Machine Learning-Based Analyses of the Effects of Various Types of Air Pollutants on Hospital Visits by Asthma Patients

Abstract

Asthma is a chronic respiratory disorder defined by airway inflammation, chest pains, wheezing, coughing, and difficulty breathing that affects an estimated 300 million individuals globally. Although various studies have shown an association between air pollution and asthma, few studies have used statistical and machine learning algorithms to investigate the effect of each individual air pollutant on asthma. The purpose of this research was to assess the association between air pollutants and the frequency of hospital visits by asthma patients using three analysis methods: linear correlation analyses were performed by Pearson correlation coefficients, and least absolute shrinkage and selection operator (LASSO) and random forest (RF) models were used for machine learning-based analyses to investigate the effect of air pollutants. This research studied asthma patients using the hospital visit database in Seoul, South Korea, collected between 2013 and 2017. The data set included outpatient hospital visits (n = 17,787,982), hospital admissions (n = 215,696), and emergency department visits (n = 85,482). The daily atmospheric environmental information from 2013 to 2017 at 25 locations in Seoul was evaluated. The three analysis models revealed that NO₂ was the most significant pollutant on average in outpatient hospital visits by asthma patients. For example, NO₂ had the greatest impact on outpatient hospital visits, resulting in a positive association (r=0.331). In hospital admissions of asthma patients, CO was the most significant pollutant on average. It was observed that CO exhibited the most positive association with hospital admissions (I = 3.329). Additionally, a significant time lag was found between both NO₂ and CO and outpatient hospital visits and hospital admissions of asthma patients in the linear correlation analysis. In particular, NO₂ and CO were shown to increase hospital admissions at lag 4 in the linear correlation analysis. This study provides evidence that PM_2.5, PM₁₀, NO₂, CO, SO₂, and O₃ are associated with the frequency of hospital visits by asthma patients.

Keywords: air pollutants; asthma; hospital visits; least absolute shrinkage and selection operator; linear correlation analysis; national health insurance database; random forest.

Figure 1

Preprocessing procedures for the database used in this study.

Figure 2

Coefficients between hospital visits and air pollutants using linear correlation analysis.

Figure 3

Coefficients between hospital visits and air pollutants using least absolute shrinkage and selection operator (LASSO).

Figure 4

The variable importance of pollutants on hospital visits using the random forest (RF) model.