Finding of the factors affecting the severity of COVID-19 based on mathematical models

A Survey of COVID-19 Diagnosis Using Routine Blood Tests with the Aid of Artificial Intelligence Techniques

Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), causing a disease called COVID-19, is a class of acute respiratory syndrome that has considerably affected the global economy and healthcare system. This virus is diagnosed using a traditional technique known as the Reverse Transcription Polymerase Chain Reaction (RT-PCR) test. However, RT-PCR customarily outputs a lot of false-negative and incorrect results. Current works indicate that COVID-19 can also be diagnosed using imaging resolutions, including CT scans, X-rays, and blood tests. Nevertheless, X-rays and CT scans cannot always be used for patient screening because of high costs, radiation doses, and an insufficient number of devices. Therefore, there is a requirement for a less expensive and faster diagnostic model to recognize the positive and negative cases of COVID-19. Blood tests are easily performed and cost less than RT-PCR and imaging tests. Since biochemical parameters in routine blood tests vary during the COVID-19 infection, they may supply physicians with exact information about the diagnosis of COVID-19. This study reviewed some newly emerging artificial intelligence (AI)-based methods to diagnose COVID-19 using routine blood tests. We gathered information about research resources and inspected 92 articles that were carefully chosen from a variety of publishers, such as IEEE, Springer, Elsevier, and MDPI. Then, these 92 studies are classified into two tables which contain articles that use machine Learning and deep Learning models to diagnose COVID-19 while using routine blood test datasets. In these studies, for diagnosing COVID-19, Random Forest and logistic regression are the most widely used machine learning methods and the most widely used performance metrics are accuracy, sensitivity, specificity, and AUC. Finally, we conclude by discussing and analyzing these studies which use machine learning and deep learning models and routine blood test datasets for COVID-19 detection. This survey can be the starting point for a novice-/beginner-level researcher to perform on COVID-19 classification.

A comparison of machine learning algorithms in predicting COVID-19 prognostics

ML algorithms are used to develop prognostic and diagnostic models and so to support clinical decision-making. This study uses eight supervised ML algorithms to predict the need for intensive care, intubation, and mortality risk for COVID-19 patients. The study uses two datasets: (1) patient demographics and clinical data (n = 11,712), and (2) patient demographics, clinical data, and blood test results (n = 602) for developing the prediction models, understanding the most significant features, and comparing the performances of eight different ML algorithms. Experimental findings showed that all prognostic prediction models reported an AUROC value of over 0.92, in which extra tree and CatBoost classifiers were often outperformed (AUROC over 0.94). The findings revealed that the features of C-reactive protein, the ratio of lymphocytes, lactic acid, and serum calcium have a substantial impact on COVID-19 prognostic predictions. This study provides evidence of the value of tree-based supervised ML algorithms for predicting prognosis in health care.

Mutations in SARS-CoV-2: Insights on structure, variants, vaccines, and biomedical interventions

COVID-19 is a worldwide pandemic caused by SARS-coronavirus-2 (SARS-CoV-2). Less than a year after the emergence of the Covid-19 pandemic, many vaccines have arrived on the market with innovative technologies in the field of vaccinology. Based on the use of messenger RNA (mRNA) encoding the Spike SARS-Cov-2 protein or on the use of recombinant adenovirus vectors enabling the gene encoding the Spike protein to be introduced into our cells, these strategies make it possible to envisage the vaccination in a new light with tools that are more scalable than the vaccine strategies used so far. Faced with the appearance of new variants, which will gradually take precedence over the strain at the origin of the pandemic, these new strategies will allow a much faster update of vaccines to fight against these new variants, some of which may escape neutralization by vaccine antibodies. However, only a vaccination policy based on rapid and massive vaccination of the population but requiring a supply of sufficient doses could make it possible to combat the emergence of these variants. Indeed, the greater the number of infected individuals, the faster the virus multiplies, with an increased risk of the emergence of variants in these RNA viruses. This review will discuss SARS-CoV-2 pathophysiology and evolution approaches in altered transmission platforms and emphasize the different mutations and how they influence the virus characteristics. Also, this article summarizes the common vaccines and the implication of the mutations and genetic variety of SARS-CoV-2 on the COVID-19 biomedical arbitrations.

Remdesivir Reduces Mortality in Hemato-Oncology Patients with COVID-19

Introduction

Remdesivir is the first agent with proven clinical efficacy against coronavirus disease 2019 (COVID-19); however, its benefit is associated with early use, and its efficacy has been poorly studied in patients with hemato-oncological diseases, who have an increased risk of a severe course of infection. This study aimed to assess the effects of remdesivir on mortality, mechanical ventilation, and the duration of hospitalization in both the general population and in patients with hemato-oncological diseases.

Materials and Methods

Longitudinal data for 4287 patients with confirmed COVID-19 were analyzed, including a subset of 200 individuals with hemato-oncological diseases. In total, 1285 (30.0%) patients received remdesivir, while the remaining patients were treated with other methods. Survival statistics for the 14- and 30-day observation time points were calculated using non-parametric and multivariate Cox models.

Results

Mortality for the 14- and 30-day observation time points was notably lower among patients receiving remdesivir (7.2% vs 11.6%, p < 0.001 and 12.7% vs 16.0, p = 0.005, respectively); however, in multivariate models adjusted for age, sex, lung involvement, and lactate dehydrogenase and interleukin-6 levels, the administration of remdesivir did not reduce patient mortality at either the 14-day or 30-day time points. Among patients with haemato-oncological disease, significant survival benefit was observed at 14 and 30 days for patients treated with remdesivir (11.3% vs.16.7% and 24.2% vs 26.1%, respectively; p < 0.001). A favorable effect of remdesivir was also noted for the 14-day time point in multivariate survival analysis (HR:4.03 [95% confidence interval:1.37-11.88]; p = 0.01).

Conclusion

Remdesivir significantly reduced the early mortality rate in COVID-19 patients with comorbid hemato-oncological disease, which emphasizes the need to administer this agent to immunosuppressed patients.

Are lipid ratios and triglyceride-glucose index associated with critical care outcomes in COVID-19 patients?

Lipid ratios and the triglyceride and glucose index (TyG) could be a simple biochemical marker of insulin resistance (IR). The current study was carried out to examine the correlation between triglyceride to high-density lipoprotein-cholesterol (TG/HDL-C), total cholesterol to HDL-C (TC/HDL-C), low-density lipoprotein-cholesterol to HDL-C ratio (LDL-C/HDL-C), as well as TyG index with the severity and mortality of severe coronavirus disease 2019 (COVID-19). A total of 1228 confirmed COVID-19 patients were included in the current research. Regression models were performed to evaluate the correlation between the lipid index and severity and mortality of COVID-19. The TyG index and TG/HDL-C levels were significantly higher in the severe patients (P<0.05). TG/HDL-C, LDL-C/HDL-C, TC/HDL-C ratios, and TyG index were significantly lower in survivor cases (P<0.05). Multivariate logistic regression analysis demonstrated that predictors of the severity adjusted for age, sex and BMI were TyG index, TG/HDL-C ratio (OR = 1.42 CI:1.10–1.82, OR = 1.06 CI: 1.02–1.11, respectively). This analysis showed that TG/HDL-C, TC/HDL-C, LDL-C/HDL-C ratios, and TyG index statistically are correlated with COVID-19 mortality (OR = 1.12 CI:1.06–1.18, OR = 1.24 CI:1.05–1.48, OR = 1.47 CI:1.19–1.80, OR = 1.52 CI:1.01–2.31, respectively). In summary, the TyG index and lipid ratios such as TC/HDL-C, TG/HDL-C, LDL-C/HDL-C could be used as an early indicator of COVID-19 mortality. Furthermore, the study revealed that TyG index and TG/HDL-C indices are biochemical markers of COVID-19 severe prognosis.

An Ensemble Learning Model for COVID-19 Detection from Blood Test Samples

Current research endeavors in the application of artificial intelligence (AI) methods in the diagnosis of the COVID-19 disease has proven indispensable with very promising results. Despite these promising results, there are still limitations in real-time detection of COVID-19 using reverse transcription polymerase chain reaction (RT-PCR) test data, such as limited datasets, imbalance classes, a high misclassification rate of models, and the need for specialized research in identifying the best features and thus improving prediction rates. This study aims to investigate and apply the ensemble learning approach to develop prediction models for effective detection of COVID-19 using routine laboratory blood test results. Hence, an ensemble machine learning-based COVID-19 detection system is presented, aiming to aid clinicians to diagnose this virus effectively. The experiment was conducted using custom convolutional neural network (CNN) models as a first-stage classifier and 15 supervised machine learning algorithms as a second-stage classifier: K-Nearest Neighbors, Support Vector Machine (Linear and RBF), Naive Bayes, Decision Tree, Random Forest, MultiLayer Perceptron, AdaBoost, ExtraTrees, Logistic Regression, Linear and Quadratic Discriminant Analysis (LDA/QDA), Passive, Ridge, and Stochastic Gradient Descent Classifier. Our findings show that an ensemble learning model based on DNN and ExtraTrees achieved a mean accuracy of 99.28% and area under curve (AUC) of 99.4%, while AdaBoost gave a mean accuracy of 99.28% and AUC of 98.8% on the San Raffaele Hospital dataset, respectively. The comparison of the proposed COVID-19 detection approach with other state-of-the-art approaches using the same dataset shows that the proposed method outperforms several other COVID-19 diagnostics methods.