Machine learning–driven identification of early-life air toxic combinations associated with childhood asthma outcomes

Abstract

Air pollution is a well-known contributor to asthma. Air toxics are hazardous air pollutants that cause or may cause serious health effects. While individual air toxics have been associated with asthma, only a limited number of studies have specifically examined combinations of air toxics associated with the disease. We geocoded air toxic levels from the US National Air Toxics Assessment (NATA) to residential locations for participants of our AiRway in Asthma (ARIA) study. We then applied Data-driven ExposurE Profile extraction (DEEP), a novel machine learning-based method, to discover combinations of early-life air toxics associated with current use of daily asthma controller medication, lifetime emergency department visit for asthma, and lifetime overnight hospitalization for asthma. We discovered 20 multi-air toxic combinations and 18 single air toxics associated with at least one outcome. The multi-air toxic combinations included those containing acrylic acid, ethylidene dichloride, and hydroquinone, and they were significantly associated with asthma outcomes with odds ratios of 1.60 to 3.19. Several air toxic members of the combinations would not have been identified by single air toxic analyses, supporting the use of machine learning-based methods designed to detect combinatorial effects. Our findings provide knowledge about air toxic combinations associated with childhood asthma.

Allergies to food and airborne allergens in children and adolescents: role of epigenetics in a changing environment

“…Another study 84 assessed multi exposure models across the life course and interactions with epithelial barriers and the microbiome, which are exemplified by the exposome concept that can be explained as the measure of all exposures of an individual related to health and disease. Two more ongoing studies 85,86 are investigating artificial intelligence applications and computational science in allergy.…”

Screening for cytological changes associated with inhaled polluted materials in Khartoum industrial area

“…Furthermore, it was found that exposure to particulate matter, sulfur dioxide, and nitrogen oxides are a risk factor for developing lung cancer (Manisalidis et al, 2020). Moreover, exposure to benzene vapor from vehicles emission causes a wide range of health problems such as hematologic disorders and lung diseases (Li et al, 2021)…”

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

“…Moreover, a predictive ML model might not be the optimal model for inference . However, in recent epidemiological studies, interpretable tree-based ML tools were used to discover simultaneously co-occurring chemicals, similar to classical Weighted Quantile Sum (WQS) Regression models. − Separately in computational biology, using a novel ML algorithm called random intersection trees, Basu et al , introduced the “signed iterative random forest” (SiRF) algorithm to discover interactions through collective activities. SiRF can efficiently search for the few stable and highly occurring interactions instead of going through each possible interaction term.…”