (χ² = 6.143; p = 0.046) and influences respondents’ efforts in creating a safe laboratory testing environment (p = 0.007). However, just a few respondents could convincingly attest to the availability of adequate and appropriate PPE with proper utilization training (45.1%), adequate rest and other welfare packages (45.8%) as well as access to appropriate Biological Safety Cabinets (BSCs) and other essential equipment in their laboratories (48.8%). Furthermore, a significant association existed between the availability of laboratory safety enabling factors and respondents’ efforts in creating a safe environment for testing with the p-value ranging between < 0.0001 and 0.003.

Conclusion

This study revealed that despite the high awareness of safety measures and good personal efforts of the study participants in creating a safe laboratory-testing environment, there was poor availability of safety facilities, equipment, support and welfare packages required to enhance their safety. It is, therefore, crucial to provide necessary laboratory biosafety equipment and PPE in order not to compromise medical scientists’ safety as they perform their duties in COVID-19 pandemic response.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12879-021-06806-0.

AutoCovNet: Unsupervised feature learning using autoencoder and feature merging for detection of COVID-19 from chest X-ray images

With the onset of the COVID-19 pandemic, the automated diagnosis has become one of the most trending topics of research for faster mass screening. Deep learning-based approaches have been established as the most promising methods in this regard. However, the limitation of the labeled data is the main bottleneck of the data-hungry deep learning methods. In this paper, a two-stage deep CNN based scheme is proposed to detect COVID-19 from chest X-ray images for achieving optimum performance with limited training images. In the first stage, an encoder-decoder based autoencoder network is proposed, trained on chest X-ray images in an unsupervised manner, and the network learns to reconstruct the X-ray images. An encoder-merging network is proposed for the second stage that consists of different layers of the encoder model followed by a merging network. Here the encoder model is initialized with the weights learned on the first stage and the outputs from different layers of the encoder model are used effectively by being connected to a proposed merging network. An intelligent feature merging scheme is introduced in the proposed merging network. Finally, the encoder-merging network is trained for feature extraction of the X-ray images in a supervised manner and resulting features are used in the classification layers of the proposed architecture. Considering the final classification task, an EfficientNet-B4 network is utilized in both stages. An end to end training is performed for datasets containing classes: COVID-19, Normal, Bacterial Pneumonia, Viral Pneumonia. The proposed method offers very satisfactory performances compared to the state of the art methods and achieves an accuracy of 90:13% on the 4-class, 96:45% on a 3-class, and 99:39% on 2-class classification.

Sero-prevalence of anti-SARS-CoV-2 antibodies among healthcare workers: A multicenter study from Egypt

Background

Healthcare workers (HCWs) are at a high risk for disease exposure. Given the limited availability of nucleic acid testing by PCR in low resource settings, serological assays can provide useful data on the proportion of HCWs who have recently or previously been infected. Therefore, in this study, we conducted an immunologic study to determine the seroprevalence of anti-SARS-CoV-2 antibodies in two university hospitals in Egypt.

Methods

in this cross sectional study, HCWs who were working in SARS-CoV-2 Isolation Hospitals were interviewed. Estimating specific antibodies (IgM and IgG) against SARS-CoV-2 was carried out using an enzyme-linked immunosorbent assay targeting the Spike antigen of SARS-CoV-2 virus.

Results

Out of 111, 82 (74%) HCWs accepted to participate with a mean age of 31.5 ± 8.5 years. Anti-SARS-COV2 antibodies were detected in 38/82 (46.3%) of cases with a mean age of 31 years and female HCWs constituted 57.6% of cases. The highest rate of seropositivity was from the nurses (60.5%), and physicians (31.6%) with only (7.9%) technicians. Only 28/82 (34.1%) HCWs reported previous history of COVID19. We reported a statistically significant difference in the timing of exposure (p = 0.010) and the frequency of contact with COVID-19 cases (p = 0.040) between previously infected and on-infected HCWs. Longer time of recovery was reported from IgG positive HCWs (p = 0.036).

Conclusion

The high frequency of seropositive HCWs in investigated hospitals is alarming, especially among asymptomatic personnel. Confirmation of diseased HCWs (among seropositive ones) are warranted.

A depthwise separable dense convolutional network with convolution block attention module for COVID-19 diagnosis on CT scans

Coronavirus disease 2019 (COVID-19) has caused more than 3 million deaths and infected more than 170 million individuals all over the world. Rapid identification of patients with COVID-19 is the key to control transmission and prevent depletion of hospitals. Several networks have been proposed to assist radiologists in diagnosing COVID-19 based on CT scans. However, CTs used in these studies are unavailable for other researchers to do deeper extensions due to privacy concerns. Furthermore, these networks are too heavy-weighted to satisfy the general trend applying on a computationally limited platform. In this paper, we aim to solve these two problems. Firstly, we establish an available dataset COVID-CTx, which contains 828 CT scans positive for COVID-19 across 324 patient cases from three open access data repositories. To our knowledge, it has the largest number of publicly available COVID-19 positive cases compared to other public datasets. Secondly, we propose a light-weighted hybrid neural network: Depthwise Separable Dense Convolutional Network with Convolution Block Attention Module (AM-SdenseNet). AM-SdenseNet synergistically integrates Convolutional Block Attention Module with depthwise separable convolutions to learn powerful feature representations while reducing the parameters to overcome the overfitting problem. Through experiments, we demonstrate the superior performance of our proposed AM-SdenseNet compared with several state-of-the-art baselines. The excellent performance of AM-SdenseNet can improve the speed and accuracy of COVID-19 diagnosis, which is extremely useful to control the spreading of infection.

Sustainable and fast saliva-based COVID-19 virus diagnosis kit using a novel GO-decorated Au/FBG sensor

Monitoring the COVID-19 virus through patients' saliva is a favorable non-invasive specimen for diagnosis and infection control. In this study, salivary samples of COVID-19 patients collected from 6 patients with the median age of 58.5 years, ranging from 34 to 72 years (2 females and 4 males) were analyzed using an Au/fiber Bragg grating (FBG) probe decorated with GO. The probe measures the prevalence of positivity in saliva and the association between the virus density and changes to sensing elements. When the probe is immersed in patients' saliva, deviation of the detected light wavelength and intensity from healthy saliva indicate the presence of the virus and confirms infection. For a patient in the hyperinflammatory phase of desease, who has virus density of 1.2 × 108 copies/mL in saliva, the maximum wavelength shift and intensity changes after 1600 s were shown to be 1.12 nm and 2.01 dB, respectively. While for a patient in the early infection phase with 1.6 × 103 copies/mL, these values were 0.98 nm and 1.32 dB. The precise and highly sensitive FBG probe proposed in this study was found a reliable tool for quick detection of the COVID-19 virus within 10 s after exposure to patients' saliva in any stage of the disease.

Residual Learning Diagnosis Detection: An Advanced Residual Learning Diagnosis Detection System for COVID-19 in Industrial Internet of Things

Due to the fast transmission speed and severe health damage, COVID-19 has attracted global attention. Early diagnosis and isolation are effective and imperative strategies for epidemic prevention and control. Most diagnostic methods for the COVID-19 is based on nucleic acid testing (NAT), which is expensive and time-consuming. To build an efficient and valid alternative of NAT, this article investigates the feasibility of employing computed tomography images of lungs as the diagnostic signals. Unlike normal lungs, parts of the lungs infected with the COVID-19 developed lesions, ground-glass opacity, and bronchiectasis became apparent. Through a public dataset, in this article, we propose an advanced residual learning diagnosis detection (RLDD) scheme for the COVID-19 technique, which is designed to distinguish positive COVID-19 cases from heterogeneous lung images. Besides the advantage of high diagnosis effectiveness, the designed residual-based COVID-19 detection network can efficiently extract the lung features through small COVID-19 samples, which removes the pretraining requirement on other medical datasets. In the test set, we achieve an accuracy of 91.33%, a precision of 91.30%, and a recall of 90%. For the batch of 150 samples, the assessment time is only 4.7 s. Therefore, RLDD can be integrated into the application programming interface and embedded into the medical instrument to improve the detection efficiency of COVID-19.

Mouth Washing Impaired SARS-CoV-2 Detection in Saliva

BACKGROUND

A previous study demonstrated the performance of the Salivette® (SARSTEDT, Numbrecht, Germany) as a homogeneous saliva collection system to diagnose COVID-19 by RT-qPCR, notably for symptomatic and asymptomatic patients. However, for convalescent patients, the corroboration of molecular detection of SARS-CoV-2 in paired nasopharyngeal swabs (NPS) and saliva samples was unsatisfactory.

OBJECTIVES

The aim of the present work was to assess the concordance level of SARS-CoV-2 detection between paired sampling of NPSs and saliva collected with Salivette® at two time points, with ten days of interval.

RESULTS

A total of 319 paired samples from 145 outpatients (OP) and 51 healthcare workers (HW) were collected. Unfortunately, at day ten, 73 individuals were lost to follow-up, explaining some kinetic missing data. Due to significant waiting rates at hospitals, most of the patients ate and/or drank while waiting for their turn. Consequently, mouth washing was systematically proposed prior to saliva collection. None of the HW were diagnosed as SARS-CoV-2 positive using NPS or saliva specimens at both time points (n = 95) by RT-qPCR. The virus was detected in 56.3% (n = 126/224) of the NPS samples from OP, but solely 26.8% (n = 60/224) of the paired saliva specimens. The detection of the internal cellular control, the human RNase P, in more than 98% of the saliva samples, underlined that the low sensitivity of saliva specimens (45.2%) for SARS-CoV-2 detection was not attributed to an improper saliva sample storing or RNA extraction.

CONCLUSIONS

This work revealed that mouth washing decreased viral load of buccal cavity conducting to impairment of SARS-CoV-2 detection. Viral loads in saliva neo-produced appeared insufficient for molecular detection of SARS-CoV-2. At the time when saliva tests could be a rapid, simple and non-invasive strategy to assess large scale schoolchildren in France, the determination of the performance of saliva collection becomes imperative to standardize procedures.

Prevalence of and factors associated with COVID-19 diagnosis in symptomatic patients followed in general practices in Germany between March 2020 and March 2021

Aims

This study aimed to investigate the prevalence of and the factors associated with the diagnosis of coronavirus disease 2019 (COVID-19) in symptomatic patients followed in general practices in Germany between March 2020 and March 2021.

Methods

Symptomatic patients tested for COVID-19 and followed in one of 962 general practices in Germany from March 2020 to March 2021 were included in this study. Covariates included sex, age, and comorbidities present in at least 3% of the population. The association between these factors and the diagnosis of COVID-19 was analyzed using an adjusted logistic regression model.

Results

A total of 301,290 patients tested for COVID-19 were included in this study (54.7% women; mean [SD] age 44.6 [18.5] years). The prevalence of COVID-19 was 13.8% in this sample. Male sex and older age were positively and significantly associated with COVID-19. In terms of comorbidities, the strongest positive associations with COVID-19 were observed for cardiac arrhythmias, depression, and obesity. There was also a negative relationship between the odds of being diagnosed with COVID-19 and several conditions such as chronic sinusitis, asthma, and anxiety disorders.

Conclusions

Approximately 14% of symptomatic patients tested for COVID-19 were diagnosed with COVID-19 in German general practices from March 2020 to March 2021.

Evaluation and Comparison of Serological Methods for COVID-19 Diagnosis

The worldwide pandemic of COVID-19 has become a global public health crisis. Various clinical diagnosis methods have been developed to distinguish COVID-19-infected patients from healthy people. The nucleic acid test is the golden standard for virus detection as it is suitable for early diagnosis. However, due to the low amount of viral nucleic acid in the respiratory tract, the sensitivity of nucleic acid detection is unsatisfactory. As a result, serological screening began to be widely used with the merits of simple procedures, lower cost, and shorter detection time. Serological tests currently include the enzyme-linked immunosorbent assay (ELISA), lateral flow immunoassay (LFIA), and chemiluminescence immunoassay (CLIA). This review describes various serological methods, discusses the performance and diagnostic effects of different methods, and points out the problems and the direction of optimization, to improve the efficiency of clinical diagnosis. These increasingly sophisticated and diverse serological diagnostic technologies will help human beings to control the spread of COVID-19.

Pulling-Force Spinning Top for Serum Separation Combined with Paper-Based Microfluidic Devices in COVID-19 ELISA Diagnosis

The spread of Coronavirus disease 2019 (COVID-19) is caused by severe acute respiratory syndrome-coronavirus 2 (SARS-CoV-2), resulting in a global pandemic with around four million deaths. Although there are a variety of nucleic acid-based tests for detecting SARS-CoV-2, these methods have a relatively high cost and require expensive supporting equipment. To overcome these limitations and improve the efficiency of SARS-CoV-2 diagnosis, we developed a microfluidic platform that collected serum by a pulling-force spinning top and paper-based microfluidic enzyme-linked immunosorbent assay (ELISA) for quantitative IgA/IgM/IgG measurements in an instrument-free way. We further validated the paper-based microfluidic ELISA analysis of SARS-CoV-2 receptor-binding domain (RBD)-specific IgA/IgM/IgG antibodies from human blood samples as a good measurement with higher sensitivity compared with traditional IgM/IgG detection (99.7% vs 95.6%) for early illness onset patients. In conclusion, we provide an alternative solution for the diagnosis of SARS-CoV-2 in a portable manner by this smart integration of pulling-force spinning top and paper-based microfluidic immunoassay.

Time scale performance of rapid antigen testing for SARS-CoV-2: Evaluation of 10 rapid antigen assays

There is a great demand for more rapid tests for SARS‐CoV‐2 detection to reduce waiting time, boost public health strategies for combating disease, decrease costs, and prevent overwhelming laboratory capacities. This study was conducted to assess the performance of 10 lateral flow device viral antigen immunoassays for the detection of SARS‐CoV‐2 in nasopharyngeal swab specimens. We analyzed 231 nasopharyngeal samples collected from October 2020 to December 2020, from suspected COVID‐19 cases and contacts of positive cases at Biotechnology Research Center laboratories, Tripoli, Libya. The performance of 10 COVID‐19 Antigen (Ag) rapid test devices for the detection of SARS‐CoV‐2 antigen was compared to a quantitative reverse transcription‐polymerase chain reaction (RT‐qPCR). In this study, 161 cases had symptoms consistent with COVID‐19. The mean duration from symptom onset was 6.6 ± 4.3 days. The median cycle threshold (C_t) of positive samples was 25. Among the 108 positive samples detected by RT‐qPCR, the COVID‐19 antigen (Ag) tests detected 83 cases correctly. All rapid Ag test devices used in this study showed 100% specificity. While tests from six manufacturers had an overall sensitivity range from 75% to 100%, the remaining four tests had a sensitivity of 50%–71.43%. Sensitivity during the first 6 days of symptoms and in samples with high viral loads (C_t < 25), was 100% in all but two of the test platforms. False‐negative samples had a median C_t of 34 and an average duration of onset of symptoms of 11.3 days (range = 5–20 days). Antigen test diagnosis has high sensitivity and specificity in early disease when patients present less than 7 days of symptom onset. Patients are encouraged to test as soon as they get COVID‐19‐related symptoms within 1 week and to seek medical advice within 24 h if they develop disturbed smell/taste. The use of rapid antigen tests is important for controlling the COVID‐19 pandemic and reducing the burden on molecular diagnostic laboratories.

Rapid antigen testing has high sensitivity and specificity in early disease when patients present less than 7 days of symptom onset

Patients should be encouraged to test within one week after getting COVID‐19 related symptoms and within 24 hrs. if they develop disturbed smell/taste.

The use of rapid antigen testing is important for reducing burden on molecular diagnostic laboratories.

NIA-Network: Towards improving lung CT infection detection for COVID-19 diagnosis

During pandemics (e.g., COVID-19) physicians have to focus on diagnosing and treating patients, which often results in that only a limited amount of labeled CT images is available. Although recent semi-supervised learning algorithms may alleviate the problem of annotation scarcity, limited real-world CT images still cause those algorithms producing inaccurate detection results, especially in real-world COVID-19 cases. Existing models often cannot detect the small infected regions in COVID-19 CT images, such a challenge implicitly causes that many patients with minor symptoms are misdiagnosed and develop more severe symptoms, causing a higher mortality. In this paper, we propose a new method to address this challenge. Not only can we detect severe cases, but also detect minor symptoms using real-world COVID-19 CT images in which the source domain only includes limited labeled CT images but the target domain has a lot of unlabeled CT images. Specifically, we adopt Network-in-Network and Instance Normalization to build a new module (we term it NI module) and extract discriminative representations from CT images from both source and target domains. A domain classifier is utilized to implement infected region adaptation from source domain to target domain in an Adversarial Learning manner, and learns domain-invariant region proposal network (RPN) in the Faster R-CNN model. We call our model NIA-Network (Network-in-Network, Instance Normalization and Adversarial Learning), and conduct extensive experiments on two COVID-19 datasets to validate our approach. The experimental results show that our model can effectively detect infected regions with different sizes and achieve the highest diagnostic accuracy compared with existing SOTA methods.

What we know and dont know on SARS-CoV-2 and COVID-19

Coronavirus disease 2019 (COVID-19), caused by the SARS-CoV-2 virus discovered in December 2019 in Wuhan, China, has had an enormous impact on public health worldwide due to its rapid spread and pandemic behavior, challenges in its control and mitigation, and few therapeutic alternatives. In this review, we summarize the pathophysiological mechanisms, clinical presentation, and diagnostic techniques. In addition, the main lineages and the different strategies for disease prevention are reviewed, with emphasis on the development of vaccines and their different platforms. Finally, some of the currently available therapeutic strategies are summarized. Throughout the article, we point out the current knowns and unknowns at the time of writing this article.

Momentum contrastive learning for few-shot COVID-19 diagnosis from chest CT images

The current pandemic, caused by the outbreak of a novel coronavirus (COVID-19) in December 2019, has led to a global emergency that has significantly impacted economies, healthcare systems and personal wellbeing all around the world. Controlling the rapidly evolving disease requires highly sensitive and specific diagnostics. While RT-PCR is the most commonly used, it can take up to eight hours, and requires significant effort from healthcare professionals. As such, there is a critical need for a quick and automatic diagnostic system. Diagnosis from chest CT images is a promising direction. However, current studies are limited by the lack of sufficient training samples, as acquiring annotated CT images is time-consuming. To this end, we propose a new deep learning algorithm for the automated diagnosis of COVID-19, which only requires a few samples for training. Specifically, we use contrastive learning to train an encoder which can capture expressive feature representations on large and publicly available lung datasets and adopt the prototypical network for classification. We validate the efficacy of the proposed model in comparison with other competing methods on two publicly available and annotated COVID-19 CT datasets. Our results demonstrate the superior performance of our model for the accurate diagnosis of COVID-19 based on chest CT images.

MetaCOVID: A Siamese neural network framework with contrastive loss for n-shot diagnosis of COVID-19 patients

Various AI functionalities such as pattern recognition and prediction can effectively be used to diagnose (recognize) and predict coronavirus disease 2019 (COVID-19) infections and propose timely response (remedial action) to minimize the spread and impact of the virus. Motivated by this, an AI system based on deep meta learning has been proposed in this research to accelerate analysis of chest X-ray (CXR) images in automatic detection of COVID-19 cases. We present a synergistic approach to integrate contrastive learning with a fine-tuned pre-trained ConvNet encoder to capture unbiased feature representations and leverage a Siamese network for final classification of COVID-19 cases. We validate the effectiveness of our proposed model using two publicly available datasets comprising images from normal, COVID-19 and other pneumonia infected categories. Our model achieves 95.6% accuracy and AUC of 0.97 in diagnosing COVID-19 from CXR images even with a limited number of training samples.

Salivette, a relevant saliva sampling device for SARS-CoV-2 detection

Background: The gold standard for COVID-19 diagnosis relies on quantitative reverse-transcriptase polymerase-chain reaction (RT-qPCR) from nasopharyngeal swab (NPS) specimens, but NPSs present several limitations. The simplicity, low invasive and possibility of self-collection of saliva imposed these specimens as a relevant alternative for SARS-CoV-2 detection. However, the discrepancy of saliva test results compared to NPSs made of its use controversial. Here, we assessed Salivettes®, as a standardized saliva collection device, and compared SARS-CoV-2 positivity on paired NPS and saliva specimens. Methods: A total of 303 individuals randomly selected among those investigated for SARS-CoV-2 were enrolled, including 30 (9.9%) patients previously positively tested using NPS (follow-up group), 90 (29.7%) mildly symptomatic and 183 (60.4%) asymptomatic. Results: The RT-qPCR revealed a positive rate of 11.6% (n = 35) and 17.2% (n = 52) for NPSs and saliva samples, respectively. The sensitivity and specificity of saliva samples were 82.9% and 91.4%, respectively, using NPS as reference. The highest proportion of discordant results concerned the follow-up group (33.3%). Although the agreement exceeded 90.0% in the symptomatic and asymptomatic groups, 17 individuals were detected positive only in saliva samples, with consistent medical arguments. Conclusion Saliva collected with Salivette® was more sensitive for detecting symptomatic and pre-symptomatic infections.

Performance comparison of the Cobas® Liat® and Cepheid® GeneXpert® systems on SARS-CoV-2 detection in nasopharyngeal swab and posterior oropharyngeal saliva

Background: Nucleic acid amplification tests (NAATs) based methods such as real-time reverse transcription polymerase-chain reaction (real-time RT-PCR) are the gold standard for diagnosis of current infection with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The cobas® Liat® and cepheid® GeneXpert® systems are two rapid real-time RT-PCR platforms offering rapid, specimen-to-answer detection of SARS-CoV-2.Research design and methods: In this study, we compared the performance of these two systems on SARS-CoV-2 detection in 9 nasopharyngeal swab (NPS) and 70 posterior oropharyngeal saliva specimens collected from 79 patients suspected of SARS-CoV-2 infection between August 2020 and March 2021.Results: The Positive Percent Agreement (PPA), Negative Percent Agreement (NPA) and overall Percent Agreement (OPA) between cepheid® Xpress SARS-CoV-2 assay and cobas® Liat® SARS-CoV-2 & Influenza A/B assay were found to be 100%. We demonstrated an excellent overall test concordance of the Liat® SARS-CoV-2 & Influenza A/B assay and Xpress SARS-CoV-2 assay. The small sample size of SARS-CoV-2 positive and weak-positive specimens is the inherent limitation of this study.Conclusions: The performance of the cobas® Liat® SARS-CoV-2 & Influenza A/B assay is equivalent to the cepheid® Xpress SARS-CoV-2 assay for SARS-CoV-2 detection using NPS and posterior oropharyngeal saliva.

Evaluating the efficiency of specimen (sample) pooling for real-time PCR based diagnosis of COVID-19

Purpose

This study is aims at evaluating the efficacy and sensitivity of specimen pooling for testing of SARS-CoV-2 virus to determine the accuracy, resource savings, and identification of borderline positive cases without impacting the accuracy of the testing.

Method

This study was conducted between August and October 2020, we performed COVID-19 testing by RT-PCR on the samples from varying prevalence of rural population (non-hot spot) referred to COVID laboratory, in the first step, the samples were collated into pools of 5 or 10. These pools were tested by RT-PCR. Negative pools were reported as negative whereas positive pools of 5 and 10 were then de-convoluted and each sample was tested individually.

Results

In the present study, we tested 1580 samples in 158 pools of 10 and 17,515 samples in 3503 pools of 5. Among 10 samples pool, 11 (13%) pools flagged positive in the first step. In the second step, among 11 pools (110 samples) de-convoluted strategy was followed in which 10 individual samples came positive. Among 5 samples pool, 164 (13%) pools flagged positive in the first step. In the second step, among 164 pools (820 samples) de-convoluted strategy was followed in which 171 individual samples came positive. The pooled sample testing strategy saves substantial resources and time during surge testing and enhanced pandemic surveillance. This approach requires around 76%–93% fewer tests in low to moderate prevalence settings and group sizes up to 5–10 in a population, compared to individual testing.

Conclusion

Pooled sample RT- PCR analysis strategies can save substantial resources and time for COVID-19 mass testing in comparison with individual testing without compromising the quality of outcome of the test. In particular, the pooled sample approach can facilitate mass screening in the early asymptomatic stages of COVID-19 infections.

Pooling of Nasopharyngeal Swab Samples To Overcome a Global Shortage of Real-Time Reverse Transcription-PCR COVID-19 Test Kits

The global outbreak and rapid spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) have created an urgent need for large-scale testing of populations. There is a demand for high-throughput testing protocols that can be used for efficient and rapid testing of clinical specimens. We evaluated a pooled PCR protocol for testing nasopharyngeal (NP) swabs using known positive/negative and untested clinical samples that were assigned to pools of 5 or 10. In total, 630 samples were used in this study. Individual positive samples with cycle threshold (C_T ) values as high as 33 could be consistently detected when pooled with 4 negative samples (pool of 5), and individual positive samples with C_T values up to 31 could be consistently detected when pooled with 9 negative samples (pool of 10). Pooling of up to 5 samples can be employed in laboratories for the diagnosis of COVID-19 for efficient utilization of resources, rapid screening of a greater number of people, and faster reporting of test results.

Accurate Classification of COVID-19 Based on Incomplete Heterogeneous Data using a KNN Variant Algorithm

Great efforts are now underway to control the coronavirus 2019 disease (COVID-19). Millions of people are medically examined, and their data keep piling up awaiting classification. The data are typically both incomplete and heterogeneous which hampers classical classification algorithms. Some researchers have recently modified the popular KNN algorithm as a solution, where they handle incompleteness by imputation and heterogeneity by converting categorical data into numbers. In this article, we introduce a novel KNN variant (KNNV) algorithm that provides better results as demonstrated by thorough experimental work. We employ rough set theoretic techniques to handle both incompleteness and heterogeneity, as well as to find an ideal value for K. The KNNV algorithm takes an incomplete, heterogeneous dataset, containing medical records of people, and identifies those cases with COVID-19. We use in the process two popular distance metrics, Euclidean and Mahalanobis, in an effort to widen the operational scope. The KNNV algorithm is implemented and tested on a real dataset from the Italian Society of Medical and Interventional Radiology. The experimental results show that it can efficiently and accurately classify COVID-19 cases. It is also compared to three KNN derivatives. The comparison results show that it greatly outperforms all its competitors in terms of four metrics: precision, recall, accuracy, and F-Score. The algorithm given in this article can be easily applied to classify other diseases. Moreover, its methodology can be further extended to do general classification tasks outside the medical field.

Accurate Classification of COVID-19 Based on Incomplete Heterogeneous Data using a KNN Variant Algorithm

Great efforts are now underway to control the coronavirus 2019 disease (COVID-19). Millions of people are medically examined, and their data keep piling up awaiting classification. The data are typically both incomplete and heterogeneous which hampers classical classification algorithms. Some researchers have recently modified the popular KNN algorithm as a solution, where they handle incompleteness by imputation and heterogeneity by converting categorical data into numbers. In this article, we introduce a novel KNN variant (KNNV) algorithm that provides better results as demonstrated by thorough experimental work. We employ rough set theoretic techniques to handle both incompleteness and heterogeneity, as well as to find an ideal value for K. The KNNV algorithm takes an incomplete, heterogeneous dataset, containing medical records of people, and identifies those cases with COVID-19. We use in the process two popular distance metrics, Euclidean and Mahalanobis, in an effort to widen the operational scope. The KNNV algorithm is implemented and tested on a real dataset from the Italian Society of Medical and Interventional Radiology. The experimental results show that it can efficiently and accurately classify COVID-19 cases. It is also compared to three KNN derivatives. The comparison results show that it greatly outperforms all its competitors in terms of four metrics: precision, recall, accuracy, and F-Score. The algorithm given in this article can be easily applied to classify other diseases. Moreover, its methodology can be further extended to do general classification tasks outside the medical field.

An alternative way to perform diagnostic nasopharyngeal swab for SARS-CoV-2 infection

On March 11, 2020, WHO has defined the novel coronavirus disease SARS-CoV-2 (COVID-19) outbreak as a pandemic and still today continues to affect much of the world. Among the reasons for the rapid spread of SARS–CoV-2 infection, there is not only the high transmissibility of the virus, but also the role of asymptomatic or minimally symptomatic carriers. Therefore diagnostic testing is central to contain the global pandemic. Up to now real-time reverse transcriptase polymerase chain reaction (RT-PCR)–based molecular assays for detecting SARSCoV-2 in respiratory specimens is the current reference standard for COVID-19 diagnosis. Nasopharyngeal swab is the preferred choice for SARS–CoV-2 testing; however is not always a free of complications procedure. In patients with severe coagulopathies or diseases such as HHT, the risk of nosebleeding may be high. As in all those conditions like advanced stage sinonasal neoplasms or unfavorable anatomical characteristics, the nasopharyngeal swab may not be feasible.

This work reports a safe and effective procedure of nasopharyngeal swab collection for COVID-19 testing, through the transoral way, in patients with contraindication to perform it transnasally.

The procedure proved feasible and well tolerated. The discomfort for the patient is comparable with the execution of an oropharyngeal swab without exposing him to additional complications.

In selected cases, the procedure described represents a valid alternative to nasopharyngeal swab performed transnasally. In particular, it allows reaching the area with the highest diagnostic sensitivity. Moreover it can be performed by Otolaryngology and, with adequate training, also by non-specialist staff.

Recent advances in nanomaterials based biosensors for point of care (PoC) diagnosis of Covid-19 - A minireview

Early diagnosis and ultrahigh sample throughput screening are the need of the hour to control the geological spread of the COVID-19 pandemic. Traditional laboratory tests such as enzyme-linked immunosorbent assay (ELISA), reverse transcription polymerase chain reaction (RT-PCR) and computed tomography are implemented for the detection of COVID-19. However, they are limited by the laborious sample collection and processing procedures, longer wait time for test results and skilled technicians to operate sophisticated facilities. In this context, the point of care (PoC) diagnostic platform has proven to be the prospective approach in addressing the abovementioned challenges. This review emphasizes the mechanism of viral infection spread detailing the host-virus interaction, pathophysiology, and the recent advances in the development of affordable PoC diagnostic platforms for rapid and accurate diagnosis of COVID-19. First, the well-established optical and electrochemical biosensors are discussed. Subsequently, the recent advances in the development of PoC biosensors, including lateral flow immunoassays and other emerging techniques, are highlighted. Finally, a focus on integrating nanotechnology with wearables and smartphones to develop smart nanobiosensors is outlined, which could promote COVID-19 diagnosis accessible to both individuals and the mass population at patient care.

Chest X-ray image phase features for improved diagnosis of COVID-19 using convolutional neural network

Purpose:

Recently, the outbreak of the novel coronavirus disease 2019 (COVID-19) pandemic has seriously endangered human health and life. In fighting against COVID-19, effective diagnosis of infected patient is critical for preventing the spread of diseases. Due to limited availability of test kits, the need for auxiliary diagnostic approach has increased. Recent research has shown radiography of COVID-19 patient, such as CT and X-ray, contains salient information about the COVID-19 virus and could be used as an alternative diagnosis method. Chest X-ray (CXR) due to its faster imaging time, wide availability, low cost, and portability gains much attention and becomes very promising. In order to reduce intra- and inter-observer variability, during radiological assessment, computer-aided diagnostic tools have been used in order to supplement medical decision making and subsequent management. Computational methods with high accuracy and robustness are required for rapid triaging of patients and aiding radiologist in the interpretation of the collected data.

Method:

In this study, we design a novel multi-feature convolutional neural network (CNN) architecture for multi-class improved classification of COVID-19 from CXR images. CXR images are enhanced using a local phase-based image enhancement method. The enhanced images, together with the original CXR data, are used as an input to our proposed CNN architecture. Using ablation studies, we show the effectiveness of the enhanced images in improving the diagnostic accuracy. We provide quantitative evaluation on two datasets and qualitative results for visual inspection. Quantitative evaluation is performed on data consisting of 8851 normal (healthy), 6045 pneumonia, and 3323 COVID-19 CXR scans.

Results:

In Dataset-1, our model achieves 95.57% average accuracy for a three classes classification, 99% precision, recall, and F1-scores for COVID-19 cases. For Dataset-2, we have obtained 94.44% average accuracy, and 95% precision, recall, and F1-scores for detection of COVID-19.

Conclusions:

Our proposed multi-feature-guided CNN achieves improved results compared to single-feature CNN proving the importance of the local phase-based CXR image enhancement. Future work will involve further evaluation of the proposed method on a larger-size COVID-19 dataset as they become available.

On the Challenges for the Diagnosis of SARS-CoV-2 Based on a Review of Current Methodologies

Diagnosis of COVID-19 has been challenging owing to the need for mass testing and for combining distinct types of detection to cover the different stages of the infection. In this review, we have surveyed the most used methodologies for diagnosis of COVID-19, which can be basically categorized into genetic-material detection and immunoassays. Detection of genetic material with real-time polymerase chain reaction (RT-PCR) and similar techniques has been achieved with high accuracy, but these methods are expensive and require time-consuming protocols which are not widely available, especially in less developed countries. Immunoassays for detecting a few antibodies, on the other hand, have been used for rapid, less expensive tests, but their accuracy in diagnosing infected individuals has been limited. We have therefore discussed the strengths and limitations of all of these methodologies, particularly in light of the required combination of tests owing to the long incubation periods. We identified the bottlenecks that prevented mass testing in many countries, and proposed strategies for further action, which are mostly associated with materials science and chemistry. Of special relevance are the methodologies which can be integrated into point-of-care (POC) devices and the use of artificial intelligence that do not require products from a well-developed biotech industry.

Improving the performance of CNN to predict the likelihood of COVID-19 using chest X-ray images with preprocessing algorithms

OBJECTIVE

This study aims to develop and test a new computer-aided diagnosis (CAD) scheme of chest X-ray images to detect coronavirus (COVID-19) infected pneumonia.

METHOD

CAD scheme first applies two image preprocessing steps to remove the majority of diaphragm regions, process the original image using a histogram equalization algorithm, and a bilateral low-pass filter. Then, the original image and two filtered images are used to form a pseudo color image. This image is fed into three input channels of a transfer learning-based convolutional neural network (CNN) model to classify chest X-ray images into 3 classes of COVID-19 infected pneumonia, other community-acquired no-COVID-19 infected pneumonia, and normal (non-pneumonia) cases. To build and test the CNN model, a publicly available dataset involving 8474 chest X-ray images is used, which includes 415, 5179 and 2,880 cases in three classes, respectively. Dataset is randomly divided into 3 subsets namely, training, validation, and testing with respect to the same frequency of cases in each class to train and test the CNN model.

RESULTS

The CNN-based CAD scheme yields an overall accuracy of 94.5 % (2404/2544) with a 95 % confidence interval of [0.93,0.96] in classifying 3 classes. CAD also yields 98.4 % sensitivity (124/126) and 98.0 % specificity (2371/2418) in classifying cases with and without COVID-19 infection. However, without using two preprocessing steps, CAD yields a lower classification accuracy of 88.0 % (2239/2544).

CONCLUSION

This study demonstrates that adding two image preprocessing steps and generating a pseudo color image plays an important role in developing a deep learning CAD scheme of chest X-ray images to improve accuracy in detecting COVID-19 infected pneumonia.

The diagnostic methods in the COVID-19 pandemic, today and in the future

INTRODUCTION

The emergence of anovel coronavirus identified in patients with unknown cause of acute respiratory disease in Wuhan, China at the end of 2019 has caused aglobal outbreak. The causative coronavirus was later named as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and the disease caused by SARS-CoV-2 was named as Coronavirus Disease-2019 (COVID-19). As of 10 August 2020, more than 19,718,030 confirmed cases and 728,013 deaths have been reported. COVID-19 is spread via respiratory droplets which are inhaled into the lungs.

AREAS COVERED

In this article, we summarized the knowledge about the causative pathogen of COVID-19 and various diagnostic methods in this pandemic for better understanding of the limitations and the nuances of virus testing for COVID-19.

EXPERT OPINION

In this pandemic, rapid and accurate identification of COVID-19 patients are critical to break the chain of infection in the community. RT-PCR provides a rapid and reliable identification of SARS-CoV-2 infection. In the future, molecular diagnostics will still be the gold standard and next-generation sequencing can help us to understand more on the pathogenesis and detect novel mutations. It is believed that more sophisticated detection methods will be introduced to detect SARS-CoV-2 as earliest as possible.

COVID-19 diagnosis and management: a comprehensive review

Severe acute respiratory syndrome coronavirus (SARS-CoV)-2, a novel coronavirus from the same family as SARS-CoV and Middle East respiratory syndrome coronavirus, has spread worldwide leading the World Health Organization to declare a pandemic. The disease caused by SARS-CoV-2, coronavirus disease 2019 (COVID-19), presents flu-like symptoms which can become serious in high-risk individuals. Here, we provide an overview of the known clinical features and treatment options for COVID-19. We carried out a systematic literature search using the main online databases (PubMed, Google Scholar, MEDLINE, UpToDate, Embase and Web of Science) with the following keywords: 'COVID-19', '2019-nCoV', 'coronavirus' and 'SARS-CoV-2'. We included publications from 1 January 2019 to 3 April 2020 which focused on clinical features and treatments. We found that infection is transmitted from human to human and through contact with contaminated environmental surfaces. Hand hygiene is fundamental to prevent contamination. Wearing personal protective equipment is recommended in specific environments. The main symptoms of COVID-19 are fever, cough, fatigue, slight dyspnoea, sore throat, headache, conjunctivitis and gastrointestinal issues. Real-time PCR is used as a diagnostic tool using nasal swab, tracheal aspirate or bronchoalveolar lavage samples. Computed tomography findings are important for both diagnosis and follow-up. To date, there is no evidence of any effective treatment for COVID-19. The main therapies being used to treat the disease are antiviral drugs, chloroquine/hydroxychloroquine and respiratory therapy. In conclusion, although many therapies have been proposed, quarantine is the only intervention that appears to be effective in decreasing the contagion rate. Specifically designed randomized clinical trials are needed to determine the most appropriate evidence-based treatment modality.

CovXNet: A multi-dilation convolutional neural network for automatic COVID-19 and other pneumonia detection from chest X-ray images with transferable multi-receptive feature optimization

With the recent outbreak of COVID-19, fast diagnostic testing has become one of the major challenges due to the critical shortage of test kit. Pneumonia, a major effect of COVID-19, needs to be urgently diagnosed along with its underlying reasons. In this paper, deep learning aided automated COVID-19 and other pneumonia detection schemes are proposed utilizing a small amount of COVID-19 chest X-rays. A deep convolutional neural network (CNN) based architecture, named as CovXNet, is proposed that utilizes depthwise convolution with varying dilation rates for efficiently extracting diversified features from chest X-rays. Since the chest X-ray images corresponding to COVID-19 caused pneumonia and other traditional pneumonias have significant similarities, at first, a large number of chest X-rays corresponding to normal and (viral/bacterial) pneumonia patients are used to train the proposed CovXNet. Learning of this initial training phase is transferred with some additional fine-tuning layers that are further trained with a smaller number of chest X-rays corresponding to COVID-19 and other pneumonia patients. In the proposed method, different forms of CovXNets are designed and trained with X-ray images of various resolutions and for further optimization of their predictions, a stacking algorithm is employed. Finally, a gradient-based discriminative localization is integrated to distinguish the abnormal regions of X-ray images referring to different types of pneumonia. Extensive experimentations using two different datasets provide very satisfactory detection performance with accuracy of 97.4% for COVID/Normal, 96.9% for COVID/Viral pneumonia, 94.7% for COVID/Bacterial pneumonia, and 90.2% for multiclass COVID/normal/Viral/Bacterial pneumonias. Hence, the proposed schemes can serve as an efficient tool in the current state of COVID-19 pandemic. All the architectures are made publicly available at: https://github.com/Perceptron21/CovXNet.

Evaluation of Nucleocapsid and Spike Protein-Based Enzyme-Linked Immunosorbent Assays for Detecting Antibodies against SARS-CoV-2

At present, PCR-based nucleic acid detection cannot meet the demands for coronavirus infectious disease (COVID-19) diagnosis. Two hundred fourteen confirmed COVID-19 patients who were hospitalized in the General Hospital of Central Theater Command of the People’s Liberation Army between 18 January and 26 February 2020 were recruited. Two enzyme-linked immunosorbent assay (ELISA) kits based on recombinant severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) nucleocapsid protein (rN) and spike protein (rS) were used for detecting IgM and IgG antibodies, and their diagnostic feasibility was evaluated.

At present, PCR-based nucleic acid detection cannot meet the demands for coronavirus infectious disease (COVID-19) diagnosis. Two hundred fourteen confirmed COVID-19 patients who were hospitalized in the General Hospital of Central Theater Command of the People’s Liberation Army between 18 January and 26 February 2020 were recruited. Two enzyme-linked immunosorbent assay (ELISA) kits based on recombinant severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) nucleocapsid protein (rN) and spike protein (rS) were used for detecting IgM and IgG antibodies, and their diagnostic feasibility was evaluated. Among the 214 patients, 146 (68.2%) and 150 (70.1%) were successfully diagnosed with the rN-based IgM and IgG ELISAs, respectively; 165 (77.1%) and 159 (74.3%) were successfully diagnosed with the rS-based IgM and IgG ELISAs, respectively. The positive rates of the rN-based and rS-based ELISAs for antibody (IgM and/or IgG) detection were 80.4% and 82.2%, respectively. The sensitivity of the rS-based ELISA for IgM detection was significantly higher than that of the rN-based ELISA. We observed an increase in the positive rate for IgM and IgG with an increasing number of days post-disease onset (d.p.o.), but the positive rate of IgM dropped after 35 d.p.o. The positive rate of rN-based and rS-based IgM and IgG ELISAs was less than 60% during the early stage of the illness, 0 to 10 d.p.o., and that of IgM and IgG was obviously increased after 10 d.p.o. ELISA has a high sensitivity, especially for the detection of serum samples from patients after 10 d.p.o., so it could be an important supplementary method for COVID-19 diagnosis.