Cargando…

Analysis of COVID-19 Death Cases Using Machine Learning

COVID-19 has threatened the existence of human life for more than the last 2 years. More than 460 million confirmed cases and 6 million deaths have been reported worldwide due to COVID-19. To measure the severity of the COVID-19, the mortality rate plays an important role. Understanding the nature o...

Descripción completa

Detalles Bibliográficos
Autores principales: Aslam, Humaira, Biswas, Santanu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer Nature Singapore 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10191086/
https://www.ncbi.nlm.nih.gov/pubmed/37220559
http://dx.doi.org/10.1007/s42979-023-01835-9
Descripción
Sumario:COVID-19 has threatened the existence of human life for more than the last 2 years. More than 460 million confirmed cases and 6 million deaths have been reported worldwide due to COVID-19. To measure the severity of the COVID-19, the mortality rate plays an important role. Understanding the nature of COVID-19 and forecasting the death cases of COVID-19 require more investigation of the real effect for different risk factors. In this work, various regression machine learning models are proposed to extract the relationship between different factors and the death rate of COVID-19. The optimal regression tree algorithm employed in this work estimates the impact of essential causal variables that significantly affect the mortality rates. We have generated a real-time forecast for the death case of COVID-19 using machine learning techniques. The analysis is evaluated with the well-known regression models XGBoost, Random Forest, and SVM on the data sets of the US, India, Italy, and three continents Asia, Europe, and North America. The results show that the models can be used to forecast the death cases for the near future in case of an epidemic like Novel Coronavirus.