4. Discussion
This research is one of the first of its kind to integrate exponential
growth modelling with machine learning techniques. COVID-19 pandemic
which started in Wuhan, China is spreading at a rapid rate across the
world and understanding early signs of containment of the disease
through proper policies, interventions, and behavioural changes are very
important moving forward. The research presents machine learning models
based on variables centred towards infrastructure, environment,
policies, and the infection itself to predict if there are any early
signs of containment in the country. For the purpose, disease data from
42 leading countries in COVID-19 infections were taken and exponential
growth modelling was used to see if the countries showed signs of
containment. Then with the sign of the containment of the infection as a
dependent variable, supervised machine learning predictive models
including logistic regression, decision tree, random forest, and support
vector machine were developed. This research can directly of use to
countries and policymakers to understand if the interventions they take
is effective or not in containing infections. Table 5 shows a step of
steps taken by countries as an attempt to contain the COVID-19 infection
from spreading.
This research identifies a group of countries that have successfully or
showing signs of containing COVID-19 since infection form the
exponential growth modelling in stage I of the research. Logistic
regression results prove the need for infrastructure and the percentage
of lockdown days as significant factors to contain infections. This
research also proves that environmental factors like temperature and
humidity of the countries do not significantly affect spreading patterns
or contain COVID-19 infections. Decision tree analysis also shows that
early signs of containment are possible if the number of lockdown days
is at least 33.7% of the days since the first contact to contain the
infection. If that is not the case, countries show recovery signs if the
lockdown is at least 10 days or more. For countries on a lower lockdown
period of lesser than 10 days, the number of deaths per million
population plays a significant role in containing the infection. This
variable is indirectly related to the health care infrastructure of
countries like beds, physician, ventilators, ICUs etc. The machine
learning models random forest and support vector machines were able to
classify the countries with respect to their signs of initial
containment with an accuracy of 92.9 and 76.2 percentages respectively
proving decision trees to be the best machine learning algorithm in
pandemic situations.
While almost all countries practised lockdowns to contain the virus,
certain countries have also taken some unique measures to contain the
infection. China is one of the very first countries in the world to
contain and control COVID-19. China used policy changes in terms of
lockdowns, travel restrictions, infrastructure development, and machine
learning to properly predict and flatten the infection curve over time
and has almost resumed normal lives. Studying the transmission dynamics
of the COVID-19 virus in different settings and continuously measuring
the ongoing progress and impact lead to the containment (WHO, 2020b).
Austria enforced strict rules on social distancing, closure of schools
and colleges, the closing of entertainment and grouping places and this
has led to showing initial signs of containment. The country passed a
special act called COVID-19 Act which has proven effective to contain
the infection [62]. The number of hospital beds per 1000 population
of Austria was also on the higher side facilitating early recovery.
Chile has implemented sanitary barriers and intense screening mechanisms
to track and quarantine the infected [63]. Despite the tough
quarantine measures, Denmark closed down schools and also announced
lockdown in March. Employers were also instructed to not cut down the
salaries of the employees on quarantine thereby inducing social
distancing and hence containing the infection[64]. Japan, South
Korea, and Singapore did not announce any lockdowns. South Korea used
processes that led to early detection of the COVID-19 and quarantining
the infected making virus spreads impossible. They also predicted the
movement of viruses and tactical interventions were taken to minimize
spread [65] . Singapore had a ready infrastructure with isolation
wards in place during the SARS outbreak and was readily equipped which
led to early containment of COVID-19. Strong community engagement
messages and communications from the government was also a reason to
contain the virus in Singapore [66]. Most other countries that
showed early signs of recovery rigorously followed lockdowns, social
distancing, travel restrictions, and rigorous testing to contain
infections. Another reason for the countries like Japan, Korea and
Austria to contain the infection was their availability of health care
infrastructure to address the infections.
Table 5. Actions and Policies of Government to Contain COVID-19