Leveraging Data Science To Combat COVID-19: A Comprehensive Review

Abstract

<div>COVID-19, an infectious disease caused by the SARS-CoV-2 virus, was declared a pandemic by the World Health Organisation (WHO) in March 2020. At the time of writing, more than 2.8 million people have tested positive. Infections have been growing exponentially and tremendous efforts are being made to fight the disease. In this paper, we attempt to systematise ongoing data science activities in this area. As well as reviewing the rapidly growing body of recent research, we survey public datasets and repositories that can be used for further work to track COVID-19 spread and mitigation strategies.</div><div>As part of this, we present a bibliometric analysis of the papers produced in this short span of time. Finally, building on these insights, we highlight common challenges and pitfalls observed across the surveyed works.</div>

COVID-19 open source data sets: a comprehensive survey

“…The data and code can be found at. 28 The study found that before the implementation of travel restrictions, the spatial distribution of COVID-19 can be highly correlated to mobility. However, the correlation is lower after the imposition of travel restrictions.…”

“…ML, big data, and statistical techniques can be applied to the data sets for tasks related to prediction. Figure 1 illustrates a consolidated view of the taxonomy of COVID-19 open source data sets [13,28].…”

“…MRI based COVID-19 diagnosis and data set are demanded to compare their accuracy with CT-scans and Xray based methods. Moreover, the operational performance and effectiveness of the proposed AI/ML-based diagnosis in clinical work-flows under regulatory and quality control measures and unbiased data needs investigation [28,111].…”

“…The timeliness of the research is another important issue for textual data. Social media data analysis and corresponding actions become outdated very quickly as it is collected, pre-processed, and annotated at large-scale [28].…”

“…The work did not detail the AI applications of the data set and textual and cough based data sets. Latif et al [28] reviewed data science research focusing on mitigation and diagnosis of COVID-19. The listed surveys mention few open source data sets and point towards the unavailability of open data resources challenging trustworthy and realworld operations of AI/ML-based techniques.…”