Investigating artificial neural networks versus regression models in predicting Myocardial Infarction (MI) mortality based on climatic elements in Sanandaj city, Iran

Abstract

Abstract In the present study, to analyze the relationship between mortality due to Myocardial Infarction (MI) with climatic parameters and its prediction, the ability of artificial neural network models, and linear and nonlinear regression in Sanandaj was evaluated. The study population in this study is the total number of monthly deaths due to myocardial infarction (MI) in Sanandaj city and also the data related to the climatic variables of Sanandaj synoptic station during the statistical period 2014–2018. Variables such as mean monthly temperature, mean minimum, and maximum monthly temperature, average monthly minimum and maximum station air pressure (QFE), total hours of sunshine, and several days with minimum temperature, equal to or below zero and the output of the models is the total number of monthly deaths due to MI in Sanandaj city. The results showed that there is a nonlinear relationship between the total number of monthly deaths due to MI and climatic parameters in Sanandaj, Which can be measured and predicted only by an artificial neural network (ANNs) model, and multiple linear and nonlinear regression models do not have the necessary efficiency in this field.