Data-driven Analytical Models of COVID-2019 for Epidemic Prediction, Clinical Diagnosis, Policy Effectiveness and Contact Tracing: A Survey

TL;DR

This survey reviews recent data-driven models for COVID-19 epidemic prediction, diagnosis, policy assessment, and contact tracing, highlighting their methodologies, evaluations, and data sources amidst the ongoing pandemic.

Contribution

It provides a comprehensive overview of COVID-19 data analytics models, including evaluations and comparisons, filling a gap in the early-stage literature.

Findings

Reviewed latest COVID-19 data analysis models

Conducted post-publication evaluations and comparisons

Compiled diverse data sources for COVID-19 research

Abstract

The widely spread CoronaVirus Disease (COVID)-19 is one of the worst infectious disease outbreaks in history and has become an emergency of primary international concern. As the pandemic evolves, academic communities have been actively involved in various capacities, including accurate epidemic estimation, fast clinical diagnosis, policy effectiveness evaluation and development of contract tracing technologies. There are more than 23,000 academic papers on the COVID-19 outbreak, and this number is doubling every 20 days while the pandemic is still on-going [1]. The literature, however, at its early stage, lacks a comprehensive survey from a data analytics perspective. In this paper, we review the latest models for analyzing COVID19 related data, conduct post-publication model evaluations and cross-model comparisons, and collect data sources from different projects.