A Machine Learning Based Determining the Effects of Air Pollution and Weather in Respiratory Disease Patients Visiting at Emergency Department Using a National Emergency Department Information System in Seoul, Korea

Abstract

Introduction: Fine dust known as a group 1 carcinogen is reportedly related to death, stroke, neuropathy, hypertension, cardiovascular, and respiratory diseases. To date, there is no relevant research regarding respiratory disease patients who visit emergency departments. This study aimed to analyze the effects of weather and air pollution as variables on respiratory disease patients who visited the emergency departments.

Materials and Method: Among the patients who had visited emergency medical centers in Seoul over the last 3 years, those whose disease classification code (J code; J00–J99) was related to respiratory diseases according to the Korean Standard Classification of Diseases (based on International Classification of Diseases -10) at the time of leaving an emergency department were selected. Carbon monoxide, nitrogen dioxide, ozone (O3), PM₁₀, PM_2·5, sulfur trioxide, average temperature, amount of precipitation, relative humidity, steam pressure, wind speed, and wind direction were used as variables in the Random Forest Regression model. In the model, the effects of these variables on the diseases were analyzed.

Results: The study included 525,579 participants. With regard to PM₁₀, a patient’s visit to an emergency department due to an acute upper respiratory infection [J00–J06] had high correlations with day 0, and day 1. With regard to influenza [J09–J11], pneumonia [J12–J18], other acute lower respiratory infections [J20–J22], and other diseases of the upper respiratory tract [J30–J39], day 0 was influential. In the case of chronic lower respiratory diseases [J40–J47], day 0, day 1, day 2, and day 3 influenced a patient’s visit to the emergency department. In the case of suppurative and necrotic conditions of the lower respiratory tract [J85–J86], day 0 was influential.

Conclusion: This study found that multiple variables of weather and air pollution influenced the respiratory diseases of patients who visited emergency departments. Most of the respiratory disease patients had acute upper respiratory infections [J00–J06], influenza [J09–J11], and pneumonia [J12–J18] on which PM₁₀ following temperature and steam pressure was most influential. As the top three leading causes of admission to the emergency department, pneumonia [J12–J18], acute upper respiratory infections [J00–J06], and chronic lower respiratory diseases [J40–J47] were highly influenced by PM₁₀. Given the results, among air pollution variables, PM₁₀ influenced the respiratory disease patients’ visits to the emergency departments. It is expected that the number of respiratory disease patients visiting the emergency departments will increase by day 3 when the steam pressure and temperature values are low and the variables of air pollution are high.

Funding Statement: Korea University Guro Hospital ‘KOREA RESEARCH-DRIVEN HOSPITALS’ Grant (O1905501)

Declaration of Interests: All authors declare no competing interests.

Ethics Approval Statement: This study was approved by the institutional review board of the Korea University Guro Hospital (NO. 2019GR0197). The requirement for informed consent from the participants was waived by the board.

Keywords: Air Pollution, Emergency Medical Services, Machine Learning