Predicting emerging chemical content in consumer products using machine learning.

Accepted

Journal Article (Journal Article)

Chemical ingredients in consumer products are continually changing. To understand our exposure to chemicals and their consequent risk, we need to know their concentrations in products, or chemical weight fractions. Unfortunately, manufacturers rarely report comprehensive weight fraction data on product labels. The goal of this study was to evaluate the utility of machine learning strategies for predicting weight fractions when chemical constituent data are limited. A "data-poor" framework was developed and tested using a small dataset on consumer products containing engineered nanomaterials to represent emerging substances. A second, more traditional framework was applied to a "data-rich" product dataset comprised of bulk-scale organic chemicals for comparison purposes. Feature variables included chemical properties, functional use categories (e.g., antimicrobial), product categories (e.g., makeup), product matrix categories, and whether weight fractions were manufacturer-reported or experimentally obtained. Classification into three weight fraction bins was done using a random forest or nonlinear support vector classifier. An ablation study revealed that functional use data improved predictive performance when included alongside chemical property data, suggesting the utility of functional use categories in evaluating the safety and sustainability of emerging chemicals. Models could roughly stratify material-product observations into order of magnitude weight fractions with moderate success; the best of these achieved an average balanced accuracy of 73% on the nanomaterials product data. Framework comparisons also revealed a positive trend in sample size versus average balanced accuracy, suggesting great promise for machine learning approaches with continued investment in chemical data collection.

Full Text

Duke Authors

Cited Authors

  • Thornton, LL; Carlson, DE; Wiesner, MR

Published Date

  • August 2022

Published In

Volume / Issue

  • 834 /

Start / End Page

  • 154849 -

PubMed ID

  • 35405240

Electronic International Standard Serial Number (EISSN)

  • 1879-1026

International Standard Serial Number (ISSN)

  • 0048-9697

Digital Object Identifier (DOI)

  • 10.1016/j.scitotenv.2022.154849

Language

  • eng