Interpretable machine learning-based insights into early-life endocrine disruptor exposure and small vulnerable newborns.

Journal: Journal of hazardous materials
Published Date:

Abstract

Early-life exposure to endocrine-disrupting chemicals (EDCs) may contribute to small vulnerable newborns, including conditions such as being small for gestational age (SGA) and preterm birth (PTB), yet evidence remains limited. This study, which is based on 739 mother-infant pairs in the Chinese Jiashan Birth Cohort (2016-2018), including 39 SGA and 38 PTB cases, employed interpretable machine learning to elucidate the isolated effects of 34 EDCs on SGA and PTB risk and sex interactions in a multi-substance exposure context. Extra Trees and CatBoost classifiers performed best for SGA and PTB, respectively, achieving sensitivities of 0.60 and 0.73 and specificities of 0.82 and 0.97. For SGA, key predictors included bisphenol A (2,3-dihydroxypropyl) glycidyl ether (BADGE-HO), benzophenone (bZp), bisphenol A bis(2,3-dihydroxypropyl) ether (BADGE-2HO), propyl paraben (PrP), and 2-methylthio-benzothiazole (2-Me-S-BTH). Lower exposures to BADGE-HO, bZp, and BADGE-2HO (concentrations below 0.21, 4.22, and 0.93 μg·g creatinine, respectively) and higher exposure to 2-Me-S-BTH (above 0.15 μg·g creatinine) were both associated with increased SGA risk. Notably, BADGE-HO, BADGE-2HO, and PrP showed significant interactions with fetal sex. For PTB, key predictors included ethyl paraben (EtP), methyl paraben (MeP), bZp, BADGE-HO, and 1H-benzotriazole (1-H-BTR). Lower BADGE-HO and higher EtP and bZp exposures increased PTB risk (< 0.10 and > 0.01 and 0.60 μg·g creatinine, respectively). Male fetuses appeared more susceptible to EtP and MeP, and female fetuses were more susceptible to 1-H-BTR. Bayesian kernel machine regression was performed to compare the results. This study demonstrated the potential of interpretable machine learning in environmental epidemiology.

Authors

  • Luhan Yang
    School of Environmental Science and Engineering, Sun Yat-Sen University, Guangzhou 510275, China.
  • Yuxian Liu
    Key Laboratory of Ministry of Education for Water Quality Security and Protection in Pearl River Delta, School of Environmental Science and Engineering, Guangzhou University, Guangzhou 510006, China.
  • Henglin Zhang
    School of Environmental Science and Engineering, Sun Yat-Sen University, Guangzhou 510275, China.
  • Yanan Zhao
    Department of Oncology and Hematology Surgery, China-Japan Union Hospital, Changchun, Jilin Province, China.
  • Guanglan Zhang
    Department of Obstetrics and Gynecology, Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou 510006, China.
  • Yanpeng Cai
    State Key Laboratory of Water Environment Simulation, Beijing Normal University, Beijing 100875, China; Institute of Environmental and Ecological Engineering, Guangdong University of Technology, Guangzhou 510006, China; Institute for Energy, Environment, and Sustainable Communities, University of Regina, Regina, Saskatchewan, S4S 0A2, Canada. Electronic address: yanpeng.cai@gdut.edu.cn.
  • Lan Yang
    The State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, #7 Jinsui Road, Guangzhou, Guangdong 510230, China.
  • Jianya Xi
    Shanghai-MOST Key Laboratory of Health and Disease Genomics, NHC Key Lab of Reproduction Regulation, Shanghai Institute for Biomedical and Pharmaceutical Technologies, 779 Lao Humin Road, Shanghai 200237, China.
  • Ziliang Wang
    4School of Psychology, Beijing Normal University, Beijing, PR China.
  • Hong Liang
    Department of Mechanical Engineering, Texas A&M University, College Station, TX 77843-3123, USA hliang@tamu.edu.
  • Maohua Miao
    Shanghai-MOST Key Laboratory of Health and Disease Genomics, NHC Key Lab of Reproduction Regulation, Shanghai Institute for Biomedical and Pharmaceutical Technologies, 779 Lao Humin Road, Shanghai 200237, China. Electronic address: miaomaohua@163.com.
  • Tao Zhang
    Department of Traumatology, Chongqing Emergency Medical Center, Chongqing University Central Hospital, School of Medicine, Chongqing University, Chongqing, 40044, People's Republic of China.
  • Jingchuan Xue
    Guangdong Basic Research Center of Excellence for Ecological Security and Green Development, Key Laboratory for City Cluster Environmental Safety and Green Development of the Ministry of Education, School of Ecology, Environment and Resources, Guangdong University of Technology, Guangzhou 510006, China; Guangdong Provincial Key Laboratory of Water Quality Improvement and Ecological Restoration for Watersheds, Institute of Environmental and Ecological Engineering, Guangdong University of Technology, Guangzhou 510006, China; Guangdong Provincial Observation and Research Station for Social-Natural Complex Ecosystems in Haizhu Wetlands, Guangzhou 510006, China. Electronic address: xue@gdut.edu.cn.