Machine learning to analyse omic-data for COVID-19 diagnosis and prognosis.

BACKGROUND: With the global spread of COVID-19, the world has seen many patients, including many severe cases. The rapid development of machine learning (ML) has made significant disease diagnosis and prediction achievements. Current studies have confirmed that omics data at the host level can reflect the development process and prognosis of the disease. Since early diagnosis and effective treatment of severe COVID-19 patients remains challenging, this research aims to use omics data in different ML models for COVID-19 diagnosis and prognosis. We used several ML models on omics data of a large number of individuals to first predict whether patients are COVID-19 positive or negative, followed by the severity of the disease. RESULTS: On the COVID-19 diagnosis task, we got the best AUC of 0.99 with our multilayer perceptron model and the highest F1-score of 0.95 with our logistic regression (LR) model. For the severity prediction task, we achieved the highest accuracy of 0.76 with an LR model. Beyond classification and predictive modeling, our study founds ML models performed better on integrated multi-omics data, rather than single omics. By comparing top features from different omics dataset, we also found the robustness of our model, with a wider range of applicability in diverse dataset related to COVID-19. Additionally, we have found that omics-based models performed better than image or physiological feature-based models, proving the importance of the omics-based dataset for future model development. CONCLUSIONS: This study diagnoses COVID-19 positive cases and predicts accurate severity levels. It lowers the dependence on clinical data and professional judgment, by leveraging the utilization of state-of-the-art models. our model showed wider applicability across different omics dataset, which is highly transferable in other respiratory or similar diseases. Hospital and public health care mechanisms can optimize the distribution of medical resources and improve the robustness of the medical system.

Application of ultrasensitive assay for SARS-CoV-2 antigen in nasopharynx in the management of COVID-19 patients with comorbidities during the peak of 2022 Shanghai epidemics in a tertiary hospital.

OBJECTIVES: Various comorbidities associated with COVID-19 add up in severity of the disease and obviously prolonged the time for viral clearance. This study investigated a novel ultrasensitive MAGLUMI® SARS-CoV-2 Ag chemiluminescent immunoassay assay (MAG-CLIA) for diagnosis and monitoring the infectivity of COVID-19 patients with comorbid conditions during the pandemic of 2022 Shanghai. METHODS: Analytical performances of the MAG-CLIA were evaluated, including precision, limit of quantitation, linearity and specificity. Nasopharyngeal specimens from 232 hospitalized patients who were SARS-CoV-2 RT-qPCR positive and from 477 healthy donors were included. The longitudinal studies were performed by monitoring antigen concentrations alongside with RT-qPCR results in 14 COVID-19 comorbid participants for up to 22 days. The critical antigen concentration in determining virus infectivity was evaluated at the reference cycle threshold (Ct) of 35. RESULTS: COVID-19 patients were well-identified using an optimal threshold of 0.64 ng/L antigen concentration, with sensitivity and specificity of 95.7% (95% CI: 92.2-97.9%) and 98.3% (95% CI: 96.7-99.3%), respectively, while the Wondfo LFT exhibited those of 34.9% (95% CI: 28.8-41.4%) and 100% (95% CI: 99.23-100%), respectively. The sensitivity of MAG-CLIA remained 91.46% (95% CI: 83.14-95.8%) for the samples with Ct values between 35 and 40. Close dynamic consistence was observed between MAG-CLIA and viral load time series in the longitudinal studies. The critical value of 8.82 ng/L antigen showed adequate sensitivity and specificity in evaluating the infectivity of hospitalized convalescent patients with comorbidities. CONCLUSIONS: The MAG-CLIA SARS-CoV-2 Ag detection is an effective and alternative approach for rapid diagnosis and enables us to evaluate the infectivity of hospitalized convalescent patients with comorbidities.

COV-MobNets: a mobile networks ensemble model for diagnosis of COVID-19 based on chest X-ray images.

BACKGROUND: The medical profession is facing an excessive workload, which has led to the development of various Computer-Aided Diagnosis (CAD) systems as well as Mobile-Aid Diagnosis (MAD) systems. These technologies enhance the speed and accuracy of diagnoses, particularly in areas with limited resources or remote regions during the pandemic. The primary purpose of this research is to predict and diagnose COVID-19 infection from chest X-ray images by developing a mobile-friendly deep learning framework, which has the potential for deployment in portable devices such as mobile or tablet, especially in situations where the workload of radiology specialists may be high. Moreover, this could improve the accuracy and transparency of population screening to assist radiologists during the pandemic. METHODS: In this study, the Mobile Networks ensemble model called COV-MobNets is proposed to classify positive COVID-19 X-ray images from negative ones and can have an assistant role in diagnosing COVID-19. The proposed model is an ensemble model, combining two lightweight and mobile-friendly models: MobileViT based on transformer structure and MobileNetV3 based on Convolutional Neural Network. Hence, COV-MobNets can extract the features of chest X-ray images in two different methods to achieve better and more accurate results. In addition, data augmentation techniques were applied to the dataset to avoid overfitting during the training process. The COVIDx-CXR-3 benchmark dataset was used for training and evaluation. RESULTS: The classification accuracy of the improved MobileViT and MobileNetV3 models on the test set has reached 92.5% and 97%, respectively, while the accuracy of the proposed model (COV-MobNets) has reached 97.75%. The sensitivity and specificity of the proposed model have also reached 98.5% and 97%, respectively. Experimental comparison proves the result is more accurate and balanced than other methods. CONCLUSION: The proposed method can distinguish between positive and negative COVID-19 cases more accurately and quickly. The proposed method proves that utilizing two automatic feature extractors with different structures as an overall framework of COVID-19 diagnosis can lead to improved performance, enhanced accuracy, and better generalization to new or unseen data. As a result, the proposed framework in this study can be used as an effective method for computer-aided diagnosis and mobile-aided diagnosis of COVID-19. The code is available publicly for open access at https://github.com/MAmirEshraghi/COV-MobNets .

COVID-19 diagnosis utilizing wavelet-based contrastive learning with chest CT images.

The pandemic caused by the coronavirus disease 2019 (COVID-19) has continuously wreaked havoc on human health. Computer-aided diagnosis (CAD) system based on chest computed tomography (CT) has been a hotspot option for COVID-19 diagnosis. However, due to the high cost of data annotation in the medical field, it happens that the number of unannotated data is much larger than the annotated data. Meanwhile, having a highly accurate CAD system always requires a large amount of labeled data training. To solve this problem while meeting the needs, this paper presents an automated and accurate COVID-19 diagnosis system using few labeled CT images. The overall framework of this system is based on the self-supervised contrastive learning (SSCL). Based on the framework, our enhancement of our system can be summarized as follows. 1) We integrated a two-dimensional discrete wavelet transform with contrastive learning to fully use all the features from the images. 2) We use the recently proposed COVID-Net as the encoder, with a redesign to target the specificity of the task and learning efficiency. 3) A new pretraining strategy based on contrastive learning is applied for broader generalization ability. 4) An additional auxiliary task is exerted to promote performance during classification. The final experimental result of our system attained 93.55%, 91.59%, 96.92% and 94.18% for accuracy, recall, precision, and F1-score respectively. By comparing results with the existing schemes, we demonstrate the performance enhancement and superiority of our proposed system.

Momentum contrast transformer for COVID-19 diagnosis with knowledge distillation.

Intelligent diagnosis has been widely studied in diagnosing novel corona virus disease (COVID-19). Existing deep models typically do not make full use of the global features such as large areas of ground glass opacities, and the local features such as local bronchiolectasis from the COVID-19 chest CT images, leading to unsatisfying recognition accuracy. To address this challenge, this paper proposes a novel method to diagnose COVID-19 using momentum contrast and knowledge distillation, termed MCT-KD. Our method takes advantage of Vision Transformer to design a momentum contrastive learning task to effectively extract global features from COVID-19 chest CT images. Moreover, in transfer and fine-tuning process, we integrate the locality of convolution into Vision Transformer via special knowledge distillation. These strategies enable the final Vision Transformer simultaneously focuses on global and local features from COVID-19 chest CT images. In addition, momentum contrastive learning is self-supervised learning, solving the problem that Vision Transformer is challenging to train on small datasets. Extensive experiments confirm the effectiveness of the proposed MCT-KD. In particular, our MCT-KD is able to achieve 87.43% and 96.94% accuracy on two publicly available datasets, respectively.

Capacitive immunosensor for COVID-19 diagnosis.

COVID-19 has spread worldwide and early detection has been the key to controlling its propagation and preventing severe cases. However, diagnostic devices must be developed using different strategies to avoid a shortage of supplies needed for tests' fabrication caused by their large demand in pandemic situations. Furthermore, some tropical and subtropical countries are also facing epidemics of Dengue and Zika, viruses with similar symptoms in early stages and cross-reactivity in serological tests. Herein, we reported a qualitative immunosensor based on capacitive detection of spike proteins of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the causative agent of COVID-19. The sensor device exhibited a good signal-to-noise ratio (SNR) at 1 kHz frequency, with an absolute value of capacitance variation significantly smaller for Dengue and Zika NS1 proteins (|ΔC| = 1.5 ± 1.0 nF and 1.8 ± 1.0 nF, respectively) than for the spike protein (|ΔC| = 7.0 ± 1.8 nF). Under the optimized conditions, the established biosensor is able to indicate that the sample contains target proteins when |ΔC| > 3.8 nF, as determined by the cut-off value (CO). This immunosensor was developed using interdigitated electrodes which require a measurement system with a simple electrical circuit that can be miniaturized to enable point-of-care detection, offering an alternative for COVID-19 diagnosis, especially in areas where there is also a co-incidence of Zika and Dengue.

Comparison of SARS-CoV-2 Detection in Nasopharyngeal Swab and Saliva Samples from Patients Infected with Omicron Variant.

To compare the detection of the SARS-CoV-2 Omicron variant in nasopharyngeal-swab (NPS) and oral saliva samples. 255 samples were obtained from 85 Omicron-infected patients. SARS-CoV-2 load was measured in the NPS and saliva samples by using Simplexa™ COVID-19 direct and Alinity m SARS-CoV-2 AMP assays. Results obtained with the two diagnostic platforms showed very good inter-assay concordance (91.4 and 82.4% for saliva and NPS samples, respectively) and a significant correlation among cycle threshold (Ct) values. Both platforms revealed a highly significant correlation among Ct obtained in the two matrices. Although the median Ct value was lower in NPS than in saliva samples, the Ct drop was comparable in size for both types of samples after 7 days of antiviral treatment of the Omicron-infected patients. Our result demonstrates that the detection of the SARS-CoV-2 Omicron variant is not influenced by the type of sample used for PCR analysis, and that saliva can be used as an alternative specimen for detection and follow-up of Omicron-infected patients.

Sandwich ELISA for the Quantification of Nucleocapsid Protein of SARS-CoV-2 Based on Polyclonal Antibodies from Two Different Species.

In this study, a cost-effective sandwich ELISA test, based on polyclonal antibodies, for routine quantification SARS-CoV-2 nucleocapsid (N) protein was developed. The recombinant N protein was produced and used for the production of mice and rabbit antisera. Polyclonal N protein-specific antibodies served as capture and detection antibodies. The prototype ELISA has LOD 0.93 ng/mL and LOQ 5.3 ng/mL, with a linear range of 1.52-48.83 ng/mL. N protein heat pretreatment (56 °C, 1 h) decreased, while pretreatment with 1% Triton X-100 increased analytical ELISA sensitivity. The diagnostic specificity of ELISA was 100% (95% CI, 91.19-100.00%) and sensitivity was 52.94% (95% CI, 35.13-70.22%) compared to rtRT-PCR (Ct < 40). Profoundly higher sensitivity was obtained using patient samples mostly containing Wuhan-similar variants (Wuhan, alpha, and delta), 62.50% (95% CI, 40.59 to 81.20%), in comparison to samples mostly containing Wuhan-distant variants (Omicron) 30.00% (6.67-65.25%). The developed product has relatively high diagnostic sensitivity in relation to its analytical sensitivity due to the usage of polyclonal antibodies from two species, providing a wide repertoire of antibodies against multiple N protein epitopes. Moreover, the fast, simple, and inexpensive production of polyclonal antibodies, as the most expensive assay components, would result in affordable antigen tests.

Omnidirectional 2.5D representation for COVID-19 diagnosis using chest CTs.

The Coronavirus Disease 2019 (COVID-19) has drastically overwhelmed most countries in the last two years, and image-based approaches using computerized tomography (CT) have been used to identify pulmonary infections. Recent methods based on deep learning either require time-consuming per-slice annotations (2D) or are highly data- and hardware-demanding (3D). This work proposes a novel omnidirectional 2.5D representation of volumetric chest CTs that allows exploring efficient 2D deep learning architectures while requiring volume-level annotations only. Our learning approach uses a siamese feature extraction backbone applied to each lung. It combines these features into a classification head that explores a novel combination of Squeeze-and-Excite strategies with Class Activation Maps. We experimented with public and in-house datasets and compared our results with state-of-the-art techniques. Our analyses show that our method provides better or comparable prediction quality and accurately distinguishes COVID-19 infections from other kinds of pneumonia and healthy lungs.

Detection of Covid-19 and other pneumonia cases from CT and X-ray chest images using deep learning based on feature reuse residual block and depthwise dilated convolutions neural network.

Covid-19 has become a worldwide epidemic which has caused the death of millions in a very short time. This disease, which is transmitted rapidly, has mutated and different variations have emerged. Early diagnosis is important to prevent the spread of this disease. In this study, a new deep learning-based architecture is proposed for rapid detection of Covid-19 and other symptoms using CT and X-ray chest images. This method, called CovidDWNet, is based on a structure based on feature reuse residual block (FRB) and depthwise dilated convolutions (DDC) units. The FRB and DDC units efficiently acquired various features in the chest scan images and it was seen that the proposed architecture significantly improved its performance. In addition, the feature maps obtained with the CovidDWNet architecture were estimated with the Gradient boosting (GB) algorithm. With the CovidDWNet+GB architecture, which is a combination of CovidDWNet and GB, a performance increase of approximately 7% in CT images and between 3% and 4% in X-ray images has been achieved. The CovidDWNet+GB architecture achieved the highest success compared to other architectures, with 99.84% and 100% accuracy rates, respectively, on different datasets containing binary class (Covid-19 and Normal) CT images. Similarly, the proposed architecture showed the highest success with 96.81% accuracy in multi-class (Covid-19, Lung Opacity, Normal and Viral Pneumonia) X-ray images and 96.32% accuracy in the dataset containing X-ray and CT images. When the time to predict the disease in CT or X-ray images is examined, it is possible to say that it has a high speed because the CovidDWNet+GB method predicts thousands of images within seconds.

Improved deep convolutional neural networks using chimp optimization algorithm for Covid19 diagnosis from the X-ray images.

Applying Deep Learning (DL) in radiological images (i.e., chest X-rays) is emerging because of the necessity of having accurate and fast COVID-19 detectors. Deep Convolutional Neural Networks (DCNN) have been typically used as robust COVID-19 positive case detectors in these approaches. Such DCCNs tend to utilize Gradient Descent-Based (GDB) algorithms as the last fully-connected layers' trainers. Although GDB training algorithms have simple structures and fast convergence rates for cases with large training samples, they suffer from the manual tuning of numerous parameters, getting stuck in local minima, large training samples set requirements, and inherently sequential procedures. It is exceedingly challenging to parallelize them with Graphics Processing Units (GPU). Consequently, the Chimp Optimization Algorithm (ChOA) is presented for training the DCNN's fully connected layers in light of the scarcity of a big COVID-19 training dataset and for the purpose of developing a fast COVID-19 detector with the capability of parallel implementation. In addition, two publicly accessible datasets termed COVID-Xray-5 k and COVIDetectioNet are used to benchmark the proposed detector known as DCCN-Chimp. In order to make a fair comparison, two structures are proposed: i-6c-2 s-12c-2 s and i-8c-2 s-16c-2 s, all of which have had their hyperparameters fine-tuned. The outcomes are evaluated in comparison to standard DCNN, Hybrid DCNN plus Genetic Algorithm (DCNN-GA), and Matched Subspace classifier with Adaptive Dictionaries (MSAD). Due to the large variation in results, we employ a weighted average of the ensemble of ten trained DCNN-ChOA, with the validation accuracy of the weights being used to determine the final weights. The validation accuracy for the mixed ensemble DCNN-ChOA is 99.11%. LeNet-5 DCNN's ensemble detection accuracy on COVID-19 is 84.58%. Comparatively, the suggested DCNN-ChOA yields over 99.11% accurate detection with a false alarm rate of less than 0.89%. The outcomes show that the DCCN-Chimp can deliver noticeably superior results than the comparable detectors. The Class Activation Map (CAM) is another tool used in this study to identify probable COVID-19-infected areas. Results show that highlighted regions are completely connected with clinical outcomes, which has been verified by experts.

Diagnostic performance of RT-PCR-based sample pooling strategy for the detection of SARS-CoV-2.

BACKGROUND: The rapid spread of SARS-CoV-2 has created a shortage of supplies of reagents for its detection throughout the world, especially in Latin America. The pooling of samples consists of combining individual patient samples in a block and analyzing the group as a particular sample. This strategy has been shown to reduce the burden of laboratory material and logistical resources by up to 80%. Therefore, we aimed to evaluate the diagnostic performance of the pool of samples analyzed by RT-PCR to detect SARS-CoV-2. METHODS: A cross-sectional study of diagnostic tests was carried out. We individually evaluated 420 samples, and 42 clusters were formed, each one with ten samples. These clusters could contain 0, 1 or 2 positive samples to simulate a positivity of 0, 10 and 20%, respectively. RT-PCR analyzed the groups for the detection of SARS-CoV-2. The area under the ROC curve (AUC), the Youden index, the global and subgroup sensitivity and specificity were calculated according to their Ct values that were classified as high (H: ≤ 25), moderate (M: 26-30) and low (L: 31-35) concentration of viral RNA. RESULTS: From a total of 42 pools, 41 (97.6%) obtained the same result as the samples they contained (positive or negative). The AUC for pooling, Youden index, sensitivity, and specificity were 0.98 (95% CI, 0.95-1); 0.97 (95% CI, 0.90-1.03); 96.67% (95% CI; 88.58-100%) and 100% (95% CI; 95.83-100%) respectively. In the stratified analysis of the pools containing samples with Ct ≤ 25, the sensitivity was 100% (95% CI; 90-100%), while with the pools containing samples with Ct ≥ 31, the sensitivity was 80% (95% CI, 34.94-100%). Finally, a higher median was observed in the Ct of the clusters, with respect to the individual samples (p < 0.001). CONCLUSIONS: The strategy of pooling nasopharyngeal swab samples for analysis by SARS-CoV-2 RT-PCR showed high diagnostic performance.

COVID-19 diagnosis by SARS-CoV-2 Spike protein detection in saliva using an ultrasensitive magneto-assay based on disposable electrochemical sensor.

The outbreak of the COVID-19 pandemic, caused by Severe Acute Respiratory Syndrome of Coronavirus 2 (SARS-CoV-2), has fueled the search for diagnostic tests aiming at the control and reduction of the viral transmission. The main technique used for diagnosing the Coronavirus disease (COVID-19) is the reverse transcription-polymerase chain reaction (RT-PCR) technique. However, considering the high number of cases and the underlying limitations of the RT-PCR technique, especially with regard to accessibility and cost of the test, one does not need to overemphasize the need to develop new and less expensive testing techniques that can aid the early diagnosis of the disease. With that in mind, we developed an ultrasensitive magneto-assay using magnetic beads and gold nanoparticles conjugated to human angiotensin-converting enzyme 2 (ACE2) peptide (Gln24-Gln42) for the capturing and detection of SARS-CoV-2 Spike protein in human saliva. The technique applied involved the use of a disposable electrochemical device containing eight screen-printed carbon electrodes which allow the simultaneous analysis of eight samples. The magneto-assay exhibited an ultralow limit of detection of 0.35 ag mL-1 for the detection of SARS-CoV-2 Spike protein in saliva. The magneto-assay was tested in saliva samples from healthy and SARS-CoV-2-infected individuals. In terms of efficiency, the proposed technique - which presented a sensitivity of 100.0% and specificity of 93.7% for SARS-CoV-2 Spike protein-exhibited great similarity with the RT-PCR technique. The results obtained point to the application potential of this simple, low-cost magneto-assay for saliva-based point-of-care COVID-19 diagnosis.

Factors influencing the performance of rapid SARS-CoV-2 antigen tests under field condition.

BACKGROUND: Globally, real-time reverse transcription-polymerase chain reaction (rRT-PCR) is the reference detection technique for SARS-CoV-2, which is expensive, time consuming, and requires trained laboratory personnel. Thus, a cost-effective, rapid antigen test is urgently needed. This study evaluated the performance of the rapid antigen tests (RATs) for SARS-CoV-2 compared with rRT-PCR, considering different influencing factors. METHODS: We enrolled a total of 214 symptomatic individuals with known COVID-19 status using rRT-PCR. We collected and tested paired nasopharyngeal (NP) and nasal swab (NS) specimens (collected from same individual) using rRT-PCR and RATs (InTec and SD Biosensor). We assessed the performance of RATs considering specimen types, viral load, the onset of symptoms, and presenting symptoms. RESULTS: We included 214 paired specimens (112 NP and 100 NS SARS-CoV-2 rRT-PCR positive) to the analysis. For NP specimens, the average sensitivity, specificity, and accuracy of the RATs were 87.5%, 98.6%, and 92.8%, respectively, when compared with rRT-PCR. While for NS, the overall kit performance was slightly lower than that of NP (sensitivity 79.0%, specificity 96.1%, and accuracy 88.3%). We observed a progressive decline in the performance of RATs with increased Ct values (decreased viral load). Moreover, the RAT sensitivity using NP specimens decreased over the time of the onset of symptoms. CONCLUSION: The RATs showed strong performance under field conditions and fulfilled the minimum performance limit for rapid antigen detection kits recommended by World Health Organization. The best performance of the RATs can be achieved within the first week of the onset of symptoms with high viral load.

Proof-of-concept for speedy development of rapid and simple at-home method for potential diagnosis of early COVID-19 mutant infections using nanogold and aptamer.

The positive single-stranded nature of COVID-19 mRNA led to the low proof-reading efficacy for its genome authentication. Thus mutant covid-19 strains have been rapidly evolving. Besides Alpha, Beta, Gamma, Delta, and Omicron variants, currently, subvariants of omicron are circulating, including BA.4, BA.5, and BA.2.12.1. Therefore, the speedy development of a rapid, simple, and easier diagnosis method to deal with new mutant covid viral infection is critically important. Many diagnosis methods have been developed for COVID-19 detection such as RT-PCR and antibodies detection. However, the former is time-consuming, laborious, and expensive, and the latter relies on the production of antibodies making it not suitable for the early diagnosis of viral infection. Many lateral-flow methods are available but might not be suitable for detecting the mutants, Here we proved the concept for the speedy development of a simple, rapid, and cost-effective early at-home diagnosis method for mutant Covid-19 infection by combining a new aptamer. The idea is to use the current lateral flow Covid-19 diagnosis system available in the market or to use one existing antibody for the Lateral Flow Nitrocellulose filter. To prove the concept, the DNA aptamer specific to spike proteins (S-proteins) was conjugated to gold nanoparticles and served as a detection probe. An antibody that is specific to spike proteins overexpressed on COVID viral particles was used as a second probe immobilized to the nitrocellulose membrane. The aptamer conjugated nanoparticles were incubated with spike proteins for half an hour and tested for their ability to bind to antibodies anchored on the nitrocellulose membrane. The gold nanoparticles were visualized on the nitrocellulose membrane due to interaction between the antigen (S-protein) with both the aptamer and the antibody. Thus, the detection of viral antigen can be obtained within 2 h, with a cost of less than $5 for the diagnosis reagent. In the future, as long as the mutant of the newly emerged viral surface protein is reported, a peptide or protein corresponding to the mutation can be produced by peptide synthesis or gene cloning within several days. An RNA or DNA aptamer can be generated quickly via SELEX. A gold-labeled aptamer specific to spike proteins (S-proteins) will serve as a detection probe. Any available lateral-flow diagnosis kits with an immobilized antibody that has been available on the market, or simply an antibody that binds COVID-19 virus might be used as a second probe immobilized on the nitrocellulose. The diagnosis method can be carried out by patients at home if a clinical trial verifies the feasibility and specificity of this method.

Evaluation and comparison of eighteen SARS-CoV-2 antibody assays from seven different companies to assess its diagnostic role in SARS-CoV-2 infections.

The diagnostic performance of reverse transcriptase polymerase chain reaction (RT-PCR) decreases during the late acute stage of the corona virus disease (COVID-19) infection; hence, serological assays can be used for disease diagnosis in patients non-protected through vaccinations at this stage. The objective of this study was to assess the diagnostic accuracy of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) antibody tests in current/past infections, determine proper testing time, and check the accuracy of cutoff values. In this study, 18 Ig (immunoglobulin) G, IgM, IgA, and total antibody serological assays were performed using 839 samples. Positive sera (n=132) were collected during the first 5 months after the patients were symptomatic and tested positive for the SARS-CoV-2 RT-PCR test; they were grouped as 0-10, 10-15, >15 days according to the symptom onset. Negative sera (N=707) were obtained from patients with lupus before the pandemic. The performance of IgG and total antibody assays was better than those of IgA, IgM, and IgA-IgM for all post-symptom groups except for 0-10 days, which showed lower Ig assay sensitivity. During 10-15 and >15 days, >70% sensitivity to IgA, IgM, IgM-IgA assays and lower sensitivity were noted, respectively. The sensitivities of IgG and total antibody assays for group C were slightly lower than that of group B. There were no significant differences, but there were higher correlations between the methods or antigenic structures. Receiving operating characteristics (ROC) analysis revealed better cutoff values. For the diagnosis of late acute/past SARS-CoV-2 infection, serological tests can be performed on unvaccinated patients showing symptoms for ≥10 days. SARS-CoV-2 IgG and total antibodies were better diagnostic markers than IgM, IgA, and IgM+IgA, which were restricted to group B.

The Use of Audio Signals for Detecting COVID-19: A Systematic Review.

A systematic review on the topic of automatic detection of COVID-19 using audio signals was performed. A total of 48 papers were obtained after screening 659 records identified in the PubMed, IEEE Xplore, Embase, and Google Scholar databases. The reviewed studies employ a mixture of open-access and self-collected datasets. Because COVID-19 has only recently been investigated, there is a limited amount of available data. Most of the data are crowdsourced, which motivated a detailed study of the various pre-processing techniques used by the reviewed studies. Although 13 of the 48 identified papers show promising results, several have been performed with small-scale datasets (<200). Among those papers, convolutional neural networks and support vector machine algorithms were the best-performing methods. The analysis of the extracted features showed that Mel-frequency cepstral coefficients and zero-crossing rate continue to be the most popular choices. Less common alternatives, such as non-linear features, have also been proven to be effective. The reported values for sensitivity range from 65.0% to 99.8% and those for accuracy from 59.0% to 99.8%.

Handling class imbalance in COVID-19 chest X-ray images classification: Using SMOTE and weighted loss.

Healthcare systems worldwide have been struggling since the beginning of the COVID-19 pandemic. The early diagnosis of this unprecedented infection has become their ultimate objective. Detecting positive patients from chest X-ray images is a quick and efficient solution for overloaded hospitals. Many studies based on deep learning (DL) techniques have shown high performance in classifying COVID-19 chest X-ray images. However, most of these studies suffer from a class imbalance problem mainly due to the limited number of COVID-19 samples. Such a problem may significantly reduce the efficiency of DL classifiers. In this work, we aim to build an accurate model that assists clinicians in the early diagnosis of COVID-19 using balanced data. To this end, we trained six state-of-the-art convolutional neural networks (CNNs) via transfer learning (TL) on three different COVID-19 datasets. The models were developed to perform a multi-classification task that distinguishes between COVID-19, normal, and viral pneumonia cases. To address the class imbalance issue, we first investigated the Weighted Categorical Loss (WCL) and then the Synthetic Minority Oversampling Technique (SMOTE) on each dataset separately. After a comparative study of the obtained results, we selected the model that achieved high classification results in terms of accuracy, sensitivity, specificity, precision, F1 score, and AUC compared to other recent works. DenseNet201 and VGG-19 claimed the best scores. With an accuracy of 98.87%, an F1_Score of 98.21%, a sensitivity of 98.86%, a specificity of 99.43%, a precision of 100%, and an AUC of 99.15%, the WCL combined with CheXNet outperformed the other examined models.

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.

Multi-attention representation network partial domain adaptation for COVID-19 diagnosis.

The outbreak of COVID-19 threatens the safety of all human beings. Rapid and accurate diagnosis of patients is the effective way to prevent the rapid spread of COVID-19. The current computer-aided diagnosis of COVID-19 requires extensive labeled data for training, and this undoubtedly increases human and material resources costs. Domain adaptation (DA), an existing promising approach, can transfer knowledge from rich labeled pneumonia datasets for COVID-19 diagnosis and classification. However, due to the differences in feature distribution and task semantic between pneumonia and COVID-19, negative transfer may reduce the performance in diagnosis COVID-19 and pneumonia. Furthermore, the training data is usually mixed with many noise samples in practice, and this also poses new challenges for domain adaptation. As a kind of domain adaptation, partial domain adaptation (PDA) can well avoid outlier samples in the source domain and achieve good classification performance in the target domain. However, the existing PDA methods all learn a single feature representation; this can only learn local information about the inputs and ignore other important information in the samples. Therefore multi-attention representation network partial domain adaptation (MARPDA) is proposed in this paper to overcome the above shortcomings of PDA. In MARPDA, we construct the multiple representation networks with attention to acquire the image representation and effectively learn knowledge from different feature spaces. We design the sample-weighted strategy to achieve partial data transfer and address the negative transfer of noise data during training. MARPDA adapts to complex application scenarios and learns fine-grained features of the image from multiple representations. We apply the model to classify pneumonia and COVID-19 respectively, and evaluate it in qualitative and quantitative manners. The experimental results show that our classification accuracy is higher than that of the existing state-of-the-art methods. The stability and reliability of the proposed method are validated by the confusion matrix and the performance curves experiments. In summary, our method has better performance for diagnosis COVID-19 compared to the existing state-of-the-art methods.