Maternal exposure to ambient PM10 during pregnancy increases the risk of congenital heart defects: Evidence from machine learning models

doi:10.1016/j.scitotenv.2018.02.181

	Maternal exposure to ambient PM10 during pregnancy increases the risk of congenital heart defects: Evidence from machine learning models
	Ren, Zhoupeng 1; Zhu, Jun 2,3; Gao, Yanfang 1; Yin, Qian 1; Hu, Maogui 1; Dai, Li 2; Deng, Changfei 2; Yi, Lin 3; Deng, Kui 3; Wang, Yanping 2
刊名	SCIENCE OF THE TOTAL ENVIRONMENT
	2018-07-15
卷号	630 页码:1-10
关键词	Congenital heart defects Machine learning Air pollution Birth defects Particulate matter
ISSN号	0048-9697
DOI	10.1016/j.scitotenv.2018.02.181
通讯作者	Li, Xiaohong(iiaoong@163.com) ; Wang, Jinfeng(wangjf@lreis.ac.cn)
英文摘要	Previous research suggested an association between maternal exposure to ambient air pollutants and risk of congenital heart defects (CHDs), though the effects of particulate matter <= 10 mu m in aerodynamic diameter (PM10) on CHDs arc inconsistent. We used two machine learning models (i.e., random forest (RE) and gradient boosting (GB)) to investigate the non-linear effects of PM10 exposure during the critical time window, weeks 3-8 in pregnancy, on risk of CHDs. From 2009 through 2012, we carried out a population-based birth cohort study on 39,053 live-born infants in Beijing. Rr and GB models were used to calculate odds ratios for CHDs associated with increase in PM10 exposure, adjusting for maternal and perinatal characteristics. Maternal exposure to PM10 was identified as the primary risk factor for CHDs in all machine learning models. We observed a clear non-linear effect of maternal exposure to PM10 on CHDs risk. Compared to 40 mu g m(-3), the following odds ratios resulted: 1) 92 mu g m(-3) [RF: 1.16 (95% CI: 1.06, 1.28); GB: 1.26 (95% CI: 1.17,135)]; 2) 111 mu g m(-3) [RF: 1.04 (95% CI: 0.96,1.14); GB: 1.04 (95% CI: 0.99,1.08)1; 3) 124 mu g m(-3) [RF: 1.01 (95% CI: 0.94, 1.10); GB: 0.98 (95% CI: 0.93,1.02)]; 4) 190 mu g m(-3) [RF: 129 (95% CI: 1.14, 1.44); GB: 1.71 (95% CI: 1.04, 2.17)1. Overall, both machine models showed an association between maternal exposure to ambient PM10 and CHDs in Beijing, highlighting the need for non-linear methods to investigate dose-response relationships. (C) 2018 Elsevier B.V. All rights reserved.
资助项目	National Twelfth Five-Year Plan for Science & Technology Support[2014BAI06B01] ; National Key Research and Development Project[2017YFC0211705] ; National Science Foundation[41531179] ; National Science Foundation[41421001] ; National Science Foundation[81573165] ; National Science Foundation for Young Scholars of China[81502818]
WOS关键词	SAN-JOAQUIN VALLEY ; AIR-POLLUTION ; PRETERM BIRTH ; SYSTEMATIC ANALYSIS ; PARTICULATE MATTER ; UNDER-5 MORTALITY ; CHILD-MORTALITY ; NORTH-CAROLINA ; CHINA ; DISEASE
WOS研究方向	Environmental Sciences & Ecology
语种	英语
出版者	ELSEVIER SCIENCE BV
WOS记录号	WOS:000432467700001
资助机构	National Twelfth Five-Year Plan for Science & Technology Support ; National Key Research and Development Project ; National Science Foundation ; National Science Foundation for Young Scholars of China
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/54894]
专题	中国科学院地理科学与资源研究所
通讯作者	Li, Xiaohong; Wang, Jinfeng
作者单位	1.Chinese Acad Sci, Inst Geog Sci & Nat Resource Res, State Key Lab Resources & Environm Informat Syst, Beijing, Peoples R China 2.Sichuan Univ, West China Univ Hosp 2, Dept Obstet, Natl Off Maternal & Child Hlth Surveillance China, Chengdu, Sichuan, Peoples R China 3.Sichuan Univ, West China Univ Hosp 2, Dept Pediat, Natl Ctr Birth Defect Monitoring China, Chengdu, Sichuan, Peoples R China 4.Sichuan Univ, Minist Educ, Key Lab Birth Defects & Related Dis Women & Child, Chengdu, Sichuan, Peoples R China 5.Univ Chinese Acad Sci, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Ren, Zhoupeng,Zhu, Jun,Gao, Yanfang,et al. Maternal exposure to ambient PM10 during pregnancy increases the risk of congenital heart defects: Evidence from machine learning models[J]. SCIENCE OF THE TOTAL ENVIRONMENT,2018,630:1-10.
APA	Ren, Zhoupeng.,Zhu, Jun.,Gao, Yanfang.,Yin, Qian.,Hu, Maogui.,...&Wang, Jinfeng.(2018).Maternal exposure to ambient PM10 during pregnancy increases the risk of congenital heart defects: Evidence from machine learning models.SCIENCE OF THE TOTAL ENVIRONMENT,630,1-10.
MLA	Ren, Zhoupeng,et al."Maternal exposure to ambient PM10 during pregnancy increases the risk of congenital heart defects: Evidence from machine learning models".SCIENCE OF THE TOTAL ENVIRONMENT 630(2018):1-10.