Identifying novel factors associated with COVID-19 transmission and fatality using the machine learning approach

The COVID-19 virus has infected millions of people and resulted in hundreds of thousands of deaths worldwide. By using the logistic regression model, we identified novel critical factors associated with COVID19 cases, death, and case fatality rates in 154 countries and in the 50 U.S. states. Among numerous factors associated with COVID-19 risk, we found that the unitary state system was counter-intuitively positively associated with increased COVID-19 cases and deaths. Blood type B was a protective factor for COVID-19 risk, while blood type A was a risk factor. The prevalence of HIV, influenza and pneumonia, and chronic lower respiratory diseases was associated with reduced COVID-19 risk. Obesity and the condition of unimproved water sources were associated with increased COVID-19 risk. Other factors included temperature, humidity, social distancing, smoking, and vitamin D intake. Our comprehensive identification of the factors affecting COVID-19 transmission and fatality may provide new insights into the COVID-19 pandemic and advise effective strategies for preventing and migrating COVID-19 spread.