PMID- 33249040 OWN - NLM STAT- MEDLINE DCOM- 20210421 LR - 20220402 IS - 1096-0953 (Electronic) IS - 0013-9351 (Print) IS - 0013-9351 (Linking) VI - 195 DP - 2021 Apr TI - Identifying environmental exposure profiles associated with timing of menarche: A two-step machine learning approach to examine multiple environmental exposures. PG - 110524 LID - S0013-9351(20)31421-3 [pii] LID - 10.1016/j.envres.2020.110524 [doi] AB - BACKGROUND: Variation in the timing of menarche has been linked with adverse health outcomes in later life. There is evidence that exposure to hormonally active agents (or endocrine disrupting chemicals; EDCs) during childhood may play a role in accelerating or delaying menarche. The goal of this study was to generate hypotheses on the relationship between exposure to multiple EDCs and timing of menarche by applying a two-stage machine learning approach. METHODS: We used data from the National Health and Nutrition Examination Survey (NHANES) for years 2005-2008. Data were analyzed for 229 female participants 12-16 years of age who had blood and urine biomarker measures of 41 environmental exposures, all with >70% above limit of detection, in seven classes of chemicals. We modeled risk for earlier menarche (<12 years of age vs older) with exposure biomarkers. We applied a two-stage approach consisting of a random forest (RF) to identify important exposure combinations associated with timing of menarche followed by multivariable modified Poisson regression to quantify associations between exposure profiles ("combinations") and timing of menarche. RESULTS: RF identified urinary concentrations of monoethylhexyl phthalate (MEHP) as the most important feature in partitioning girls into homogenous subgroups followed by bisphenol A (BPA) and 2,4-dichlorophenol (2,4-DCP). In this first stage, we identified 11 distinct exposure biomarker profiles, containing five different classes of EDCs associated with earlier menarche. MEHP appeared in all 11 exposure biomarker profiles and phenols appeared in five. Using these profiles in the second-stage of analysis, we found a relationship between lower MEHP and earlier menarche (MEHP 2.36 ng/mL: adjusted PR = 1.36, 95% CI: 1.02, 1.80). Combinations of lower MEHP with benzophenone-3, 2,4-DCP, and BPA had similar associations with earlier menarche, though slightly weaker in those smaller subgroups. For girls not having lower MEHP, exposure profiles included other biomarkers (BPA, enterodiol, monobenzyl phthalate, triclosan, and 1-hydroxypyrene); these showed largely null associations in the second-stage analysis. Adjustment for covariates did not materially change the estimates or CIs of these models. We observed weak or null effect estimates for some exposure biomarker profiles and relevant profiles consisted of no more than two EDCs, possibly due to small sample sizes in subgroups. CONCLUSION: A two-stage approach incorporating machine learning was able to identify interpretable combinations of biomarkers in relation to timing of menarche; these should be further explored in prospective studies. Machine learning methods can serve as a valuable tool to identify patterns within data and generate hypotheses that can be investigated within future, targeted analyses. CI - Copyright (c) 2020 Elsevier Inc. All rights reserved. FAU - Oskar, Sabine AU - Oskar S AD - Environmental Medicine and Public Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Department of Epidemiology, Columbia University Mailman School of Public Health, New York, NY, USA. Electronic address: so2359@columbia.edu. FAU - Wolff, Mary S AU - Wolff MS AD - Environmental Medicine and Public Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA. FAU - Teitelbaum, Susan L AU - Teitelbaum SL AD - Environmental Medicine and Public Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA. FAU - Stingone, Jeanette A AU - Stingone JA AD - Department of Epidemiology, Columbia University Mailman School of Public Health, New York, NY, USA. LA - eng GR - K99 ES027022/ES/NIEHS NIH HHS/United States GR - P30 ES009089/ES/NIEHS NIH HHS/United States GR - P30 ES023515/ES/NIEHS NIH HHS/United States GR - R00 ES027022/ES/NIEHS NIH HHS/United States PT - Journal Article DEP - 20201126 PL - Netherlands TA - Environ Res JT - Environmental research JID - 0147621 RN - 0 (Environmental Pollutants) RN - 0 (Phthalic Acids) SB - IM MH - Child MH - Environmental Exposure MH - *Environmental Pollutants MH - Female MH - Humans MH - Machine Learning MH - Menarche MH - Nutrition Surveys MH - *Phthalic Acids MH - Prospective Studies PMC - PMC8673778 MID - NIHMS1651291 OTO - NOTNLM OT - Environmental exposures OT - Machine learning OT - Menarche OT - Mixtures OT - Multiple exposures EDAT- 2020/11/30 06:00 MHDA- 2021/04/22 06:00 PMCR- 2022/04/01 CRDT- 2020/11/29 20:28 PHST- 2020/08/22 00:00 [received] PHST- 2020/11/19 00:00 [revised] PHST- 2020/11/20 00:00 [accepted] PHST- 2020/11/30 06:00 [pubmed] PHST- 2021/04/22 06:00 [medline] PHST- 2020/11/29 20:28 [entrez] PHST- 2022/04/01 00:00 [pmc-release] AID - S0013-9351(20)31421-3 [pii] AID - 10.1016/j.envres.2020.110524 [doi] PST - ppublish SO - Environ Res. 2021 Apr;195:110524. doi: 10.1016/j.envres.2020.110524. Epub 2020 Nov 26.