Journal
ENVIRONMENTAL RESEARCH
Volume 200, Issue -, Pages -Publisher
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.envres.2021.111344
Keywords
Asthma; Air pollution; Machine learning; Spatio-temporal modeling
Funding
- MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program [IITP-2021-2016-0-00312]
Ask authors/readers for more resources
Industrialization and urbanization have worsened air pollution, impacting public health and asthma. This study modeled the spatial-temporal patterns of asthma in Tehran, Iran using machine learning, finding that PM2.5 had the most significant impact on asthma occurrence. Evaluation results suggested that asthma is more likely to occur in autumn.
Industrialization and increasing urbanization have led to increased air pollution, which has a devastating effect on public health and asthma. This study aimed to model the spatial-temporal of asthma in Tehran, Iran using a machine learning model. Initially, a spatial database was created consisting of 872 locations of asthma children and six air pollution parameters, including carbon monoxide (CO), particulate matter (PM10 and PM2.5), nitrogen dioxide (NO2), sulfur dioxide (SO2), and ozone (O3) in four-seasons (spring, summer, autumn, and winter). Spatial-temporal modeling and mapping of asthma-prone areas were performed using a random forest (RF) model. For Spatio-temporal modeling and assessment, 70% and 30% of the dataset were used, respectively. The Spearman correlation and RF model findings showed that during different seasons, the PM2.5 parameter had the most important effect on asthma occurrence in Tehran. The assessment of the Spatio-temporal modeling of asthma using the receiver operating characteristic (ROC)-area under the curve (AUC) showed an accuracy of 0.823, 0.821, 0.83, and 0.827, respectively for spring, summer, autumn, and winter. According to the results, asthma occurs more often in autumn than in other seasons.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available