Revisión sistemática las tecnologías aplicadas para mitigar el Covid-19 con inteligencia artificial desde un enfoque al aprendizaje profundo

Abstract

In December 2019, a coronavirus variant called SARS-CoV-2 emerged. Months later, given the rapidity of its spread, morbidity, and mortality rates, how unknown it was, and the difficulties in managing the disease, the World Health Organization declared it a pandemic. This scenario was characterized by the collection of large amounts of data, both structured and unstructured, which the health systems did not have the capacity to use for improving the management of the pandemic. Faced with such a scenario, multidisciplinary teams made use of Artificial Intelligence, Data Science, Big Data and other disruptive technologies. The objective of this work is to determine the main emerging technologies, based on Artificial Intelligence, that have been successfully applied in the mitigation of Covid-19. The method used to achieve this objective was the systematic review of the literature, following the methodology proposed by Barbara Kitchenham. As main results it was found that deep learning methods were the predominant Artificial Intelligence techniques, especially models based on Generative Adversarial Neural Networks (GAN), Extreme Learning Machines (ELM) and Recurrent Neural Networks type LSTM. Most of the studies analyzed were devoted to detection and diagnosis, then to treatment and to a lesser extent to propagation and mitigation.