تاثیر آلودگی هوا بر پذیرش بیمارستانی با علایم تنفسی با استفاده از مدل شبکه عصبی

  Background and Aim: A ssociations between air pollution and morbidity have been reported in several studies. Due to limited publications in the literature for Iran, this study aimed to determine the association between air pollution and hospital admissions of respiratory disease patients in Tabriz, Iran.   Materials and Methods: The methodology used in this study was case -crossover and the artificial neural network model. The variables of the model included air quality, hospital admission and air pollutants. Daily hospital admission data were collected from five hospitals in Tabriz, Iran based on the International Classification of Diseases (ICD-10) , air quality data including NO2, SO2, CO, PM10 and O3 from the six fixed online air quality monitoring stations, and the daily mean temperature and relative humidity data for the same period from the East Azerbaijan Meteorological Bureau.   Results : P articulate matter with a median aerometric diameter <10 μm (PM10) was found to be the most important pollutant affecting respiratory hospital admissions. The ANNs data showed that the most important causes of hospital admissions were for COPD NO2, NO and CO, for respiratory infections PM10, and for asthma PM10, O3 and CO. The highest associations were observed between hospital admissions due to COPD and asthma in females and those due to respiratory infections in males. The elderly (individuals over 65 years old) were at the highest risk.   Conclusion: The results show a significant relation between air pollutants and respiratory hospital admissions in Tabriz, Iran. The importance and necessity of enforcement of existing regulations and enacting laws to prevent and control the adverse health effects of air pollution are confirmed.