2021 •
Predicting Novel CoronaVirus 2019 with Machine Learning Algorithms
Authors:
Umang Soni, Nishu Gupta, Sakshi
Abstract:
The 2019 coronavirus pandemic which started infecting the people of Wuhan, China during December 2019 has affected many countries worldwide within a span of 4–5 months. This has forced the countries to close their borders resulting in a global lockdown. The World Health Organization declared the disease as a pandemic during early March this year. As of 15th April 2020, nearly 3 months since the spread of the disease, no vaccine has been developed and preventive measures such as social distancing and countrywide lockdown seem to be the only wa (...)
The 2019 coronavirus pandemic which started infecting the people of Wuhan, China during December 2019 has affected many countries worldwide within a span of 4–5 months. This has forced the countries to close their borders resulting in a global lockdown. The World Health Organization declared the disease as a pandemic during early March this year. As of 15th April 2020, nearly 3 months since the spread of the disease, no vaccine has been developed and preventive measures such as social distancing and countrywide lockdown seem to be the only way to prevent it from spreading further. The rising death toll indicates the need to carry out extensive research to aid medical practitioners as well as the governments worldwide to comprehend the rapid spread of the disease. While many research papers have been published explaining the origin and theoretical background of the disease, further research is needed to develop better prediction models. The data for the problem was generated from the sources available during the course of this study. This paper extensively analyzes the medical features of 269 patients using various Machine Learning techniques such as KNN, Random Forest, Ridge classifier, Decision Tree, Support Vector Classifier and Logistic Regression. The paper aims to predict the fatality status of an individual diagnosed with COVID-19 by assessing various factors including age, symptoms, etc. The experimental results from the research would help medical practitioners to identify the patients at higher risk and require extra medical attention, thereby helping the medical practitioners to prioritize them and increase their chances of survival. (Read More)
Artificial intelligence |
Machine learning |
Data science |
We have placed cookies on your device to help make this website and the services we offer better. By using this site, you agree to the use of cookies. Learn more