Identifying key risk factors of polycyclic aromatic hydrocarbons and benzene exposure in Korean adult males using machine learning approaches - Abstract

Aug 5, 2026

Upload by Sage

Background: This study explores key risk factors associated with polycyclic aromatic hydrocarbons (PAHs) and benzene exposure in Korean adult males (n = 2744) using data from the Korean National Environmental Health Survey (2015–2017). Methods: Isolation Forest was used to identify variables influencing urinary biomarkers (1-Hydroxypyrene, 2-Hydroxynaphthalene, trans-Muconic acid). Results: Age, smoking, alcohol consumption, proximity to roads, and grilled food consumption were significant, with smoking the strongest predictor. Model performance exceeded CHAID, KNN, and Random Forest (accuracy 92%, recall 89%, precision 90%, F1 89.5%, AUC 0.93). Conclusions: Findings support machine learning for exposure assessment and suggest smoking-focused policy interventions, with longitudinal work recommended.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Abstract

Introduction

Health relevance of PAHs and benzene

Male-focused exposure risks

Korean environmental health monitoring context

O R I G I NA L R E S EA R C H Identifying key risk factors of polycyclic aromatic hydrocarbons and benzene exposure in Korean adult males using machine learning approaches Haewon Byeon 1 , * 1Worker’s Care & Digital Health Lab, Department of Future Technology, Korea University of Technology and Education, 31253 Cheonan, Republic of Korea *Correspondence [bhwpuma@naver.com](bhwpuma@naver.com) (Haewon Byeon) Abstract Background: This study aims to explore the various risk factors associated with exposure to polycyclic aromatic hydrocarbons (PAHs) and benzene in Korean adult males (n = 2744), using data from the Korean National Environmental Health Survey (KoNEHS) conducted from 2015 to 2017 . Methods: Isolation Forest, a machine learning algorithm specialized in anomaly detection, was employed to identify key variables influencing urinary biomarkers such as 1-Hydroxypyrene, 2-Hydroxynaphthalene and trans-Muconic acid. Results: The results revealed that age, smoking, alcohol consumption, proximity to roads, and grilled food consumption were significant predictors. Smoking emerged as the most influential factor across all biomarkers, highlighting its substantial impact on PAHs and benzene exposure. Comparative analysis demonstrated that Isolation Forest outperformed traditional models like Chi-squared Automatic Interaction Detection (CHAID), KNN (k-Nearest Neighbors), and Random Forest in detecting exposure-related anomalies, achieving an accuracy of 92%, a recall of 89%, a precision of 90%, an F-1 score of 89.5%, and an Area Under the Curve (AUC) of 0.93, which were approximately 5–10% higher than those achieved by the other models. Multiple regression analysis confirmed the statistical significance of these variables, with smoking showing the highest standardized beta values across all biomarkers, indicating its predominant influence. Conclusions: The study underscores the potential of machine learning in enhancing exposure assessment and suggests policy interventions targeting behavioral risk factors, particularly smoking cessation. Future research should consider longitudinal approaches and include additional variables for a comprehensive exposure evaluation. Keywords PAHs; Benzene; Isolation Forest; Risk factors; Environmental health 1. Introduction Globally, research on exposure to Polycyclic Aromatic Hydrocarbons (PAHs) and benzene has been actively conducted as their impact on environmental pollution and human health has gained prominence [1] . PAHs are harmful chemicals primarily released into the environment through various pathways such as industrial activities, vehicle emissions and smoking [2] . These substances can expose humans through different media, including air, soil and water [3] . Benzene is mainly emitted during industrial production processes and is commonly found in everyday environments such as gasoline, tobacco smoke and vehicle exhaust [3, 4] . These substances pose various health risks, including carcinogenicity, prompting ongoing regulation and research on their exposure levels and health impacts internationally [5] . Particularly, PAHs are classified as carcinogens [6], and benzene has also been shown to have harmful effects on human health according to multiple studies [5–7] . The level of exposure to these substances can vary based on the concentration present in the air as well as individuals’daily habits and dietary patterns [8, 9] . Consequently, they are a key focus in environmental policies and health protection strategies across countries [9] . The risk of exposure to PAHs and benzene is gaining particular attention concerning men’s health. Several studies [10, 11] have indicated that men may be exposed to higher levels of PAHs and benzene than women due to factors related to occupational exposure, smoking and drinking habits. Such exposure can potentially have negative effects on reproductive health, leading to issues like reduced sperm quality, reproductive dys

FAQs

Which risk factors were identified as significant predictors for PAHs and benzene exposure?

Age, smoking, alcohol consumption, proximity to roads, and grilled food consumption were significant predictors. Smoking showed the strongest influence across all biomarkers.

What machine learning method was used in the study, and what was its purpose?

Isolation Forest was used for anomaly detection to identify key variables influencing urinary biomarkers related to PAHs and benzene exposure.

How did Isolation Forest perform compared with traditional models?

Isolation Forest achieved higher performance than CHAID, KNN, and Random Forest, with accuracy 92%, recall 89%, precision 90%, F1 89.5%, and AUC 0.93.

Aug 5, 2026

Upload by Sage