Dynamics of anti-S IgG antibodies titers after the second dose of COVID 19 mRNA and non-mRNA vaccines in the manual and craft worker population of Qatar (preprint)

Background: There is limited sero epidemiological evidence on the magnitude and long-term durability of antibody titers of mRNA and non-mRNA vaccines in the Qatari population. This study was conducted to generate evidence on long-term anti-S IgG antibodies titers and their dynamics in individuals who have completed a primary COVID-19 vaccination schedule. Methods: A total of 300 participants who received any of the following vaccines BNT162b2/Comirnaty or mRNA-1273 or ChAdOx1-S/Covishield or COVID-19 Vaccine Janssen/Johnson or BBIBP-CorV or Covaxin were enrolled in our study. All sera samples were tested by chemiluminescent microparticle immunoassay (CMIA) for the quantitative determination of IgG antibodies to SARS-CoV-2, receptor-binding domain (RBD) of the S1 subunit of the spike protein of SARS-CoV-2. Antibodies against SARS-CoV-2 nucleocapsid (SARS-CoV-2 N-protein IgG) were also determined. Kaplan-Meier survival curves were used to compare the time from the last dose of the primary vaccination schedule to the time by which anti-S IgG antibodies titers fell into the lowest quartile (range of values collected) for the mRNA and non-mRNA vaccines. Results: Participants vaccinated with mRNA vaccines had higher median anti-S IgG antibody titers. Participants vaccinated with the mRNA-1273 vaccine had the highest median anti-S-antibody level of 13720.9 AU/mL (IQR 6426.5 to 30185.6 AU/mL) followed by BNT162b2 (median, 7570.9 AU/ml; IQR, 3757.9 to 16577.4 AU/mL); while the median anti-S antibody titer for non-mRNA vaccinated participants was 3759.7 AU/mL (IQR, 2059.7-5693.5 AU/mL). The median time to reach the lowest quartile was 3.53 months (IQR, 2.2-4.5 months) and 7.63 months (IQR, 6.3-8.4 months) for the non-mRNA vaccine recipients and Pfizer vaccine recipients, respectively. However, more than 50% of the Moderna vaccine recipients did not reach the lowest quartile by the end of the follow-up period. Conclusions: This evidence on anti-S IgG antibody titers, their durability and decay over time should be considered for the utility of these assays in transmission dynamics after the full course of primary vaccination.

BIO-CXRNET: A Robust Multimodal Stacking Machine Learning Technique for Mortality Risk Prediction of COVID-19 Patients using Chest X-Ray Images and Clinical Data (preprint)

Fast and accurate detection of the disease can significantly help in reducing the strain on the healthcare facility of any country to reduce the mortality during any pandemic. The goal of this work is to create a multimodal system using a novel machine learning framework that uses both Chest X-ray (CXR) images and clinical data to predict severity in COVID-19 patients. In addition, the study presents a nomogram-based scoring technique for predicting the likelihood of death in high-risk patients. This study uses 25 biomarkers and CXR images in predicting the risk in 930 COVID-19 patients admitted during the first wave of COVID-19 (March-June 2020) in Italy. The proposed multimodal stacking technique produced the precision, sensitivity, and F1-score, of 89.03%, 90.44%, and 89.03%, respectively to identify low or high-risk patients. This multimodal approach improved the accuracy by 6% in comparison to the CXR image or clinical data alone. Finally, nomogram scoring system using multivariate logistic regression -- was used to stratify the mortality risk among the high-risk patients identified in the first stage. Lactate Dehydrogenase (LDH), O2 percentage, White Blood Cells (WBC) Count, Age, and C-reactive protein (CRP) were identified as useful predictor using random forest feature selection model. Five predictors parameters and a CXR image based nomogram score was developed for quantifying the probability of death and categorizing them into two risk groups: survived (<50%), and death (>=50%), respectively. The multi-modal technique was able to predict the death probability of high-risk patients with an F1 score of 92.88 %. The area under the curves for the development and validation cohorts are 0.981 and 0.939, respectively.

High temporal resolution transcriptomic profiling delineates distinct patterns of interferon response following Covid-19 mRNA vaccination and SARS-CoV2 infection (preprint)

Knowledge of the factors contributing to the development of protective immunity after vaccination with COVID-19 mRNA vaccines is fragmentary. Thus we employed high-temporal-resolution transcriptome profiling and in-depth characterization of antibody production approaches to investigate responses to COVID-19 mRNA vaccination. There were marked differences in the timing and amplitude of the responses to the priming and booster doses. Notably, two distinct interferon signatures were identified, that differed based on their temporal patterns of induction. The first signature (S1), which was preferentially induced by type I interferon, peaked at day 2 post-prime and at day 1 post-boost, and in both instances was associated with subsequent development of the antibody response. In contrast, the second interferon signature (S2) peaked at day 1 both post-prime and post-boost but was found to be potently induced only post-boost, where it coincided with a robust inflammation peak. Notably, we also observed post-prime-like (S1++,S20/+) and post-boost-like (S1++,S2++) patterns of interferon response among COVID-19 patients. A post-boost-like signature was observed in most severely ill patients at admission to the intensive care unit and was associated with a shorter hospital stay. Interestingly, severely ill patients who stayed hospitalized the longest showed a peculiar pattern of interferon induction (S1-/0,S2+), that we did not observe following the administration of mRNA vaccines. In summary, high temporal resolution profiling revealed an elaborate array of immune responses elicited by priming and booster doses of COVID-19 mRNA vaccines. Furthermore, it contributed to the identification of distinct interferon-response phenotypes underpinning vaccine immunogenicity and the course of COVID-19 disease.

Exploring the Effect of Image Enhancement Techniques on COVID-19 Detection using Chest X-rays Images (preprint)

The use of computer-aided diagnosis in the reliable and fast detection of coronavirus disease (COVID-19) has become a necessity to prevent the spread of the virus during the pandemic to ease the burden on the medical infrastructure. Chest X-ray (CXR) imaging has several advantages over other imaging techniques as it is cheap, easily accessible, fast and portable. This paper explores the effect of various popular image enhancement techniques and states the effect of each of them on the detection performance. We have compiled the largest X-ray dataset called COVQU-20, consisting of 18,479 normal, non-COVID lung opacity and COVID-19 CXR images. To the best of our knowledge, this is the largest public COVID positive database. Ground glass opacity is the common symptom reported in COVID-19 pneumonia patients and so a mixture of 3616 COVID-19, 6012 non-COVID lung opacity, and 8851 normal chest X-ray images were used to create this dataset. Five different image enhancement techniques: histogram equalization, contrast limited adaptive histogram equalization, image complement, gamma correction, and Balance Contrast Enhancement Technique were used to improve COVID-19 detection accuracy. Six different Convolutional Neural Networks (CNNs) were investigated in this study. Gamma correction technique outperforms other enhancement techniques in detecting COVID-19 from standard and segmented lung CXR images. The accuracy, precision, sensitivity, f1-score, and specificity in the detection of COVID-19 with gamma correction on CXR images were 96.29%, 96.28%, 96.29%, 96.28% and 96.27% respectively. The accuracy, precision, sensitivity, F1-score, and specificity were 95.11 %, 94.55 %, 94.56 %, 94.53 % and 95.59 % respectively for segmented lung images. The proposed approach with very high and comparable performance will boost the fast and robust COVID-19 detection using chest X-ray images.

An early warning tool for predicting mortality risk of COVID-19 patients using machine learning (preprint)

COVID-19 pandemic has created an extreme pressure on the global healthcare services. Fast, reliable and early clinical assessment of the severity of the disease can help in allocating and prioritizing resources to reduce mortality. In order to study the important blood biomarkers for predicting disease mortality, a retrospective study was conducted on 375 COVID-19 positive patients admitted to Tongji Hospital (China) from January 10 to February 18, 2020. Demographic and clinical characteristics, and patient outcomes were investigated using machine learning tools to identify key biomarkers to predict the mortality of individual patient. A nomogram was developed for predicting the mortality risk among COVID-19 patients. Lactate dehydrogenase, neutrophils (%), lymphocyte (%), high sensitive C-reactive protein, and age - acquired at hospital admission were identified as key predictors of death by multi-tree XGBoost model. The area under curve (AUC) of the nomogram for the derivation and validation cohort were 0.961 and 0.991, respectively. An integrated score (LNLCA) was calculated with the corresponding death probability. COVID-19 patients were divided into three subgroups: low-, moderate- and high-risk groups using LNLCA cut-off values of 10.4 and 12.65 with the death probability less than 5%, 5% to 50%, and above 50%, respectively. The prognostic model, nomogram and LNLCA score can help in early detection of high mortality risk of COVID-19 patients, which will help doctors to improve the management of patient stratification.

COVID-19 Lesion Segmentation using Lung CT Scan Images: Comparative Study based on Active Contour Models (preprint)

Pneumonia is a lung infection threaten that threats all age groups. In this paper, using CT scans images, we used active contour models to evaluate and determine pneumonia infection caused by the Coronavirus disease (COVID-19). A background of active contour models (ACM) including contour representation and object boundary description methods is presented. The focus of this paper is on the conducted works based on the external forces. These methods include edge-based and region-based methods. Furthermore, the explanations of these methods, as well as the advantages and disadvantages of each method are presented. Finally, a comparison between the performances of the conducted works has been done based on a database of Lung CT Scan Images. The present review helps readers identify research starting points in active contour models on COVID19 research, which is a high priority topic to guide researchers and practitioners. In addition, when there are not enough images to use machine learning techniques, such as deep learning methods, the experimental results indicate that active contour methods obtain promising results.