Machine Learning Technology Identifies 2 Synergistic Interactions Between Environmental Chemicals and ASD

September 04, 2023

Trace-Element Cadmium and DEP, along with TCP-246 and DEP, Showed Increased Odds of Developing Autism in a Subset of Children

A team of researchers from the Icahn School of Medicine and the MIND Institute have recently conducted a case-control study using data from the Childhood Autism Risks from Genetics and Environment (CHARGE) study. Their work evaluated multiordered synergistic interactions among 62 environmental chemicals (pesticides, phthalates, phenols, and trace elements), which were measured in urine samples of 479 children. These samples were analyzed using Weighted Quantile Sum (WQS) regression and a machine learning method named Signed iterative Random Forest (SiRF). These techniques were specifically used to discover if there was an increased risk of an autism diagnosis in certain chemical interactions. Interestingly, WQS-SiRF identified two synergistic two-ordered interactions between (1) trace-element cadmium (Cd) and the organophosphate pesticide metabolite diethyl-phosphate (DEP); and (2) 2,4,6-trichlorophenol (TCP-246) and DEP.  Both interactions showed an association between Cd, DEP, and TCP-246 urinary concentrations and increased odds of an autism diagnosis in a subset of children. The team behind this research believes their study demonstrates a new method that combines the inferential power of WQS and the predictive accuracy of machine-learning algorithms to discover other potentially biologically relevant chemical-chemical interactions associated with autism spectrum disorder. 

Original Study

Show Buttons
Hide Buttons