|
Estimation of Covid-19 Mortality Rate in Iran using the Autoregressive Model
|
Atefeh Goshvarpour   , Ateke Goshvarpour * |
| Department of Biomedical Engineering, Imam Reza International University, Mashhad, Razavi Khorasan, Iran , ak_goshvarpour@imamreza.ac.ir |
|
|
Abstract: (4198 Views) |
Introduction: The COVID-19 is an emerging global pandemic which has been developed from a new type of coronavirus in the form of a viral infection with high transmissibility and spread. The disease has so far infected millions and killed thousands. Since the outbreak of the disease, many researchers have become interested in modeling and estimating the probable number of infected people with COVID-19 or estimating the mortality rate from this pandemic in a specific period of time and in different countries. These models make it possible to better understand the behavior of this pandemic and predict its trend. This study aimed to model the mortality rate due to the COVID-19 pandemic in five consecutive months in Iran.
Materials and Methods: The Autoregressive (AR) model and the Autoregressive Moving Average (ARMA) model were analyzed to test the ability of these models to estimate the mortality rate of COVID-19 disease from March to July. The performance of these models was evaluated with three criteria: mean square error, cost function, and final prediction error. The models were evaluated on the number of deaths confirmed by the Iran Ministry of Health and Medical Education.
Results: The results of the analysis showed that the AR model with a rank of ten was successfully able to predict the mortality rate of COVID-19.
Conclusion: The proposed model can predict the death rate of the COVID-19 pandemic. Estimating the mortality rate of the COVID-19 pandemic helps to better understand the behavior of this disease and predict its trends, which affect the type and timing of actions to control it. |
|
| Keywords: COVID-19, Modeling, Mortality Rate, Iran, Autoregressive Model |
|
|
Full-Text [PDF 1063 kb]
(1378 Downloads)
|
Type of Study: Research |
Subject:
Special
Received: 2020/08/21 | Accepted: 2020/10/18 | Published: 2020/11/9
|
|
|
|
|
|
