Using an Artificial Neural Network Model to Predict the Number of COVID-۱۹ Cases in Iran

Background: Forecasting methods are used in various fields including the health problems. This study aims to use the Artificial Neural Network (ANN) method for predicting coronavirus disease ۲۰۱۹ (COVID-۱۹) cases in Iran. Materials and Methods: This is a descriptive, analytical, and comparative study to predict the time series of COVID-۱۹ cases in Iran from May ۲۰۲۰ to May ۲۰۲۱. An ANN model was used for forecast​ing, which had three Input, output, and intermediate layers. The network training was conducted by the Levenberg-Marquardt algorithm. The forecasting accuracy was measured by calculating the mean absolute percentage error. Results: The mean absolute error of the designed ANN model was ۶ and its accuracy was ۹۴%. Conclusion: The ANN has high accuracy in forecasting the number of COVID-۱۹ cases in Iran. The outputs of this model can be used as a basis for decisions in controlling the COVID-۱۹.