The impact of multipollutant exposure on hepatic steatosis - a machine learning-based investigation into multipollutant synergistic effects

Q: What does the study evaluate regarding hepatic steatosis in NAFLD?

It assesses the synergistic effects of multi-pollutant exposure on hepatic lipid accumulation in NAFLD using an explainable machine learning framework.

Q: Which data and modeling approach are used to analyze pollutant biomarkers?

It uses NHANES 2015–2016 urinary biomarker data (n = 494) and builds a stacked ensemble integrating LASSO, SVM, neural networks, and XGBoost.

Q: Which pollutant and exposure metric are identified as most important?

2-Hydroxynaphthalene is highlighted as the predominant pollutant, and EPEI is presented as a quantifiable metric of cumulative exposure effects.

Aug 5, 2026

Upload by Rowan

This original research investigates how synergistic multi-pollutant exposure contributes to hepatic steatosis in non-alcoholic fatty liver disease (NAFLD). An explainable machine learning framework is applied to NHANES 2015–2016 data (n = 494) by integrating urinary biomarkers of heavy metals, PAHs, and VOCs. A stacked ensemble and cumulative exposure metric (EPEI), interpreted with SHAP values, quantify critical pollutants and thresholds. Results identify 2-Hydroxynaphthalene as a key hepatotoxicant and show amplified risks in severe obesity and impaired fasting glucose.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Introduction

Methods

Results

Discussion

TYPE Original Research PUBLISHED 22 May 2025 DOI 10.3389/fpubh.2025.1598639 OPEN ACCESS EDITED BY Tong Wang, Duke University, United States REVIEWED BY Xue Wu, University of California, San Francisco, United States Xiaoyi Zhang, Jacobi Medical Center, United States Fangran Liu, The University of Hong Kong, Hong Kong SAR, China Ran Tong, The University of Texas at Dallas, United States Zixu Wang, Bicycle Therapeutics, United Kingdom *CORRESPONDENCE Shujuan Gao [1149905009@qq.com](1149905009@qq.com) RECEIVED 23 March 2025 ACCEPTED 07 May 2025 PUBLISHED 22 May 2025 CITATION Yan C, Zhu Z, Guo X, Zong W, Liu G, Jin Y, Cui S, Liu F and Gao S (2025) The impact of multipollutant exposure on hepatic steatosis: a machine learning-based investigation into multipollutant synergistic effects. Front. Public Health 13:1598639. doi: 10.3389/fpubh.2025.1598639 COPYRIGHT © 2025 Yan, Zhu, Guo, Zong, Liu, Jin, Cui, Liu and Gao. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. The impact of multipollutant exposure on hepatic steatosis: a machine learning-based investigation into multipollutant synergistic effects Chunying Yan 1, Zhanfang Zhu 2, Xueyan Guo 1, Wei Zong 1, Guisheng Liu 1, Yan Jin 1, Shiyuan Cui 1, Fuqiang Liu3 and Shujuan Gao 1* 1 Department of Gastroenterology, Shaanxi Provincial People's Hospital, Xi’an, China, 2Xi'an Jiaotong University Hospital, Xi’an, China, 3 Department of Cardiology, Shaanxi Provincial People's Hospital, Xi’an, China Introduction: This study examines the synergistic effects of multi-pollutant exposure on hepatic lipid accumulation in non-alcoholic fatty liver disease (NAFLD) through the application of an explainable machine learning framework. This approach addresses the limitations of traditional models in managing complex environmental interactions. Methods: Using data from the National Health and Nutrition Examination Survey (NHANES) 2015–2016 (n = 494), we developed a stacked ensemble model that integrates LASSO, support vector machines (SVM), neural networks, and XGBoost to analyze urinary biomarkers of heavy metals, polycyclic aromatic hydrocarbons (PAHs), and volatile organic compounds (VOCs) . The Environmental Pollution Exposure Index (EPEI) was constructed to quantify cumulative effects, with SHAP values employed to identify critical pollutants and thresholds. Subgroup analyses were conducted to assess heterogeneity across different Body Mass Index (BMI), diabetes, and hyperlipidemia statuses. Results: 2-Hydroxynaphthalene was identified as the predominant pollutant (SHAP = 0. 89), with cobalt and VOC metabolites (e. g., N-AcetylS-(2-carbamoylethyl)-L-cysteine) also contributing significantly. The EPEI demonstrated strong associations with obesity-related parameters (PLF: 7.02 vs. 3.41 in high/low-exposure groups, p < 0.0001) and hyperlipidemia (OR = 2.28 vs. 1.08, p = 2.7e-06) . The model demonstrated an amplification of effects in subgroups with severe obesity (OR = 2.66, 95% CI: 2.08–3. 24) and impaired fasting glucose. Discussion: This study establishes a machine learning framework for assessing multi-pollutant risks in NAFLD, identifying 2-Hydroxynaphthalene as a significant hepatotoxicant and EPEI as a quantifiable metric of exposure. The findings highlight the metabolic vulnerabilities associated with obesity and early dysglycemia, thereby informing precision prevention strategies. Methodological advancements integrate exposomics with interpretable artificial intelligence, facilitating targeted interventions in environmental health.

FAQs

What does the study evaluate regarding hepatic steatosis in NAFLD?

It assesses the synergistic effects of multi-pollutant exposure on hepatic lipid accumulation in NAFLD using an explainable machine learning framework.

Which data and modeling approach are used to analyze pollutant biomarkers?

It uses NHANES 2015–2016 urinary biomarker data (n = 494) and builds a stacked ensemble integrating LASSO, SVM, neural networks, and XGBoost.

Which pollutant and exposure metric are identified as most important?

2-Hydroxynaphthalene is highlighted as the predominant pollutant, and EPEI is presented as a quantifiable metric of cumulative exposure effects.

Aug 5, 2026

Upload by Rowan