COVID-19 – ANALYSIS OF THE FIRST 3 MONTHS OF THE VIRUS THAT STOPPED THE WORLD

By late December of 2019, Wuhan Municipal Health Commission reported a series of concerning pneumonia cases. Then, Chinese Center for Disease Control and Prevention intervened and World Health Organization was notified. The novel coronavirus 2019-nCoV (COVID-19) has been identified as a class B notifiable disease, and although different from and less severe than SARS-CoV and MERS-CoV coronavirus, it seems to be more contagious.

The data represents 72.314 unique patient records diagnosed with COVID-19 by 11 of February of 2020. About 22% of cases were suspected, i.e. clinically diagnosed by symptoms (fever and dry cough) and exposures. The rest of the cases were diagnosed by acid nucleic test and lung images. The total number of confirmed cases, 44672, out of which 74.7% coresponded to cases from Hubei province. At present, there are more than 720,000 cases worldwide, with the United States, Italy and Spain being the three focal points, according to official statistics. This data can be viewed on the dashboard created by the Data Management & Analytics department of stratesys.

If we continue to analyze the statistics, we see that The Pearson Χ2 test indicates (p-value < 0.001) that the age factor is statistically significant, which means that it might be related to the infection process and epidemiological features of COVID-19. Nevertheless, due to lack of data granularity it was impossible to perform a more complex analysis to discover interactions and confounding factors such as comorbid conditions variable (including hypertension, diabetes, respiratory diseases among others). Therefore, this result based on statistical inference does not establish causal effects, but merely indicates that there might be a pattern that should be studied in detail with more complete data. Using data from the ongoing study of influence of ABO blood type groups, the age variable also appears as significant for being infected by COVID-19.

Now, there is an ongoing research to find an effective treatment of COVID-19. And the causes and combinations of risk factors of getting infected are still under research. In this article, the purpose was to present as accurate and rigurous as possible the information about the topic and discuss statistical data analyses performed so far.

What is clear is that the human-to-human transmission is very fast, the reproductive number R0 was estimated as 2.2. Therefore, it is very important to avoid social contact and follow careful hygienic habits as suggests World Health Organization.

You can read and download the full covid-19 analysis report here and follow the daily evolution of how the virus is affecting all countries on the dasbhboard produced by the Data Management & Analytics team of stratesys

 

Publicado por

Yaroslav Hernández Potiomkin

Data Scientist en STRATESYS