ABSTRACT
In 2019, COVID-19 disease emerged in Wuhan, China, leading to a pandemic that saturated health systems, raising the need to develop effective diagnostic methods. This work presents an approach based on artificial intelligence applied to X-ray images obtained from Mexican patients, provided by Hospital General de Zona No. 24. A dataset of 612 images with 2 classes: COVID and HEALTHY, were labelled by a radiologist and also verified with positive RT-PCR test. The first class contains X-ray images of patients with pneumonia due to SARS-CoV-2 and the second contains patients without diseases affecting the lung parenchyma. The proposed work aims to classify COVID-19 pneumonia using convolutional neural networks to provide the physician with a suggestive diagnosis. Images were automatically trimmed and then transfer learning was applied to VGG-16 and ResNet-50 models, which were trained and tested using the generated dataset, both achieving an accuracy, recall, specificity and F1-score of over 98%. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
Background: There are recognized complications in patients infected by COVID-19 and thrombotic processes are closely related to infection. Objective: To describe the factors associated with increased risk in thrombotic events in COVID-19. Material and methods: Case-control study to identify factors associated with thrombotic processes in patients with COVID-19. Descriptive, comparative and inferential statistics were used, as well as logistic regression.The value of p <0.05 was determined as statistically significant and the statistical program IBM SPSS V.25 was used. Results: 15 cases of acute thrombosis were assesed, 17.5% were arterial and 8.8% were venous, 66.7% (n = 10) were men.Therapeutic anticoagulation and surgical procedures were neccesary. There was an association as a risk factor the fact of presenting some comorbidity (p = 0.005), and prolonged aPTT (p = 0.10), as well as abnormalities in the D-dimer. Conclusions: Infected patients suffers from hypercoagulability and confers a high risk of thrombosis. Significant elevation of D-dimer may be one of the markers of inflammation. The condition of presenting COVID-19 is not a contraindication for any revascularization procedure, which encourages us to improve our diagnostic and therapeutic behavior in patients with COVID-19 infection. © 2021 Sociedad Mexicana de Angiología y Cirugía Vascular y Endovascular, A.C. Publicado por Permanyer. Este es un artículo open access bajo la licencia CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
ABSTRACT
The current phase of the pandemic in different regions of the world is complex, a high community transmission of variants adapted to infect more susceptible people, combined with the increasing availability of different vaccines against covid-19, leads to the need to review basic aspects of the vaccines such as their efficacy, dosage and main side effects, among other aspects of interest. It is also important to contrast the covid-19 vaccines currently in use. In this review, an intentional search was carried out by type of vaccine applied and manufacturing laboratory in Mexico. Clinical trials and different secondary sources in PubMed and academic search engines were selected. The primary search variable was vaccine efficacy and its safety profile;secondary variables were viral platforms, dose and site of application. At the time of searching for this information, there were 287 vaccines against covid-19 in development, five different vaccines had been licensed in our country;one based on mrna technology (Pfizer), four based on viral vectors (AstraZeneca, CanSino, Sputnik V, Jennsen) and one based on inactivated virus (Sinovac). With the exception of CanSino which efficacy data are not available, the performance in the other licensed vaccines offers an excellent safety profile and protection against covid- 19. Efforts to improve vaccination coverage in the Mexican population should be reinforced.