Background and Purpose: Evaluating the causal association effect of risk factors is essential in estimating the mortality rate among COVID-19 patients. Much research has been conducted to assess the impact of COVID-19 on death in various countries worldwide. However, few studies have addressed the effect of causal association of risk factors. This study aims to address this gap by estimating the impact of COVID-19 on death by evaluating the causal association with the risk factors. 
Materials and Methods: The research population included all inpatients with initial COVID-19 symptoms, confirmed by their PCR test results. They were admitted to hospitals affiliated with Golestan University of Medical Science, Golestan, Iran, in 2020. We employed the propensity score method, an effective statistical technique for evaluating the causal association effect of risk factors in observational studies. We also used the student and chi-squared tests to compare the differences between the two study groups.
Results: We used the propensity score matching estimation approach and logistic regression analysis for comparison. Of 6379 inpatients, 5581 (87.5%) were discharged or recovered, and 798 (12.5%) died. The causal association between treatment results (discharged vs died) and variables of PCR test, SpO2, gender, age, and hospitalization duration in ICU were statistically significant. 
Conclusion: The propensity score matching estimation method revealed a high risk of death in patients with PCR+ test diagnosis. Specifically, using this approach, the above-measured risk factors increased the chance of death in patients with PCR+ to 72%. However, the traditional multiple logistic regression model estimated the risk of death at 46%, suggesting potential underestimation. This disparity might be due to better control of the effect of the above-measured risk factors by the propensity score matching. Therefore, the former estimating approach is more effective in assessing the impact of COVID-19 on death.