Regression analysis of air pollution and pediatric respiratory diseases based on interpretable machine learning
Air pollution is of high relevance to human health. In this study, multiple machine-learning (ML) models—linear regression, random forest (RF), AdaBoost, and neural networks (NNs)—were used to explore the potential impacts of air-pollutant concentrations on the incidence of pediatric respiratory dis...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-03-01
|
| Series: | Frontiers in Earth Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/feart.2023.1105140/full |
| _version_ | 1811162600509014016 |
|---|---|
| author | Yan Ji Yan Ji Xiefei Zhi Xiefei Zhi Ying Wu Yanqiu Zhang Yitong Yang Ting Peng Luying Ji |
| author_facet | Yan Ji Yan Ji Xiefei Zhi Xiefei Zhi Ying Wu Yanqiu Zhang Yitong Yang Ting Peng Luying Ji |
| author_sort | Yan Ji |
| collection | DOAJ |
| description | Air pollution is of high relevance to human health. In this study, multiple machine-learning (ML) models—linear regression, random forest (RF), AdaBoost, and neural networks (NNs)—were used to explore the potential impacts of air-pollutant concentrations on the incidence of pediatric respiratory diseases in Taizhou, China. A number of explainable artificial intelligence (XAI) methods were further applied to analyze the model outputs and quantify the feature importance. Our results demonstrate that there are significant seasonal variations both in the numbers of pediatric respiratory outpatients and the concentrations of air pollutants. The concentrations of NO2, CO, and particulate matter (PM10 and PM2.5), as well as the numbers of outpatients, reach their peak values in the winter. This indicates that air pollution is a major factor in pediatric respiratory diseases. The results of the regression models show that ML methods can capture the trends and turning points of clinic visits, and the non-linear models were superior to the linear ones. Among them, the RF model served as the best-performing model. The analysis on the RF model by XAI found that AQI, O3, PM10, and the current month are the most important predictors affecting the numbers of pediatric respiratory outpatients. This shows that the number of outpatients rises with an increasing AQI, especially with the increasing of particulate matter. Our study indicates that ML models with XAI methods are promising for revealing the underlying impacts of air pollution on the pediatric respiratory diseases, which further assists the health-related decision-making. |
| first_indexed | 2024-04-10T06:32:04Z |
| format | Article |
| id | doaj.art-9205fb2c63654d29a4c0206da1bf2647 |
| institution | Directory Open Access Journal |
| issn | 2296-6463 |
| language | English |
| last_indexed | 2024-04-10T06:32:04Z |
| publishDate | 2023-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Earth Science |
| spelling | doaj.art-9205fb2c63654d29a4c0206da1bf26472023-03-01T05:35:24ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632023-03-011110.3389/feart.2023.11051401105140Regression analysis of air pollution and pediatric respiratory diseases based on interpretable machine learningYan Ji0Yan Ji1Xiefei Zhi2Xiefei Zhi3Ying Wu4Yanqiu Zhang5Yitong Yang6Ting Peng7Luying Ji8Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters (CIC-FEMD)/Key Laboratory of Meteorological Disasters, Ministry of Education (KLME), Nanjing University of Information Science and Technology, Nanjing, ChinaWeather Online Institute of Meteorological Applications, Wuxi, ChinaCollaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters (CIC-FEMD)/Key Laboratory of Meteorological Disasters, Ministry of Education (KLME), Nanjing University of Information Science and Technology, Nanjing, ChinaWeather Online Institute of Meteorological Applications, Wuxi, ChinaTaizhou Environmental Monitoring Center, Taizhou, ChinaDepartment of Environmental Occupational Hygiene, Taizhou Center for Disease Control and Prevention, Taizhou, ChinaDepartment of Environmental Occupational Hygiene, Taizhou Center for Disease Control and Prevention, Taizhou, ChinaTaizhou Environmental Monitoring Center, Taizhou, ChinaKey Laboratory of Transportation Meteorology of China Meteorological Administration, Nanjing Joint Institute for Atmospheric Sciences, Nanjing, ChinaAir pollution is of high relevance to human health. In this study, multiple machine-learning (ML) models—linear regression, random forest (RF), AdaBoost, and neural networks (NNs)—were used to explore the potential impacts of air-pollutant concentrations on the incidence of pediatric respiratory diseases in Taizhou, China. A number of explainable artificial intelligence (XAI) methods were further applied to analyze the model outputs and quantify the feature importance. Our results demonstrate that there are significant seasonal variations both in the numbers of pediatric respiratory outpatients and the concentrations of air pollutants. The concentrations of NO2, CO, and particulate matter (PM10 and PM2.5), as well as the numbers of outpatients, reach their peak values in the winter. This indicates that air pollution is a major factor in pediatric respiratory diseases. The results of the regression models show that ML methods can capture the trends and turning points of clinic visits, and the non-linear models were superior to the linear ones. Among them, the RF model served as the best-performing model. The analysis on the RF model by XAI found that AQI, O3, PM10, and the current month are the most important predictors affecting the numbers of pediatric respiratory outpatients. This shows that the number of outpatients rises with an increasing AQI, especially with the increasing of particulate matter. Our study indicates that ML models with XAI methods are promising for revealing the underlying impacts of air pollution on the pediatric respiratory diseases, which further assists the health-related decision-making.https://www.frontiersin.org/articles/10.3389/feart.2023.1105140/fullair pollutantsrespiratory diseases in childrenexplainable artificial intelligence (XAI)feature importance analysisTaizhou city |
| spellingShingle | Yan Ji Yan Ji Xiefei Zhi Xiefei Zhi Ying Wu Yanqiu Zhang Yitong Yang Ting Peng Luying Ji Regression analysis of air pollution and pediatric respiratory diseases based on interpretable machine learning Frontiers in Earth Science air pollutants respiratory diseases in children explainable artificial intelligence (XAI) feature importance analysis Taizhou city |
| title | Regression analysis of air pollution and pediatric respiratory diseases based on interpretable machine learning |
| title_full | Regression analysis of air pollution and pediatric respiratory diseases based on interpretable machine learning |
| title_fullStr | Regression analysis of air pollution and pediatric respiratory diseases based on interpretable machine learning |
| title_full_unstemmed | Regression analysis of air pollution and pediatric respiratory diseases based on interpretable machine learning |
| title_short | Regression analysis of air pollution and pediatric respiratory diseases based on interpretable machine learning |
| title_sort | regression analysis of air pollution and pediatric respiratory diseases based on interpretable machine learning |
| topic | air pollutants respiratory diseases in children explainable artificial intelligence (XAI) feature importance analysis Taizhou city |
| url | https://www.frontiersin.org/articles/10.3389/feart.2023.1105140/full |
| work_keys_str_mv | AT yanji regressionanalysisofairpollutionandpediatricrespiratorydiseasesbasedoninterpretablemachinelearning AT yanji regressionanalysisofairpollutionandpediatricrespiratorydiseasesbasedoninterpretablemachinelearning AT xiefeizhi regressionanalysisofairpollutionandpediatricrespiratorydiseasesbasedoninterpretablemachinelearning AT xiefeizhi regressionanalysisofairpollutionandpediatricrespiratorydiseasesbasedoninterpretablemachinelearning AT yingwu regressionanalysisofairpollutionandpediatricrespiratorydiseasesbasedoninterpretablemachinelearning AT yanqiuzhang regressionanalysisofairpollutionandpediatricrespiratorydiseasesbasedoninterpretablemachinelearning AT yitongyang regressionanalysisofairpollutionandpediatricrespiratorydiseasesbasedoninterpretablemachinelearning AT tingpeng regressionanalysisofairpollutionandpediatricrespiratorydiseasesbasedoninterpretablemachinelearning AT luyingji regressionanalysisofairpollutionandpediatricrespiratorydiseasesbasedoninterpretablemachinelearning |