Long-term exposure to particulate matter was associated with increased dementia risk using both traditional approaches and novel machine learning methods
Abstract Air pollution exposure has been linked to various diseases, including dementia. However, a novel method for investigating the associations between air pollution exposure and disease is lacking. The objective of this study was to investigate whether long-term exposure to ambient particulate...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-10-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-22100-8 |
| _version_ | 1798029976530845696 |
|---|---|
| author | Yuan-Horng Yan Ting-Bin Chen Chun-Pai Yang I-Ju Tsai Hwa-Lung Yu Yuh-Shen Wu Winn-Jung Huang Shih-Ting Tseng Tzu-Yu Peng Elizabeth P. Chou |
| author_facet | Yuan-Horng Yan Ting-Bin Chen Chun-Pai Yang I-Ju Tsai Hwa-Lung Yu Yuh-Shen Wu Winn-Jung Huang Shih-Ting Tseng Tzu-Yu Peng Elizabeth P. Chou |
| author_sort | Yuan-Horng Yan |
| collection | DOAJ |
| description | Abstract Air pollution exposure has been linked to various diseases, including dementia. However, a novel method for investigating the associations between air pollution exposure and disease is lacking. The objective of this study was to investigate whether long-term exposure to ambient particulate air pollution increases dementia risk using both the traditional Cox model approach and a novel machine learning (ML) with random forest (RF) method. We used health data from a national population-based cohort in Taiwan from 2000 to 2017. We collected the following ambient air pollution data from the Taiwan Environmental Protection Administration (EPA): fine particulate matter (PM2.5) and gaseous pollutants, including sulfur dioxide (SO2), carbon monoxide (CO), ozone (O3), nitrogen oxide (NOx), nitric oxide (NO), and nitrogen dioxide (NO2). Spatiotemporal-estimated air quality data calculated based on a geostatistical approach, namely, the Bayesian maximum entropy method, were collected. Each subject's residential county and township were reviewed monthly and linked to air quality data based on the corresponding township and month of the year for each subject. The Cox model approach and the ML with RF method were used. Increasing the concentration of PM2.5 by one interquartile range (IQR) increased the risk of dementia by approximately 5% (HR = 1.05 with 95% CI = 1.04–1.05). The comparison of the performance of the extended Cox model approach with the RF method showed that the prediction accuracy was approximately 0.7 by the RF method, but the AUC was lower than that of the Cox model approach. This national cohort study over an 18-year period provides supporting evidence that long-term particulate air pollution exposure is associated with increased dementia risk in Taiwan. The ML with RF method appears to be an acceptable approach for exploring associations between air pollutant exposure and disease. |
| first_indexed | 2024-04-11T19:32:57Z |
| format | Article |
| id | doaj.art-70b4eae7351e4d26afc9e9ff3dc8d896 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-11T19:32:57Z |
| publishDate | 2022-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-70b4eae7351e4d26afc9e9ff3dc8d8962022-12-22T04:06:56ZengNature PortfolioScientific Reports2045-23222022-10-011211910.1038/s41598-022-22100-8Long-term exposure to particulate matter was associated with increased dementia risk using both traditional approaches and novel machine learning methodsYuan-Horng Yan0Ting-Bin Chen1Chun-Pai Yang2I-Ju Tsai3Hwa-Lung Yu4Yuh-Shen Wu5Winn-Jung Huang6Shih-Ting Tseng7Tzu-Yu Peng8Elizabeth P. Chou9Department of Endocrinology and Metabolism, Kuang Tien General HospitalDepartment of Neurology, Neurological Institute, Taichung Veterans General HospitalDepartment of Medical Research, Kuang Tien General HospitalDepartment of Medical Research, Kuang Tien General HospitalDepartment of Bioenvironmental Systems Engineering, National Taiwan UniversityDepartment of Safety, Health, and Environmental Engineering, Hungkuang UniversityDepartment of Safety, Health, and Environmental Engineering, Hungkuang UniversityDivision of Endocrinology and Metabolism, Department of Internal Medicine, Kuang Tien General HospitalDepartment of Statistics, National Chengchi UniversityDepartment of Statistics, National Chengchi UniversityAbstract Air pollution exposure has been linked to various diseases, including dementia. However, a novel method for investigating the associations between air pollution exposure and disease is lacking. The objective of this study was to investigate whether long-term exposure to ambient particulate air pollution increases dementia risk using both the traditional Cox model approach and a novel machine learning (ML) with random forest (RF) method. We used health data from a national population-based cohort in Taiwan from 2000 to 2017. We collected the following ambient air pollution data from the Taiwan Environmental Protection Administration (EPA): fine particulate matter (PM2.5) and gaseous pollutants, including sulfur dioxide (SO2), carbon monoxide (CO), ozone (O3), nitrogen oxide (NOx), nitric oxide (NO), and nitrogen dioxide (NO2). Spatiotemporal-estimated air quality data calculated based on a geostatistical approach, namely, the Bayesian maximum entropy method, were collected. Each subject's residential county and township were reviewed monthly and linked to air quality data based on the corresponding township and month of the year for each subject. The Cox model approach and the ML with RF method were used. Increasing the concentration of PM2.5 by one interquartile range (IQR) increased the risk of dementia by approximately 5% (HR = 1.05 with 95% CI = 1.04–1.05). The comparison of the performance of the extended Cox model approach with the RF method showed that the prediction accuracy was approximately 0.7 by the RF method, but the AUC was lower than that of the Cox model approach. This national cohort study over an 18-year period provides supporting evidence that long-term particulate air pollution exposure is associated with increased dementia risk in Taiwan. The ML with RF method appears to be an acceptable approach for exploring associations between air pollutant exposure and disease.https://doi.org/10.1038/s41598-022-22100-8 |
| spellingShingle | Yuan-Horng Yan Ting-Bin Chen Chun-Pai Yang I-Ju Tsai Hwa-Lung Yu Yuh-Shen Wu Winn-Jung Huang Shih-Ting Tseng Tzu-Yu Peng Elizabeth P. Chou Long-term exposure to particulate matter was associated with increased dementia risk using both traditional approaches and novel machine learning methods Scientific Reports |
| title | Long-term exposure to particulate matter was associated with increased dementia risk using both traditional approaches and novel machine learning methods |
| title_full | Long-term exposure to particulate matter was associated with increased dementia risk using both traditional approaches and novel machine learning methods |
| title_fullStr | Long-term exposure to particulate matter was associated with increased dementia risk using both traditional approaches and novel machine learning methods |
| title_full_unstemmed | Long-term exposure to particulate matter was associated with increased dementia risk using both traditional approaches and novel machine learning methods |
| title_short | Long-term exposure to particulate matter was associated with increased dementia risk using both traditional approaches and novel machine learning methods |
| title_sort | long term exposure to particulate matter was associated with increased dementia risk using both traditional approaches and novel machine learning methods |
| url | https://doi.org/10.1038/s41598-022-22100-8 |
| work_keys_str_mv | AT yuanhorngyan longtermexposuretoparticulatematterwasassociatedwithincreaseddementiariskusingbothtraditionalapproachesandnovelmachinelearningmethods AT tingbinchen longtermexposuretoparticulatematterwasassociatedwithincreaseddementiariskusingbothtraditionalapproachesandnovelmachinelearningmethods AT chunpaiyang longtermexposuretoparticulatematterwasassociatedwithincreaseddementiariskusingbothtraditionalapproachesandnovelmachinelearningmethods AT ijutsai longtermexposuretoparticulatematterwasassociatedwithincreaseddementiariskusingbothtraditionalapproachesandnovelmachinelearningmethods AT hwalungyu longtermexposuretoparticulatematterwasassociatedwithincreaseddementiariskusingbothtraditionalapproachesandnovelmachinelearningmethods AT yuhshenwu longtermexposuretoparticulatematterwasassociatedwithincreaseddementiariskusingbothtraditionalapproachesandnovelmachinelearningmethods AT winnjunghuang longtermexposuretoparticulatematterwasassociatedwithincreaseddementiariskusingbothtraditionalapproachesandnovelmachinelearningmethods AT shihtingtseng longtermexposuretoparticulatematterwasassociatedwithincreaseddementiariskusingbothtraditionalapproachesandnovelmachinelearningmethods AT tzuyupeng longtermexposuretoparticulatematterwasassociatedwithincreaseddementiariskusingbothtraditionalapproachesandnovelmachinelearningmethods AT elizabethpchou longtermexposuretoparticulatematterwasassociatedwithincreaseddementiariskusingbothtraditionalapproachesandnovelmachinelearningmethods |