Big data in the times of COVID-19

Big Data is supported by the widespread use of the Internet of Things (IoT) has led to a massive amount of data produced from ubiquitous sensors and wearable technology. The enormous increase in data volumes correlated to the developments of AI-empowered analytical techniques has led to the rise of this market. The technology has also been used in a broad range of fields of industrial application, including healthcare, where electronic healthcare records (EHRs) are used to facilitate healthcare services by using intelligent analytics. Health Big Data, for instance, effectively facilitates patient health analysis, diagnostic assistance, and drug development. It can be produced from a range of sources, including social networking graphs, mobile devices such as smartphones, sensor-like IoT devices, and public data in different formats, including text or video.

The technology and the high degree of innovations available are some of the benefits we have today in the battle against COVID-19, which was not so advanced during the SARS epidemic of 2003. As the COVID-19 virus circulated through China, to map and control the disease, China tuned to big data, machine learning, and other automated technologies. As other countries around the globe battle the spread of the COVID-19 virus, they have turned to emerge technologies including this technology to develop real-time predictions and equip healthcare practitioners and government policymakers with information they could use to anticipate the effects of the COVID-19 virus.

It offers researchers, healthcare professionals, statisticians a vast amount of knowledge and enables them to make a more strategic decision to combat the COVID-19 virus. Such data can be used to continually track the virus internationally and to promote medical advancement. The role of big data in COVID-19 support starts from the very first phase that is virus spread detection. In December 2019, BluDot, a big data start-up located in Toronto, detected several rare cases of pneumonia in Wuhan, China. They performed the analysis by using their big data model that pulled data from several databases. To forecast the rise of an epidemic, the algorithm analyzed data from patient health records, airline ticketing data, government notices, media reports, and disease networks. BluDot was able to forecast the transmission of the COVID-19 virus from Wuhan to several other Asian cities using airline ticketing data.

It was presumed that as the COVID-19 virus spread across China, Taiwan would be severely impacted in part because of its relative proximity to China. However, to mitigate the effect of the virus on its territory, Taiwan used technologies and a comprehensive pandemic strategy produced after the 2003 SARS pandemic. The national health care database was combined with data from its customs and immigration database as part of their plan. When dealing with the COVID-19 virus, by centralizing the data in this manner, they were able to get real-time warnings on who could be affected based on symptoms and travel records. Also, they had QR code screening and online travel and health symptom monitoring that helped them identify the risks of illness for passengers and a toll-free hotline to report suspected symptoms.

As the databases continue to provide perspectives that enable healthcare providers to treat COVID-19 infections and subsequent post-COVID symptoms, participating researchers hope that their success will shape the future of medical research collaborative effort. The National COVID Cohort Collaborative (N3C) database, funded by the National Center for Advancing Translational Science (NCATS), a unit of the National Institutes of Health, is the most imperative step in the United States. The archive extracts data from electronic health reports of individuals who were tested for COVID-19, whether those tests returned positive or negative, or who documented symptoms related to COVID-19. Professionals in health care upload the documents and NCATS make them accessible for the study of any accredited researchers.

Worldwide, businesses and policymakers are mining millions of internet and smartphone users’ location data for details on how the virus travels and whether social distancing initiatives succeed. These activities examine vast data sets to discover trends in people’s actions and attitudes over the course of the pandemic, unlike monitoring programs that monitor the movements of a single individual. Mobile advertising agencies in the United States are currently collaborating with the Centers for Disease Control and Prevention and state and local governments to examine how the activities of people have evolved and where they also socialize based on cell location data.

Based on location data of Google Maps users, Google has released Community Mobility Reports that provide information into how Covid-19 initiatives such as social distancing are operating. Facebook is offering its research partners with information on economic migration and friendship patterns to forecast virus spread and compliance with public health measures under its remodeled Disease Prevention Maps policy.

Using data analytical software on vast databases obtained from accessible sources such as health agencies including WHO, and healthcare institutes, it analytically helps global disease forecasting. Through integrating intelligent technologies including Machine Learning, and Deep Learning for developing predictive models, it has also demonstrated great potential for COVID-19 spread detection, which is very helpful to governments in controlling the likely future outbreak of the COVID-19 virus. Also, it has the ability to support diagnosis and recovery processes for COVID-19. Data learning from massive data also allows to define possible targets for a successful COVID-19 vaccine and to combine a large-scale information graph, literature, and proteomics data to facilitate the identification of potential COVID-19 drug candidates. – Global Market Database