Safety and Health at Work

Occupational Safety and Health Research Institute, Korea Occupational Safety and Health Agency (산업안전보건연구원)
권호 표지
DOI QR코드

DOI QR Code

Utilizing Artificial Neural Networks for Establishing Hearing-Loss Predicting Models Based on a Longitudinal Dataset and Their Implications for Managing the Hearing Conservation Program

  • Thanawat Khajonklin (Department of Environmental and Occupational Health, College of Medicine, National Cheng Kung University) ;
  • Yih-Min Sun (Department of Occupational Safety and Health, Chung Hwa University of Medical Technology) ;
  • Yue-Liang Leon Guo (Department of Environmental and Occupational Medicine, Medical College, National Taiwan University) ;
  • Hsin-I Hsu (Environmental and Labor Affairs Division, Southern Taiwan Science Park Bureau, Ministry of Science and Technology) ;
  • Chung Sik Yoon (Department of Environmental Health Sciences, Seoul National University Graduate School of Public Health) ;
  • Cheng-Yu Lin (Department of Otolaryngology, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University) ;
  • Perng-Jy Tsai (Department of Environmental and Occupational Health, College of Medicine, National Cheng Kung University)
  • Received : 2023.10.03
  • Accepted : 2024.02.18
  • Published : 2024.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Background: Though the artificial neural network (ANN) technique has been used to predict noise-induced hearing loss (NIHL), the established prediction models have primarily relied on cross-sectional datasets, and hence, they may not comprehensively capture the chronic nature of NIHL as a disease linked to long-term noise exposure among workers. Methods: A comprehensive dataset was utilized, encompassing eight-year longitudinal personal hearing threshold levels (HTLs) as well as information on seven personal variables and two environmental variables to establish NIHL predicting models through the ANN technique. Three subdatasets were extracted from the afirementioned comprehensive dataset to assess the advantages of the present study in NIHL predictions. Results: The dataset was gathered from 170 workers employed in a steel-making industry, with a median cumulative noise exposure and HTL of 88.40 dBA-year and 19.58 dB, respectively. Utilizing the longitudinal dataset demonstrated superior prediction capabilities compared to cross-sectional datasets. Incorporating the more comprehensive dataset led to improved NIHL predictions, particularly when considering variables such as noise pattern and use of personal protective equipment. Despite fluctuations observed in the measured HTLs, the ANN predicting models consistently revealed a discernible trend. Conclusions: A consistent correlation was observed between the measured HTLs and the results obtained from the predicting models. However, it is essential to exercise caution when utilizing the model-predicted NIHLs for individual workers due to inherent personal fluctuations in HTLs. Nonetheless, these ANN models can serve as a valuable reference for the industry in effectively managing its hearing conservation program.

Keywords

Acknowledgement

The authors would like to thank the Institute of Labor, Occupational Safety and Health in Taiwan for supporting this research project.

References

  1. WHO. World report on hearing. Geneva: World Health Organization. 2021. Available from: https://www.who.int/publications/i/item/9789240020481.
  2. Daniel E. Noise and hearing loss: a review. J Sch Health 2007;77(5):225-31. https://doi.org/10.1111/j.1746-1561.2007.00197.x
  3. Nelson DI, Nelson RY, Concha-Barrientos M, Fingerhut M. The global burden of occupational noise-induced hearing loss. Am J Ind Med 2005;48(6):446-58. https://doi.org/10.1002/ajim.20223
  4. Roughton JE, Crutchfield N. Job hazard analysis: a guide for voluntary compliance and beyond; 2008.
  5. NIOSH. Preventing hearing loss caused by chemical (ototoxicity) and noise exposure. The National Institute for Occupational Safety and Health; 2018.
  6. Lao XQ, Yu IT, Au DK, Chiu YL, Wong CC, Wong TW. Noise exposure and hearing impairment among Chinese restaurant workers and entertainment employees in Hong Kong. PLoS One 2013;8(8):e70674.
  7. Sjodin F, Kjellberg A, Knutsson A, Landstrom U, Lindberg L. Noise exposure and auditory effects on preschool personnel. Noise Health 2012;14(57):72-82. https://doi.org/10.4103/1463-1741.95135
  8. Wang D, Wang Z, Zhou M, Li W, He M, Zhang X, Guo H, Yuan J, Zhan Y, Zhang K, Zhou T, Kong W, Chen W. The combined effect of cigarette smoking and occupational noise exposure on hearing loss: evidence from the Dongfeng-Tongji Cohort Study. Sci Rep 2017;7(1):11142.
  9. Park JA, Suh MJ. Hazardous alcohol consumption and the risk of hearing impairment in adults based on the Korean National Health and Nutrition Survey: a retrospective study. J Audiol Otol 2019;23(2):63-8. https://doi.org/10.7874/jao.2018.00241
  10. Hu H, Tomita K, Kuwahara K, Yamamoto M, Uehara A, Kochi T, Eguchi M, Okazaki H, Hori A, Sasaki N, Ogasawara T, Honda T, Yamamoto S, Nakagawa T, Miyamoto T, Imai T, Nishihara A, Nagahama S, Murakami T, Shimizu M, Akter S, Kashino I, Yamaguchi M, Kabe I, Mizoue T, Sone T, Dohi S. Obesity and risk of hearing loss: a prospective cohort study. Clin Nutr 2020;39(3):870-5. https://doi.org/10.1016/j.clnu.2019.03.020
  11. Verbeek JH, Kateman E, Morata TC, Dreschler WA, Mischke C. Interventions to prevent occupational noise-induced hearing loss. Cochrane Database Syst Rev 2012;10.
  12. Park MY, Casali JG. A controlled investigation of in-field attenuation performance of selected insert, earmuff, and canal cap hearing protectors. Hum Factors 1991;33(6):693-714.
  13. Chang SJ, Chang CK. Prevalence and risk factors of noise-induced hearing loss among liquefied petroleum gas (LPG) cylinder infusion workers in Taiwan. Ind Health 2009;47(6):603-10.
  14. Rabinowitz PM, Galusha D, Dixon-Ernst C, Slade MD, Cullen MR. Do ambient noise exposure levels predict hearing loss in a modern industrial cohort? Occup Environ Med 2007;64(1):53-9. https://doi.org/10.1136/oem.2005.025924
  15. Miyata J, Umesawa M, Yoshioka T, Iso H. Association between high systolic blood pressure and objective hearing impairment among Japanese adults: a facility-based retrospective cohort study. Hypertens Res 2022;45(1):155-61. https://doi.org/10.1038/s41440-021-00737-8
  16. Kolarzyk E, Stepniewski M, Mendyk A, Kitlinski M, Pietrzycka A. The usefulness of artificial neural networks in the evaluation of pulmonary efficiency and antioxidant capacity of welders. Int J Hyg Environ Health 2006;209(4):385-92. https://doi.org/10.1016/j.ijheh.2006.03.004
  17. Basheer IA, Hajmeer M. Artificial neural networks: fundamentals, computing, design, and application. J Microbiol Methods 2000;43(1):3-31. https://doi.org/10.1016/S0167-7012(00)00201-3
  18. Bur AM, Shew M, New J. Artificial intelligence for the otolaryngologist: a state of the art review. Otolaryngol Head Neck Surg 2019;160(4):603-11. https://doi.org/10.1177/0194599819827507
  19. Lin SC, Lin MY, Kang BH, Lin YS, Liu YH, Yin CY, Lin PS, Lin CW. Artificial neural network-assisted classification of hearing prognosis of sudden sensorineural hearing loss with vertigo. IEEE J Transl Eng Health Med 2023;11:170-81.
  20. Aliabadi M, Farhadian M, Darvishi E. Prediction of hearing loss among the noise-exposed workers in a steel factory using artificial intelligence approach. Int Arch Occup Environ Health 2015;88(6):779-87. https://doi.org/10.1007/s00420-014-1004-z
  21. Zare S, Ghotbiravandi MR, Elahishirvan H, Ahsaeed MG, Rostami M, Esmaeili R. Modeling and predicting the changes in hearing loss of workers with the use of a neural network data mining algorithm: a field study. Arch Acoust 2020;45(2):303-11.
  22. Kimberley BP, Kimberley BM, Roth L. A neural network approach to the prediction of pure tone thresholds with distortion product emissions. Ear Nose Throat J 1994;73(11). 812e813, 817-823. https://doi.org/10.1177/014556139407301105
  23. de Waal R, Hugo R, Soer M, Kruger JJ. Predicting hearing loss from otoacoustic emissions using an artificial neural network. S Afr J Commun Disord 2002;49:28-39. https://doi.org/10.4102/sajcd.v49i1.215
  24. Agrawal Y, Platz EA, Niparko JK. Risk factors for hearing loss in US adults: data from the National Health and Nutrition Examination Survey, 1999 to 2002. Otol Neurotol 2009;30(2):139-45. https://doi.org/10.1097/MAO.0b013e318192483c
  25. ANSI. American National Standard Specification for Personal Noise Dosimeters: ANSI S1.25-1991. American National Standard; 1997.
  26. ANSI. American National Standard Specification for Sound Level Meters: ANSI S1.4-1983. American National Standard; 2001.
  27. Berger EH. The Noise Manual. 5th ed. American Industrial Hygiene Association; 2003.
  28. ISO. Acoustics-audiometric test methods-Part 1: Basic pure tone air and bone conduction audiometry. ISO 8253-1: International Organization for Standardization; 1987.
  29. Olusanya BO, Davis AC, Hoffman HJ. Hearing loss grades and the International classification of functioning, disability and health. Bull World Health Organ 2019;97(10):725-8. https://doi.org/10.2471/BLT.19.230367
  30. Corne SA. Artificial neural networks for pattern recognition. Concepts Magn Reson 1996;8(5):303-24. https://doi.org/10.1002/(SICI)1099-0534(1996)8:5<303::AID-CMR1>3.0.CO;2-2
  31. Gbashi S, Maselesele TL, Njobeh PB, Molelekoa TBJ, Oyeyinka SA, Makhuvele R, Adebo OA. Application of a generative adversarial network for multi-featured fermentation data synthesis and artificial neural network (ANN) modeling of bitter gourd-grape beverage production. Sci Rep 2023;13(1):11755.
  32. Russell SJ, Norvig P. Artificial intelligence: a modern approach. Pearson; 2009.
  33. Anthony M, Bartlett PL. Neural network learning. Cambridge University Press; 2010.
  34. Haykin S. Neural networks and learning machines. 3rd ed. Pearson; 2009.
  35. Paliwal M, Kumar UA. Neural networks and statistical techniques: a review of applications. Expert Syst Appl 2009;36(1):2-17. https://doi.org/10.1016/j.eswa.2007.10.005
  36. Olden JD, Jackson DA. Illuminating the "black box": a randomization approach for understanding variable contributions in artificial neural networks. Ecol Model 2002;154(1-2):135-50. https://doi.org/10.1016/S0304-3800(02)00064-9
  37. Moshammer H, Kundi M, Wallner P, Herbst A, Feuerstein A, Hutter HP. Early prognosis of noise-induced hearing loss. Occup Environ Med 2015;72(2):85-9. https://doi.org/10.1136/oemed-2014-102200
  38. Killion MC, Villchur E. Comments on "Earphones in Audiometry" [Zwislocki et al., J. Acoust. Soc. Am. 83, 1688-1689 (1988)]. J Acoust Soc Am 1989;85(4):1775-9. https://doi.org/10.1121/1.397969
  39. Schmuziger N, Probst R, Smurzynski J. Test-retest reliability of pure-tone thresholds from 0.5 to 16 kHz using Sennheiser HDA 200 and Etymotic Research ER-2 earphones. Ear Hear 2004;25(2):127-32. https://doi.org/10.1097/01.AUD.0000120361.87401.C8
  40. Moroe NF, Khoza-Shangase K. Recent advances in hearing conservation programmes: a systematic review. S Afr J Commun Disord 2020;67(2):675.