Modeling of COVID‐19 death rate using various air pollutants: A multiple linear regression approach

Abstract

AbstractAir pollution is a significant health risk, especially for vulnerable populations such as children, people with chronic illnesses, the elderly, and the economically and socially disadvantaged. Furthermore, air pollution has enormous social costs that we all bear in the form of premature deaths, low productivity, sick leave, and other strains on the healthcare system. The primary sources of air pollution are traffic, home fires, and industry. Measuring NO2 levels in air pollution reveals the extent of pollution caused by traffic, particularly diesel vehicles, which are the primary source of NO2. COVID‐19 rates are rising in areas with high levels of air pollution, according to mounting evidence. Toxic contaminants can make people more susceptible to COVID‐19. The causal relationship between air pollution and COVID‐19 cases has yet to be established, but experts warn that long‐term exposure will undoubtedly make people more susceptible to lung infections. Air pollution has been linked to an increase in cancer, heart disease, stroke, diabetes, asthma, and other comorbidities by inducing cellular damage and inflammation throughout the body. All of these factors increase the risk of death in COVID‐19 patients. As a result, air quality parameters must be predicted and monitored. To predict results, this study proposes a statistical‐based machine learning approach. Using multiple linear regression (MLR), Decision Tree (D.T.), and Random Forest (R.F.), the experimental results achieved 80%, 73%, and 65% accuracy on the dataset, respectively.