How can we evaluate an interrelation of symptoms?

Area of Science:

• Epidemiology
• Biostatistics
• Infectious Diseases

Background:

• The COVID-19 pandemic necessitates understanding mortality risk factors.
• Existing statistical methods struggle to comprehensively assess combined patient characteristics and symptoms for mortality risk.

Purpose of the Study:

• To apply the Boolean Monte Carlo method (BMCM) to identify interrelations between patient characteristics, symptoms, and mortality in COVID-19.
• To develop a more comprehensive risk estimation model for COVID-19 mortality.

Main Methods:

• Boolean Monte Carlo method (BMCM) applied to the Novel Corona Virus 2019 Dataset.
• Analysis utilized age, fever (onset symptom), and sex as explanatory variables, with death as the objective variable.

Main Results:

• A statistically significant association (p < 0.0001) was found between age, fever, and sex for predicting death.
• The interrelation indicated that the concurrent presence of these three factors significantly increases mortality risk.

Conclusions:

• Concurrent age, fever, and male sex are strongly associated with increased mortality risk in COVID-19 patients.
• BMCM provides a valuable statistical approach for comprehensive risk assessment in complex epidemiological scenarios.