MachineX: Analysing COVID-19 Pandemic

Knoldus-corona-virus
Reading Time: 5 minutes

Introduction

COVID-19 disease, caused by the SARS-CoV-2 virus, was identified in December 2019 in China and declared a global pandemic by the WHO(World Health Organization) on 11 March 2020. The disease first originated in Wuhan, China and since then it has spread globally across the world affecting more than 200 countries. Coronavirus disease 2019 (COVID-19) is a highly infectious disease caused by the severe acute respiratory syndrome.

The Number of cases has now increased day by day. As of today,  there are a total of 1,274,346 confirmed cases with 940,028 active cases and 69,480 deaths in more than 230 countries across the globe.

You can see the condition of whole world right now , in below map:

source: google covid-19-map

All of the countries affected by this virus are nearly on complete lock-down. As a result, borders are closed, people are practicing social distancing. The government is identifying & admitting the affected ones, quarantining the probable cases but the count of individuals being affected by the virus is increasing exponentially in a majority of the countries. The United States has more than twice as many confirmed cases as any other single country and more than half of all the cases have been in Europe, with Italy and Spain worst affected.

COVID-19 cases in Europe

source: map

As you can see above on the map, Europe is the most affected part of the world right now, with nearly 80% cases. Many of the cases across Europe have been traced back to Italy, which has one of the world’s largest outbreaks. At least 128,000 people have tested positive as of Monday morning.

Even after all precaution measures done by the government, the rate of COVID-19 cases is increasing exponentially and unfortunately expected to increase until a medicine/vaccine can be developed and applied after a significant amount of clinical trials. But according to the big virus specialist, we shouldn’t expect a vaccine in the next 1/2 year.

Most countries like China, Iran are able to control the increasing number of confirmed cases as well as a decrease in the number of deaths too. According to them, in addition to lock-down, countries should also perform a huge number of corona testing.

Analysing the data

For the analyzing part, we are going to use kaggle covid-19-global forecasting. The data in that file is:

  • ID
  • Province_State
  • Country_Region
  • Date
  • ConfirmedCases
  • Fatalities

first lets understand the trend in confirmed cases all over the world

data.ConfirmedCases.plot(figsize = (15,6), marker = "*", color = 'teal',linestyle = 'dashed', linewidth =1)
plt.title("Total confirmed case of covid19")
plt.xticks(rotation=90)
plt.show()

Here we can see, In initial state February to march , number of total cases were increasing on a small rate but from mid of the march, number of cases increased on a very high rate. It is clear that , the virus is so good in spreading among people.

Next, lets see the trend of fatalities (i.e number of deaths).

data.Fatalities.plot(figsize = (15,6), marker = "*", color = 'crimson',linestyle = 'dashed', linewidth =1)
plt.title("Total fatalities of covid19")
plt.xticks(rotation=90)
plt.show()

we clearly see the same trend in fatalities as we saw in total number of deaths, from mid of march , no of deaths is also increasing on a exponentially high rate.

to make it more clear, lets see an comparison between both:

data.ConfirmedCases.plot(figsize = (10,5),marker="^", color = 'blue', linestyle = 'dashdot', title = "total ConfirmedCases")
data.Fatalities.plot(figsize = (10,5),marker="*", color = 'red',linestyle = 'dashdot',title = "total Fatalities")
plt.xlabel('Date')
plt.ylabel('confirmed and fatalities cases')
plt.title('confirmed vs fatalities plot')
plt.legend()
plt.xticks(rotation=90)
plt.show()

COVID-19 Total Deaths growth for top 10 worst affected countries

Below are my analysis from the above line plots for the top 10 affected countries:

  • Cases and Deaths for China have stagnated over time.
  • The cases and deaths are monotonically increasing(almost exponentially) for rest of the countries.
  • US has shown the greatest rise in the number of Confirmed Cases. Italy, on the other hand having the highest rise in deaths has to bear the brunt of the virus. Spain is a close second to Italy.
  • 6 out of the top 10 affected countries are Western European countries.

Note: this data is from February to march end , currently USA registered highest number of cases.

Analysis of India counts

COVID19 outbreak has started a bit late in India as compared to other countries. But, it has started to pick up the pace. With limited testing and not a well-funded healthcare system, India is surely up for a challenge. Let’s hope that the 21-day lockdown helps to stop or at least slow down the spread of this dreaded virus.

Analysis for China counts

  • This is where it all started! By looking at the graph it can be seen that China has been able to almost stop the spread of COVID19 substantially.
  • Almost all the cases are from the Hubei Province which can be attributed to the fact that the outbreak started from its capital, Wuhan.

In order to get a better understanding of the cases/fatalities growth from other provinces, you can click on Hubei in the legend so that it gets hidden and the scale will autoscale.

Conclusion

Look like the china , from where this pandemic was generated , is now stable and there is a huge decrease in no of cases and deaths.

Lock-down helps many countries like india, where there small hike on graph in no of cases.

Potential of AI against COVID-19

I find that AI has not yet been impactful against COVID-19. Its use of AI is hampered by a lack of data, and by too much noisy and outlier data. Overcoming these constraints will require a careful balance between data privacy and public health concerns, and more rigorous human-AI interaction. It is unlikely that these will be addressed in time to be of much help during the present pandemic. Instead, AI may “help with the next pandemic”. In the meantime, gathering diagnostic data on who is infectious will be essential to save lives and limiting the economic havoc due to containment.

There are many areas AI can help in the fight against COVID-19, these are:

  • Early warnings and alerts
  • Tracking and prediction
  • Data dashboards
  • Diagnosis and prognosis
  • Treatments, and cures
  • Social control.

I hope we will soon get out of this pandemic , and situation will be normal again.

Note: I will write regularly every alternate week for regular updates

Stay Home, Stay Safe!

Knoldus-blog-footer-image

Written by 

Shubham Goyal is a Data Scientist at Knoldus Inc. With this, he is an artificial intelligence researcher, interested in doing research on different domain problems and a regular contributor to society through blogs and webinars in machine learning and artificial intelligence. He had also written a few research papers on machine learning. Moreover, a conference speaker and an official author at Towards Data Science.