HOW DATA SHAPE PANDEMIC


      
The rapid global spread of COVID-19 has brought advanced big data analytics tools, with entities from all responsible sector seeking to monitor and reduce the impact of the virus. Here, I share a story about the important of data for future.                                                                                                                            In 2009, a new FLU virus was discovered. This new virus  was responsible for bird flu & swine flu, this strain dubbed H1N1. Within a week it had spread all over the world. Some commentators compared the impact of this virus with disaster made by the Spanish flu during 1918. That time no vaccine was available. Public health agency wanted to slow it's spread but they needed to know where it already was.



In US the Center for Disease Control & Prevention (CDC) requested to the doctors to inform them about the new flu cases. Flu emerged a week or two out of date. People might feel sick but they took more time for doctor consulting. Data delivery to CDC was delayed about one or two weeks. This delay completely blinded public health agency at crucial moments.                                                                                                                                                         The real astonishing thing is that, the engineers at the Internet giant Google published a  remarkable paper in the scientific journal 'Nature' about flu virus way before the H1N1 virus made headlines. It created splash among the health experts & computer scientists but it was overlooked.                                                                                                                                                                      The author explained how Goggle could predict flue not just nationally (US) but down to specific regions. Google receives more than three billion search queries every day, save them all & took 50 million most common search terms then compared it to the CDC data on the spread of seasonal flu between 2003 to 2008. They processed various mathematical models in order to test search terms comparing their predictions against actual flu cases from the CDC data in 2007 and 2008. They struck gold, their software found strong similarity between their prediction and official figures nationwide. 

                                                                                                                                                    Thus when H1N1 struck in 2009, Google's system proved that it is more useful and timely indicator than government statistics with their natural reporting lag.                                                                                                                                                                                            Strikingly, Google's method does not involve distributing mouth swabs or contacting physician offices. Instead it is built on " Big Data" -the ability of society to harness information in novel ways to produce useful insights or good and service of significant value.  

Raghunath

I am studying in M.SC Data Science at the Department of Computer Science and Engineering, Kalyani University. I am an enthusiast blogger.

6 Comments

Previous Post Next Post