Data Science, Power Bi, Machine Learning, Covid 19, Visualization

COVID-19 and a data-driven story

Written by Jeff Lumpkin, Vice President, Customer Advisory Engineering and Product Management, KenSci on 18 Mar 2020

In 2004, my wife and I moved from Seattle to Singapore, just a few months after the SARS epidemic had been contained. While Singapore wasn’t impacted to nearly the same degree as China or Hong Kong, the experience was still very fresh in people’s minds. Our 2 years there gave me an appreciation for how rapidly a virus could cross borders, and how vulnerable were unprepared populations.

In January this year, I booked a mid-February flight to Singapore to onboard a new KenSci employee. I was, however, mindful of the COVID-19 virus outbreak in Wuhan and began tracking its spread across China and the rest of Asia. When the number of confirmed cases in Singapore jumped from 1 to 40 in a little over 2 weeks, I regretfully canceled my flight. Since then, I’ve closely followed the spread of the COVID-19 virus as it has moved outward from Asia to the US, the Middle East and Europe.

Last week, as my hometown, Kirkland, Washington became the epicenter of the outbreak in the US, I began searching for credible sources of data that I could use to document the spread of the virus. One of the best data sources I’ve discovered is published by the John Hopkins Center for Systems Science and Engineering. This dataset tracks Confirmed Cases, Deaths and Recoveries by day at the country level (and for the US, Australia, China and Canada) at the state or province level.

 

covid19-updates

Click on the visual above to access the COVID-19 dashboard realtime

I’ve built this dashboard to help my colleagues, KenSci’s customers, and everyone with an interest in learning more easily gain a better understanding of the COVID-19 epidemic. I want to be able to provide a broad overview as well as the ability to easily dive down to the most granular detail possible. Furthermore, I want the data to speak for itself: as individuals and organizations, we need to make decisions based on fact; the more easily those facts are obtained and understood, the lower the barriers are to taking action and driving change.

Below are some key observations I’ve made from the data.

  1. On March 14, China had more confirmed cases than all the rest of the world combined (81,031 vs 75,066. By March 16, the number of confirmed cases outside of China had grown to 100K while China remained flat.

    relgion

     

  2. However, the increases in confirmed cases has come to halt as China’s containment program takes effect. (as of March 13).

    covid19

     

  3. Three of the countries outside of China that were most impacted by SARS were Hong Kong, Singapore and Taiwan. The swift and comprehensive actions of those respective governments to COVID-19 have been highly effective in limiting growth of cases.

    confirm-case

     

  4. Transparency is vital to containing COVID-19. South Korea saw a huge spike in confirmed cases, most of which were found among members of the secretive Shincheonji church. The church initially resisted testing by the government and held large group events which facilitated the dispersion of the virus. Since late February, however, the South Korean government has instituted the most aggressive and transparent testing program in the world. As a result, South Korea has reached a major turning point; on March 13, more people were released from hospitals than were newly diagnosed.

    south-corea

     

  5. The United States will see a rapid acceleration of cases in states that until very recently, had no confirmed cases of COVID-19. On March 1, there were 30 confirmed cases in just 7 states. Just over two weeks later (Mar 16), there are 4,655 cases in 49 states.

    march-case

    March 1, 2020


    mid-march

    March 16, 2020

The situation continues to evolve at an ever-increasing pace, particularly in Western Europe and the United States. Since first building this analysis on March 9th, I’ve watched the number of cases grow from 113K to 181K, and seen the occurrence of COVID-19 become geographically ubiquitous. While conditions remain deeply frightening, there are reasons for optimism. Countries like South Korea, Taiwan and Singapore show that swift action can be effective in controlling the spread of this epidemic. We all have both the opportunity and the responsibility to do everything we can to help ourselves, our neighbors and the world.

Access Our Latest Thinking

Research, blogs, and other whitepapers on AI Led healthcare transformation

Case Study

See how Advocate Aurora Health is working on fighting the opioid battle

May 13, 2020

Blog

How to accelerate the movement of data onto Azure in FHIR format

March 17, 2020

Webinar

SLUHN is fighting COVID-19 by staying ahead with a real-time command center

September 4, 2020

PodCast

HIT Like a girl~ Health from Corinne Stroum on Healthcare Informatics

August 12, 2020

Press Release

SCAN Health and KenSci are leveraging AI to help the senior members

August 11, 2020