Big Data Vs. the Teeny Coronavirus
By Rudrani Ghosh
If Covid-19 pandemic is rapidly traveling across the globe, can big data be far behind?
Let us hop back to 2003 during the SARS outbreak. We will witness the same empty lanes, silent malls, dark shopfronts— butone of the key features we will notice in case of today’s pandemic is how big data and sophisticated technology have come to our rescue to fight against the deadly virus.
The daily reports of the outbreak and the fatality curves reveal the grave and unsettling consequences of the fast moving pathogen. Big Data helps to understand and strategize plans for better orchestration of activities via evidence-based decision-making.
Big Data in the time of big viruses
As the world is trying to combat the deadly coronavirus, the data scientists have put on their analytical shoes that help them to stay a step ahead.
Predictive analytics, actionable intelligence and big data have augmented the nexus between human-biology and extrinsic factors— paving way for the emergence of a powerful tool to predict, respond and combat the outbreak.
Prediction of the virus outbreak
The warning signs of the impeding pandemic was detected early by a group of Canadian data scientists via AI driven health monitoring platform. They analysed billions of data (ranging from the reports of the sick people) which hinted towards the early virus attack much before the prediction by the World Health Organization (WHO) and CDC.
Apart from this, these data scientists also predicted the place where the virus would spread the next.
Data Platform during Covid-19 outbreak
Researchers are working their best to unravel the nature of the virus — why it creates an impact more than the others, what are the measures that can be adopted to help cure the situation and so on.
But if we delve deep down to the core, we will find something with which the healthcare industry is already familiarized with: Data.
“This is, in essence, a big data problem. We're trying to track the spread of a disease around the world and we're working with several organizations on modeling and dealing with the virus directly using a supercomputer, and also creating some websites where we track all the open data and documents we can find to help our researchers find what they're looking for” said James Hendler, the Tetherless World Professor of Computer, Web, and Cognitive Science at Rensselaer Polytechnic Institute (RPI) and director of the Rensselaer Institute for Data Exploration and Applications (IDEA).
Booster for Biomedical Research
Biomedical research is one of the key components where artificial intelligence and machine learning can play a major part. A lot of work is being done in order to bring out a vaccine and all these requires molecular modelling. Many researchers are using AI and machine learning to map a connection between pharmacological databases and genomic databases.
In addition, many drugs can be critically analysed for adverse outcomes using AI and actionable intelligence. For instance: PrOCTOR is an approach that has been used to predict the side effects of under trial drugs.
Big data also helps us to narrow down the potential targets which in turn the “accelerates eventual finding of the vaccine” Hendler added.
Interactive Data-driven Model
Researchers at Stanford University have founded an interactive data driven model that explores the possible outcomes of non-pharmaceutical interventions for COVID-19, including social distancing and quarantine.
“We wanted to start a larger conversation about how our long-term response might look,” said Erin Mordecai, a Stanford biologist. “We’re concerned about the potential for the disease to rapidly spread once we lift control measures.”
These models help to explores the various interventions like: What happens if we wait one week longer before issuing a shelter in place order? How long do we expect a given percent reduction in social contacts to need to be sustained before we start to see a decline in cases?
Rana Roy Choudhury, Manager of IT Clinical Applications at Stanford Healthcare asserts, “Big Data is helping in doing better analytics, we are at a stage where we need to make predictive models with a high level of accuracy to prevent the pandemic.”
Tapping into Actionable Intelligence
In order to combat the spread of the teeny virus across the country, various digital tools are being used to tap the real time forecasts and arm the healthcare professionals and decision makers with the information that they can employ to envision the ramification of the virus. For instance, the close contact detector app, “Aarogya Setu” helps to alert users if they are in close proximity with someone who have the virus.
Again, the Oxford University Big Data Institute tried to explore the advantages of a mobile app that could impart valuable data for integrated coronavirus control strategy. Professor Christophe Fraser from the Oxford University team explains that “…we need fast and effective mobile app for alerting people who have been exposed. Our mathematical modeling suggests that traditional public health contact tracing methods are too slow to keep up with the virus.”
Professor Fraser continues, “The instant mobile app concept is very simple. If you are diagnosed with coronavirus, the people you’ve recently come into contact with will be messaged advising them to isolate. If this mobile app is developed and deployed rapidly, and enough people opt-in to use such an approach, we can slow the spread of coronavirus and mitigate against devastating human, economic and social impacts.”
Prescriptive Model: The Need of the hour
In a conversation with Pulkit Kumar Sehgal, Consultant of World Bank and Visiting Faculty at Tata Institute of social Sciences (TISS) Mumbai, it was evident that there is a huge scope and need of prescriptive analytics during the pandemic. It does not only enable us to predict but it also goes a step ahead of predictive model to provide an efficient actionable solution. The prescriptive model will provide solutions to the government and healthcare providers about how they should place themselves once a certain level of positive cases is confirmed in their respective region.
Mr. Sehgal further explains that, “This model will prescribe government how they should revise lockdown and other policies with respect to forecasted confirmed cases in a particular geography. For hospitals, this model will prescribe what operational and inventory modifications can be made by the hospital administration to cater the forecasted load of confirmed cases.”
This will enable hospitals to prepare in advance “to provide quality care during this challenging pandemic situation through smart procurement and efficient management. In a nutshell, predictive and prescriptive analytics are complementary to each other especially during pandemic situation” he states.