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

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.

PAHs; Benzene; Isolation Forest; Risk factors; Environmental health

[1] Anyahara JN. Effects of polycyclic aromatic hydrocarbons (PAHs) on the environment: a systematic review. International Journal of Advanced Academic Research. 2021; 7: 12–26.

[2] Shen M, Liu G, Zhou L, Yin H, Arif M, Leung KMY. Spatial distribution, driving factors and health risks of fine particle-bound polycyclic aromatic hydrocarbons (PAHs) from indoors and outdoors in Hefei, China. Science of the Total Environment. 2022; 851: 158148.

[3] Shi R, Li X, Yang Y, Fan Y, Zhao Z. Contamination and human health risks of polycyclic aromatic hydrocarbons in surface soils from Tianjin coastal new region, China. Environmental Pollution. 2021; 268: 115938.

[4] Loomis D, Guyton KZ, Grosse Y, El Ghissassi F, Bouvard V, Benbrahim-Tallaa L, et al. Carcinogenicity of benzene. The Lancet Oncology. 2017; 18: 1574–1575.

[5] Das DN, Ravi N. Influences of polycyclic aromatic hydrocarbon on the epigenome toxicity and its applicability in human health risk assessment. Environmental Research. 2022; 213: 113677.

[6] Chang Y, Huynh CTT, Bastin KM, Rivera BN, Siddens LK, Tilton SC. Classifying polycyclic aromatic hydrocarbons by carcinogenic potency using in vitro biosignatures. Toxicology in Vitro. 2020; 69: 104991.

[7] Huang L, Cheng H, Ma S, He R, Gong J, Li G, et al. The exposures and health effects of benzene, toluene and naphthalene for Chinese chefs in multiple cooking styles of kitchens. Environment International. 2021; 156: 106721.

[8] Polachova A, Gramblicka T, Parizek O, Sram RJ, Stupak M, Hajslova J, et al. Estimation of human exposure to polycyclic aromatic hydrocarbons (PAHs) based on the dietary and outdoor atmospheric monitoring in the Czech Republic. Environmental Research. 2020; 182: 108977.

[9] Sekar A, Varghese GK, Ravi Varma MK. Analysis of benzene air quality standards, monitoring methods and concentrations in indoor and outdoor environment. Heliyon. 2019; 5: e02918.

[10] DeMoulin D, Cai H, Vermeulen R, Zheng W, Lipworth L, Shu X. Occupational benzene exposure and cancer risk among Chinese men: a report from the Shanghai men’s health study. Cancer Epidemiology, Biomarkers & Prevention. 2024; 33: 1465–1474.

[11] Barul C, Parent ME. Occupational exposure to polycyclic aromatic hydrocarbons and risk of prostate cancer. Environmental Health. 2021; 20: 71.

[12] Peña-García MV, Moyano-Gallego MJ, Gómez-Melero S, Molero-Payán R, Rodríguez-Cantalejo F, Caballero-Villarraso J. One-year impact of occupational exposure to polycyclic aromatic hydrocarbons on sperm quality. Antioxidants. 2024; 13: 1181.

[13] Olsson AC, Fevotte J, Fletcher T, Cassidy A, Mannetje AT, Zaridze D, et al. Occupational exposure to polycyclic aromatic hydrocarbons and lung cancer risk: a multicenter study in Europe. Occupational and Environmental Medicine. 2010; 67: 98–103.

[14] Zhang L, Sun P, Sun D, Zhou Y, Han L, Zhang H, et al. Occupational health risk assessment of the benzene exposure industries: a comprehensive scoring method through 4 health risk assessment models. Environmental Science and Pollution Research. 2022; 29: 84300–84311.

[15] Kim KY, Oh SE, Hong MK, Lee KS. Hazard and risk assessment and cost and benefit analysis for revising permissible exposure limits in the occupational safety and health act of Korea. Journal of Korean Society of Occupational and Environmental Hygiene. 2015; 25: 134–145.

[16] Jung SK, Choi W, Kim SY, Hong S, Jeon HL, Joo Y, et al. Profile of environmental chemicals in the Korean population—results of the Korean national environmental health survey (KoNEHS) cycle 3, 2015–2017. International Journal of Environmental Research and Public Health. 2022; 19: 626.

[17] Park C, Hwang M, Kim H, Ryu S, Lee K, Choi K, et al. Early snapshot on exposure to environmental chemicals among Korean adults—results of the first Korean National Environmental Health Survey (2009–2011). International Journal of Hygiene and Environmental Health. 2016; 219: 398–404.

[18] Choi YH, Lee JY, Moon KW. Exposure to volatile organic compounds and polycyclic aromatic hydrocarbons is associated with the risk of non-alcoholic fatty liver disease in Korean adolescents: Korea National Environmental Health Survey (KoNEHS) 2015–2017. Ecotoxicology and Environmental Safety. 2023; 251: 114508.

[19] Park C, Yu SD. Status and prospects of the Korean National Environmental Health Survey (KoNEHS). Journal of Environmental Health Sciences. 2014; 40: 1–9.

[20] Kim MJ. Air pollution, health, and avoidance behavior: evidence from South Korea. Environmental and Resource Economics. 2021; 79: 63–91.

[21] Bosker T, Mudge JF, Munkittrick KR. Statistical reporting deficiencies in environmental toxicology. Environmental Toxicology and Chemistry. 2013; 32: 1737–1739.

[22] Johnstone IM, Titterington DM. Statistical challenges of high-dimensional data. Philosophical Transactions of the Royal Society A. 2009; 367: 4237–4253.

[23] Kraemer HC, Stice E, Kazdin A, Offord D, Kupfer D. How do risk factors work together? Mediators, moderators, and independent, overlapping, and proxy risk factors. American Journal of Psychiatry. 2001; 158: 848–856.

[24] Zennaro F, Furlan E, Simeoni C, Torresan S, Aslan S, Critto A, et al. Exploring machine learning potential for climate change risk assessment. Earth-Science Reviews. 2021; 220: 103752.

[25] Byeon H. Determinants of blood pressure control in hypertensive individuals using histogram-based gradient boosting: findings from 1114 male workers in South Korea. Journal of Men’s Health. 2024; 20: 47–55.

[26] Fang M, Shin M, Park K, Kim YS, Lee JW, Cho M. Analysis of urinary S-phenylmercapturic acid and trans, trans-muconic acid as exposure biomarkers of benzene in petrochemical and industrial areas of Korea. Scandinavian Journal of Work, Environment & Health. 2000; 26: 62–66.

[27] Capleton AC, Levy LS. An overview of occupational benzene exposures and occupational exposure limits in Europe and North America. Chemico-Biological Interactions. 2005; 153: 43–53.

[28] Gearhart-Serna LM, Tacam M III, Slotkin TA, Devi GR. Analysis of polycyclic aromatic hydrocarbon intake in the US adult population from NHANES 2005–2014 identifies vulnerable subpopulations, suggests interaction between tobacco smoke exposure and sociodemographic factors. Environmental Research. 2021; 201: 111614.

[29] Arnold SM, Angerer J, Boogaard PJ, Hughes MF, O’Lone RB, Robison SH, et al. The use of biomonitoring data in exposure and human health risk assessment: benzene case study. Critical Reviews in Toxicology. 2013; 43: 119–153.

[30] De Coster S, Van Leeuwen DM, Jennen DG, Koppen G, Den Hond E, Nelen V, et al. Gender‐specific transcriptomic response to environmental exposure in Flemish adults. Environmental and Molecular Mutagenesis. 2013; 54: 574–588.

[31] Ephraim-Emmanuel BC, Ordinioha B. Exposure and public health effects of polycyclic aromatic hydrocarbon compounds in sub-Saharan Africa: a systematic review. International Journal of Toxicology. 2021; 40: 250–269.

[32] Kao TH, Chen S, Huang CW, Chen CJ, Chen BH. Occurrence and exposure to polycyclic aromatic hydrocarbons in kindling-free-charcoal grilled meat products in Taiwan. Food and Chemical Toxicology. 2014; 71: 149–158.

[33] Xu X, Liu X, Zhang J, Liang L, Wen C, Li Y, et al. Formation, migration, derivation, and generation mechanism of polycyclic aromatic hydrocarbons during frying. Food Chemistry. 2023; 425: 136485.

[34] Ledesma E, Rendueles M, Díaz MJ. Contamination of meat products during smoking by polycyclic aromatic hydrocarbons: processes and prevention. Food Control. 2016; 60: 64–87.

[35] Kumosani TA, Moselhy SS, Asseri AM, Asseri AH. Detection of polycyclic aromatic hydrocarbons in different types of processed foods. Toxicology and Industrial Health. 2013; 29: 300–304.

[36] Singh L, Agarwal T. Polycyclic aromatic hydrocarbons in diet: concern for public health. Trends in Food Science & Technology. 2018; 79: 160–170.

[37] Whaley CH, Galarneau E, Makar PA, Moran MD, Zhang J. How much does traffic contribute to benzene and polycyclic aromatic hydrocarbon air pollution? Results from a high-resolution North American air quality model centred on Toronto, Canada. Atmospheric Chemistry and Physics. 2020; 20: 2911–2925.

[38] Ali MU, Siyi L, Yousaf B, Abbas Q, Hameed R, Zheng C, et al. Emission sources and full spectrum of health impacts of black carbon associated polycyclic aromatic hydrocarbons (PAHs) in urban environment: a review. Critical Reviews in Environmental Science and Technology. 2021; 51: 857–896.

[39] Vardoulakis S, Giagloglou E, Steinle S, Davis A, Sleeuwenhoek A, Galea KS, et al. Indoor exposure to selected air pollutants in the home environment: a systematic review. International Journal of Environmental Research and Public Health. 2020; 17: 8972.

[40] Chen KC, Tsai SW, Shie RH, Zeng C, Yang HY. Indoor air pollution increases the risk of lung cancer. International Journal of Environmental Research and Public Health. 2022; 19: 1164.

[41] Yassin MF, Alhajeri NS, Kassem MA. Polycyclic aromatic hydrocarbons collected from indoor built environments on heating, ventilation and air conditioning dust filters. Indoor and Built Environment. 2016; 25: 137–150.