Role of data science in managing COVID-19 pandemic

Abstract

In December of 2019, the first outbreak of COVID-19 was detected in mainland China, eventually spreading to every continent in the world except Antarctica. Named Coronavirus Disease 19 (COVID-19) by the World Health Organization (WHO), this highly contagious disease was caused by the virus SARS-CoV-2. With a transmission rate greater than SARS or common flu, continued tremendous efforts will be needed to successfully combat this disease. In this article, we review the role that data science is playing in this war. Data science, combined with statistical analysis, computer science and computational biology, is helping in myriad ways with applications including epidemiology, drug discovery, and molecular design for diagnostic and therapeutic purposes. A number of data driven models, mathematical models, correlations and predictive models have been developed for COVID-19. Challenges faced by the data scientists today have been highlighted. Finally, open source datasets sources are mentioned that can be potentially used in diagnostics and evaluation of health policies.