Machine Learning Assisted Discovery of Interactions between Pesticides, Phthalates, Phenols, and Trace Elements in Child Neurodevelopment

Aug 4, 2026

A growing body of literature links developmental exposure to individual or mixed environmental chemicals with autism spectrum disorder (ASD), yet analyzing chemical interactions remains difficult. This study combines Weighted Quantile Sum (WQS) regression with a machine-learning approach, Signed iterative Random Forest (SiRF), to identify synergistic interactions among environmental chemicals. In the CHARGE case-control study, WQS-SiRF detects two-order synergistic interactions involving cadmium and DEP, and 2,4,6-trichlorophenol and DEP, associated with higher ASD odds in a high-concentration subset. The work demonstrates a unified inferential-predictive framework for potentially biologically relevant chemical-chemical interactions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Abstract

Introduction

UC Davis UC Davis Previously Published Works Title Machine Learning Assisted Discovery of Interactions between Pesticides, Phthalates, Phenols, and Trace Elements in Child Neurodevelopment. Permalink [https://escholarship.org/uc/item/3565n6rp](https://escholarship.org/uc/item/3565n6rp) Journal Environmental Science & Technology, 57(46) Authors Midya, Vishal Alcala, Cecilia Rechtman, Elza et al. Publication Date 2023-08-18 DOI 10.1021/acs.est.3c00848 Peer reviewed [eScholarship.org](eScholarship.org) Powered by the California Digital Library University of California This article is licensed under CC-BY-NC-ND 4.0 [pubs.acs.org/est](pubs.acs.org/est) Article Machine Learning Assisted Discovery of Interactions between Pesticides, Phthalates, Phenols, and Trace Elements in Child Neurodevelopment Vishal Midya, *,⊥ Cecilia Sara Alcala,⊥ Elza Rechtman, Jill K. Gregory, Kurunthachalam Kannan, Irva Hertz-Picciotto, Susan L. Teitelbaum, Chris Gennings, Maria J. Rosa,¶ and Damaskini Valvi¶ Cite This: Environ. Sci. Technol. 2023, 57, 18139−18150 Read Online | | | | | | | | --- | --- | --- | --- | --- | --- | | ACCESS | Metrics & More | | Article Recommendations | | *sı Supporting Information | ABSTRACT: A growing body of literature suggests that developmental exposure to individual or mixtures of environmental chemicals (ECs) is associated with autism spectrum disorder (ASD). However, investigating the effect of interactions among these ECs can be challenging. We introduced a combination of the classical exposure-mixture Weighted Quantile Sum (WQS) regression and a machine-learning method termed Signed iterative Random Forest (SiRF) to discover synergistic interactions between ECs that are (1) associated with higher odds of ASD diagnosis,(2) mimic toxicological interactions, and (3) are present only in a subset of the sample whose chemical concentrations are higher than certain thresholds. In a case-control Childhood Autism Risks from Genetics and Environment (CHARGE) study, we evaluated multiordered synergistic interactions among 62 ECs measured in the urine samples of 479 children in association with increased odds for ASD diagnosis (yes vs no). WQS-SiRF identified two synergistic two-ordered interactions between (1) traceelement cadmium (Cd) and the organophosphate pesticide metabolite diethyl-phosphate (DEP); and (2) 2,4,6-trichlorophenol (TCP-246) and DEP. Both interactions were suggestively associated with increased odds ofASD diagnosis in the subset of children with urinary concentrations of Cd, DEP, and TCP-246 above the 75th percentile. This study demonstrates a novel method that combines the inferential power of WQS and the predictive accuracy of machine-learning algorithms to discover potentially biologically relevant chemical−chemical interactions associated with ASD. KEYWORDS: autism spectrum disorder, environmental chemical exposures, iterative random forests, random intersection tree, exposure mixture model, synergistic interactions ■ INTRODUCTION Autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by deficits in social communication and interaction and repetitive and stereotyped interests and behaviors.1 ASD prevalence has increased drastically in recent years and is a public health concern worldwide. According to the Centers for Disease Control program Autism and Developmental Disabilities Monitoring (ADDM) Network, approximately 1 in 44 children have been diagnosed with ASD.2, 3 In the past decade, a growing number of epidemiological studies have associated early life environmental exposures with ASD.4 These environmental exposures include air pollution,5−9 nutrition, and several endocrinedisrupting chemicals (EDCs). Among other EDCs, studies on certain metals have been associated with ASD, 10, 11 with a compelling link between arsenic exposure and ASD in children.12 Other EDCs, such as bisphenol A (BPA), and parabens have also

FAQs

Why is discovering interactions between environmental chemicals and ASD challenging?

Studying interactions among environmental chemicals is difficult because many existing approaches mainly estimate association effects without offering mechanistic or biological insight into how chemicals interact.

What methods does the study combine to discover synergistic chemical interactions?

The study integrates Weighted Quantile Sum (WQS) regression with a machine-learning method called Signed iterative Random Forest (SiRF) to identify synergistic interactions.

Which chemical pairs were identified as synergistic interactions associated with ASD?

Two two-order synergistic interactions were reported: cadmium (Cd) with the organophosphate pesticide metabolite diethyl-phosphate (DEP), and 2,4,6-trichlorophenol (TCP-246) with DEP.

Aug 4, 2026

Upload by Emma Wilson