Abstract
During the COVID-19 pandemic, more than ever, data science has become a powerful weapon in combating an infectious disease epidemic and arguably any future infectious disease epidemic. Computer scientists, data scientists, physicists and mathematicians have joined public health professionals and virologists to confront the largest pandemic in the century by capitalizing on the large-scale ‘big data’ generated and harnessed for combating the COVID-19 pandemic. In this paper, we review the newly born data science approaches to confronting COVID-19, including the estimation of epidemiological parameters, digital contact tracing, diagnosis, policy-making, resource allocation, risk assessment, mental health surveillance, social media analytics, drug repurposing and drug development. We compare the new approaches with conventional epidemiological studies, discuss lessons we learned from the COVID-19 pandemic, and highlight opportunities and challenges of data science approaches to confronting future infectious disease epidemics.This article is part of the theme issue ‘Data science approaches to infectious disease surveillance’.
Highlights
We review the newly born data science approaches to confronting COVID-19, including the estimation of epidemiological parameters, digital contact tracing, diagnosis, policy-making, resource allocation, risk assessment, mental health surveillance, social media analytics, drug repurposing and drug development
The use of data science methodologies in medicine and public health has been enabled by the wide availability of big data of human mobility, contact tracing, medical imaging, virology, drug screening, bioinformatics, electronic health records and scientific literature along with the ever-growing computing power [1,2,3,4]
There were notable deficiencies in the public health systems [7,8], including (a) the slow response to highly contagious viruses, if the symptoms resembled those of seasonal influenza and other mild infectious diseases; (b) the lack of reliable data at critical points; (c) slow and disorganized data collection; (d) policy decision-making based on political expediency but not scientific evidence; (e) slow and incomplete manual contact tracing; (f) the conflict between the effectiveness of contact tracing and the invasion of privacy; and (g) difficulty in identifying effective drugs to treat COVID-19 patients
Summary
The use of data science methodologies in medicine and public health has been enabled by the wide availability of big data of human mobility, contact tracing, medical imaging, virology, drug screening, bioinformatics, electronic health records and scientific literature along with the ever-growing computing power [1,2,3,4]. There were notable deficiencies in the public health systems [7,8], including (a) the slow response to highly contagious viruses, if the symptoms resembled those of seasonal influenza and other mild infectious diseases; (b) the lack of reliable data at critical points (such as early outbreak and mutant strains); (c) slow and disorganized data collection; (d) policy decision-making based on political expediency but not scientific evidence; (e) slow and incomplete manual contact tracing; (f) the conflict between the effectiveness of contact tracing and the invasion of privacy; and (g) difficulty in identifying effective drugs to treat COVID-19 patients Many of these deficiencies can be addressed by creatively mining big data related to people’s behaviours and opinions, the biological structure of drugs, human interactomes and the constantly mutating virus. We conclude the paper with discussions of lessons we have learned so far in leveraging novel data and data science approaches to confront COVID-19 and other emerging infectious diseases
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
