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

IntroductionThis 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 managi...

Full description

Saved in:
Bibliographic Details
Main Authors: Chunying Yan, Zhanfang Zhu, Xueyan Guo, Wei Zong, Guisheng Liu, Yan Jin, Shiyuan Cui, Fuqiang Liu, Shujuan Gao
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-05-01
Series:Frontiers in Public Health
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpubh.2025.1598639/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850260614698500096
author Chunying Yan
Zhanfang Zhu
Xueyan Guo
Wei Zong
Guisheng Liu
Yan Jin
Shiyuan Cui
Fuqiang Liu
Shujuan Gao
author_facet Chunying Yan
Zhanfang Zhu
Xueyan Guo
Wei Zong
Guisheng Liu
Yan Jin
Shiyuan Cui
Fuqiang Liu
Shujuan Gao
author_sort Chunying Yan
collection DOAJ
description IntroductionThis 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.MethodsUsing 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.Results2-Hydroxynaphthalene was identified as the predominant pollutant (SHAP = 0.89), with cobalt and VOC metabolites (e.g., N-Acetyl-S-(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.DiscussionThis 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.
format Article
id doaj-art-2e1c606256bf4203a01123378ae89cd6
institution OA Journals
issn 2296-2565
language English
publishDate 2025-05-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Public Health
spelling doaj-art-2e1c606256bf4203a01123378ae89cd62025-08-20T01:55:37ZengFrontiers Media S.A.Frontiers in Public Health2296-25652025-05-011310.3389/fpubh.2025.15986391598639The impact of multipollutant exposure on hepatic steatosis: a machine learning-based investigation into multipollutant synergistic effectsChunying Yan0Zhanfang Zhu1Xueyan Guo2Wei Zong3Guisheng Liu4Yan Jin5Shiyuan Cui6Fuqiang Liu7Shujuan Gao8Department of Gastroenterology, Shaanxi Provincial People's Hospital, Xi’an, ChinaXi'an Jiaotong University Hospital, Xi’an, ChinaDepartment of Gastroenterology, Shaanxi Provincial People's Hospital, Xi’an, ChinaDepartment of Gastroenterology, Shaanxi Provincial People's Hospital, Xi’an, ChinaDepartment of Gastroenterology, Shaanxi Provincial People's Hospital, Xi’an, ChinaDepartment of Gastroenterology, Shaanxi Provincial People's Hospital, Xi’an, ChinaDepartment of Gastroenterology, Shaanxi Provincial People's Hospital, Xi’an, ChinaDepartment of Cardiology, Shaanxi Provincial People's Hospital, Xi’an, ChinaDepartment of Gastroenterology, Shaanxi Provincial People's Hospital, Xi’an, ChinaIntroductionThis 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.MethodsUsing 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.Results2-Hydroxynaphthalene was identified as the predominant pollutant (SHAP = 0.89), with cobalt and VOC metabolites (e.g., N-Acetyl-S-(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.DiscussionThis 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.https://www.frontiersin.org/articles/10.3389/fpubh.2025.1598639/fullmachine learningpercentage of liver fat (PLF)heavy metalspolycyclic aromatic hydrocarbons (PAHs)volatile organic compounds (VOCs)
spellingShingle Chunying Yan
Zhanfang Zhu
Xueyan Guo
Wei Zong
Guisheng Liu
Yan Jin
Shiyuan Cui
Fuqiang Liu
Shujuan Gao
The impact of multipollutant exposure on hepatic steatosis: a machine learning-based investigation into multipollutant synergistic effects
Frontiers in Public Health
machine learning
percentage of liver fat (PLF)
heavy metals
polycyclic aromatic hydrocarbons (PAHs)
volatile organic compounds (VOCs)
title The impact of multipollutant exposure on hepatic steatosis: a machine learning-based investigation into multipollutant synergistic effects
title_full The impact of multipollutant exposure on hepatic steatosis: a machine learning-based investigation into multipollutant synergistic effects
title_fullStr The impact of multipollutant exposure on hepatic steatosis: a machine learning-based investigation into multipollutant synergistic effects
title_full_unstemmed The impact of multipollutant exposure on hepatic steatosis: a machine learning-based investigation into multipollutant synergistic effects
title_short The impact of multipollutant exposure on hepatic steatosis: a machine learning-based investigation into multipollutant synergistic effects
title_sort impact of multipollutant exposure on hepatic steatosis a machine learning based investigation into multipollutant synergistic effects
topic machine learning
percentage of liver fat (PLF)
heavy metals
polycyclic aromatic hydrocarbons (PAHs)
volatile organic compounds (VOCs)
url https://www.frontiersin.org/articles/10.3389/fpubh.2025.1598639/full
work_keys_str_mv AT chunyingyan theimpactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects
AT zhanfangzhu theimpactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects
AT xueyanguo theimpactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects
AT weizong theimpactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects
AT guishengliu theimpactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects
AT yanjin theimpactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects
AT shiyuancui theimpactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects
AT fuqiangliu theimpactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects
AT shujuangao theimpactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects
AT chunyingyan impactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects
AT zhanfangzhu impactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects
AT xueyanguo impactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects
AT weizong impactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects
AT guishengliu impactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects
AT yanjin impactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects
AT shiyuancui impactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects
AT fuqiangliu impactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects
AT shujuangao impactofmultipollutantexposureonhepaticsteatosisamachinelearningbasedinvestigationintomultipollutantsynergisticeffects