Prediction of Occupational Health Risk Using the Random Forest Machine Learning Model in a Metal Casting Workplace: A Case Study at CV. Karya Yudita Baroqah

Nadilah Sary; Nismah Panjaitan; Abdul Rahim Matondang; Ukurta Tarigan

doi:10.32734/jsti.v28i2.23815

Authors

Nadilah Sary Universitas Sumatera Utara
Nismah Panjaitan USU
Abdul Rahim Matondang Universitas Sumatera Utara
Ukurta Tarigan Universitas Sumatera Utara

DOI:

https://doi.org/10.32734/jsti.v28i2.23815

Keywords:

Occupational Health Risk, Random Forest, Machine Learning, Noise Exposure, Particulate Matter

Abstract

Occupational health risks from chronic exposure to noise and airborne particulate matter remain a major concern in metal casting workplaces, especially in small-scale foundries with limited controls. The parameters measured in this study include noise exposure (Leq, dBA), particulate matter concentrations (PM₂.₅ and PM₁₀), and workers’ health symptoms. Field measurements at CV. Karya Yudita Baroqah showed exceedances of regulatory limits: noise levels in Molding and Finishing reached 89–93 dBA, and PM₂.₅ and PM₁₀ concentrations reached 72–80 µg/m³ and 155–174 µg/m³, surpassing recommended thresholds. These conditions indicate that workers are consistently exposed to hazardous environments that may lead to cumulative health impairments. This study aims to predict occupational health risk using a two-stage Random Forest model integrating environmental exposure data and workers’ symptoms. Stage-1 classified environmental risk levels with 99% accuracy, while Stage-2 predicted symptom-based health risk categories with 71% accuracy. PM₁₀ and PM₂.₅ were the strongest predictors, followed by noise intensity. The model demonstrates reliable performance and captures individual variability that traditional threshold-based assessments often overlook. The findings highlight that a combined machine-learning and HRA approach provides a practical, data-driven tool for early detection of high-risk workers and supports targeted interventions in metal casting workplaces.

Downloads

Download data is not yet available.

References

[1] G. S. Hadi, L. A. Sadat, F. A. Metekohy, S. Fatimah, and E. L. Rauf, “The Role of Occupational Health and Safety Regulations in Preventing Work-related Injuries and Diseases: A Global Perspective,” The Journal of Academic Science, vol. 2 No 1, 2025.

[2] D. Duan, P. Leng, X. Li, G. Mao, A. Wang, and D. Zhang, “Characteristics and occupational risk assessment of occupational silica-dust and noise exposure in ferrous metal foundries in Ningbo, China,” Feb. 2023.

[3] M. Z. Zaman, A. Syafiuddin, A. H. Z. Fasya, and A. A. Adriansyah, “Literature Review: Jenis Penyakit Akibat Kerja, Penyebabnya Dan Mekanisme Penyebaran Dalam Industri,” Jurnal Kesehatan MAsyarakat (e-Journal), vol. 10 No 4, no. 57, pp. 511–517, Jul. 2022

[4] X. Chen, F. Yang, S. Cheng, and S. Yuan, “Occupational Health and Safety in China: A Systematic Analysis of Research Trends and Future Perspectives,” Oct. 01, 2023, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/su151914061.

[5] C. Bartolina et al., “Summary of the 2016 World Health Organization Report and 2021 Compendium on environmental diseases,” Working Paper of Public Health, vol. 11, 2023.

[6] E. Tompa et al., “A systematic literature review of the effectiveness of occupational health and safety regulatory enforcement,” Nov. 01, 2016, Wiley-Liss Inc. doi: 10.1002/ajim.22605.

[7] M. Sahri, S. Y. Arini, F. Jannah, and M. Amin, “Occupational Exposure Assessment of Fine Particulate Matter (PM2.5) and Respirable Crystalline Silica in the Ceramic Industry of Indonesia,” Atmosphere (Basel), vol. 16, no. 10, p. 1125, Sep. 2025, doi: 10.3390/atmos16101125.

[8] E. C. Nyanza, S. O. Jackson, L. Magoha, P. Chilipweli, J. Joshua, and M. T. Madullu, “Perceived occupational health risks, noise and dust exposure levels among street sweepers in Mwanza City in Northern Tanzania,” PLOS Global Public Health, vol. 4, no. 2, Feb. 2024, doi: 10.1371/journal.pgph.0002951.

[9] I. E. Agbehadji and I. C. Obagbuwa, “Explainable Artificial Intelligence and Machine Learning for Air Pollution Risk Assessment and Respiratory Health Outcomes: A Systematic Review,” Atmosphere (Basel), vol. 16, no. 10, p. 1154, Oct. 2025, doi: 10.3390/atmos16101154.

[10] B. S. Fakinle, D. O. Oke, J. A. Sonibare, A. J. Adewale, A. O. Adetoyese, and O. O. Fasuuhan, “Assessment of Factory Workers Exposure to Particulate Matter Fractions using Exceedance Factor and Pollution Standard Index,” in 2024 International Conference on Science, Engineering and Business for Driving Sustainable Development Goals (SEB4SDG), IEEE, Apr. 2024, pp. 1–7. doi: 10.1109/SEB4SDG60871.2024.10630255.

[11] K. Stødle, R. Flage, S. D. Guikema, and T. Aven, “Data-driven predictive modeling in risk assessment: Challenges and directions for proper uncertainty representation,” Risk Analysis, vol. 43, no. 12, pp. 2644–2658, Dec. 2023, doi: 10.1111/risa.14128.

[12] D. Nadler, “Machine Learning in Occupational Health and Safety: A Review of Knowledge Gaps,” Nov. 06, 2024. doi: 10.20944/preprints202411.0464.v1.

[13] P. Manini, G. De Palma, and A. Mutti, “Exposure assessment at the workplace: Implications of biological variability,” Toxicol Lett, vol. 168, no. 3, pp. 210–218, Feb. 2007, doi: 10.1016/j.toxlet.2006.09.014.

[14] K. L. Holt, “Predictive Modeling of Occupational Exposure Using Machine Learning and Environmental Sensor Data,” Journal of Exceptional Multidisciplinary Research, vol. 2, no. 1, pp. 82–89, May 2025, doi: 10.69739/jemr.v2i1.617.

[15] N. Elsayed, S. Abd Elaleem, and M. Marie, “Improving Prediction Accuracy using Random Forest Algorithm,” Jan. 2024. [Online]. Available: www.ijacsa.thesai.org

[16] S. Lee, L. Liu, R. Radwin, and J. Li, “Machine Learning in Manufacturing Ergonomics: Recent Advances, Challenges, and Opportunities,” IEEE Robot Autom Lett, vol. 6, no. 3, pp. 5745–5752, Jul. 2021, doi: 10.1109/LRA.2021.3084881.

[17] W. Susihono and I. P. Gede Adiatmika, “Assessment of inhaled dust by workers and suspended dust for pollution control change and ergonomic intervention in metal casting industry: A cross-sectional study,” Heliyon, vol. 6, no. 5, May 2020, doi: 10.1016/j.heliyon.2020.e04067.

[18] Q. Huang et al., “Occupational health risk assessment of workplace solvents and noise in the electronics industry using three comprehensive risk assessment models,” Mar. 2023.

[19] C. Mitrakas, A. Xanthopoulos, and D. Koulouriotis, “Techniques and Models for Addressing Occupational Risk Using Fuzzy Logic, Neural Networks, Machine Learning, and Genetic Algorithms: A Review and Meta-Analysis,” Feb. 01, 2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/app15041909.

[20] Sugiyono, Metode Penelitian Kuantitatif, Kualitatif, dan R & D, 2nd edition. Penerbit Alfabeta, 2019.

[21] S. B. Budi, “A Study on Assessment of Noise Exposure in the Port Industry: Implications for Occupational Health and Safety,” Galore International Journal of Health Sciences and Research, vol. 9, no. 1, pp. 19–25, Feb. 2024, doi: 10.52403/gijhsr.20240103.

[22] A. K. Guha and S. Gokhale, “Urban workers’ cardiovascular health due to exposure to traffic-originated PM2.5 and noise pollution in different microenvironments,” Science of The Total Environment, vol. 859, p. 160268, Feb. 2023, doi: 10.1016/j.scitotenv.2022.160268.

[23] M. Sadat-Mohammadi, S. Shakerian, Y. Liu, S. Asadi, and H. Jebelli, “Non-invasive physical demand assessment using wearable respiration sensor and random forest classifier,” Journal of Building Engineering, vol. 44, p. 103279, Dec. 2021, doi: 10.1016/j.jobe.2021.103279.

[24] F. Majidi, Y. Khosravi, and kamalad-D. Abedi, “Determination of the Equivalent Continuous Sound Level (Leq) in Industrial Indoor Space Using GIS-based Noise Mapping,” Journal of Human, Environment, and Health Promotion, vol. 5, no. 2, pp. 50–55, Jun. 2019, doi: 10.29252/jhehp.5.2.1.

[25] B. Roberts, N. S. Seixas, B. Mukherjee, and R. L. Neitzel, “Evaluating the Risk of Noise-Induced Hearing Loss Using Different Noise Measurement Criteria,” Ann Work Expo Health, vol. 62, no. 3, pp. 295–306, Mar. 2018, doi: 10.1093/annweh/wxy001.

[26] A. U. Abidin, A. L. Munawaroh, A. Rosinta, A. T. Sulistiyani, I. Ardianta, and F. M. Iresha, “Environmental health risks and impacts of PM2.5 exposure on human health in residential areas, Bantul, Yogyakarta, Indonesia,” Toxicol Rep, vol. 14, Jun. 2025, doi: 10.1016/j.toxrep.2025.101949.

[27] G. N. Ferrari, G. C. L. Leal, P. C. Ossani, and E. V. C. Galdamez, “Investigation of the usage of machine learning to explore the impacts of climate change on occupational health: a systematic review and research agenda,” 2025, Frontiers Media SA. doi: 10.3389/fpubh.2025.1578558.

[28] Q. Gong, L. Xie, D. Dou, K. Wang, and G. Zhang, “A random forest model for exertional heat illness prediction in the power grid work place,” in 2022 International Conference on Frontiers of Communications, Information System and Data Science (CISDS), IEEE, Nov. 2022, pp. 60–63. doi: 10.1109/CISDS57597.2022.00017.

[29] A. Badhoutiya, R. P. Verma, A. Shrivastava, K. Laxminarayanamma, A. L. N. Rao, and A. K. Khan, “Random Forest Classification in Healthcare Decision Support for Disease Diagnosis,” in 2023 International Conference on Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI), IEEE, Dec. 2023, pp. 1–7. doi: 10.1109/ICAIIHI57871.2023.10489244.

[30] M. Rahmiani Iranshahi, M. Aliabadi, R. Golmohammadi, A. Soltanian, and M. Babamiri, “Empirical prediction model of psychophysiological responses of workers with respect to noise exposure based on random forest,” Noise and Vibration Worldwide, vol. 53, no. 6, pp. 290–299, Jun. 2022, doi: 10.1177/09574565221093258.

[31] M. Basner et al., “Auditory and non-auditory effects of noise on health,” The Lancet, vol. 383, no. 9925, pp. 1325–1332, Apr. 2014, doi: 10.1016/S0140-6736(13)61613-X.