Performance of machine-learning algorithms to pattern recognition and classification of hearing impairment in Brazilian farmers exposed to pesticide and/or cigarette smoke

  • Jamile Silveira Tomiazzi
  • Danillo Roberto Pereira
  • Meire Aparecida Judai
  • Patrícia Alexandra Antunes
  • Ana Paula Alves FavaretoEmail author
Research Article


The use of pesticides has been increasing in agriculture, leading to a public health problem. The aim of this study was to evaluate ototoxic effects in farmers who were exposed to cigarette smoke and/or pesticides and to identify possible classification patterns in the exposure groups. The sample included 127 participants of both sexes aged between 18 and 39, who were divided into the following four groups: control group (CG), smoking group (SG), pesticide group (PG), and smoking + pesticide group (SPG). Meatoscopy, pure tone audiometry, logoaudiometry, high-frequency thresholds, and immittance testing were performed. Data were evaluated by artificial neural network (ANN), K-nearest neighbors (K-NN), and support vector machine (SVM). There was symmetry between the right and left ears, an increase in the incidence of hearing loss at high frequency and of downward sloping audiometric curve configuration, and alteration of stapedial reflex in the three exposed groups. The machine-learning classifiers achieved good classification performance (control and exposed). The best classification results occur in high type (I and II) datasets (about 90% accuracy) in k-NN test. It is concluded that both xenobiotic substances have ototoxic potential; however, their combined use does not present additive or potentiating effects recognizable by the algorithms.


Machine learning Artificial intelligence Pesticide Smoking Hearing loss Farmer 



This study was financed in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Brasil (CAPES) - Finance Code 001. Grant support was provided by University of Western São Paulo (UNOESTE).

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Supplementary material

11356_2018_4106_MOESM1_ESM.pdf (560 kb)
ESM 1 (PDF 559 kb)


  1. Abdollahi H, Mostafaei S, Cheraghi S, Shiri I, Rabi Mahdavi S, Kazemnejad A (2018) Cochlea CT radiomics predicts chemoradiotherapy induced sensorineural hearing loss in head and neck cancer patients: a machine learning and multi-variable modelling study. Phys Med 45:192–197. CrossRefGoogle Scholar
  2. Agrawal Y, Platz E, Niparko JK (2008) Prevalence of hearing loss and differences by demographic characteristics among US adults. Arch Intern Med 168:1522–1530. CrossRefGoogle Scholar
  3. Albuquerque VHC, Nunes TM, Pereira DR, Luz EJ, Menotti D, Papa JP, Tavares JMRS (2016) Robust automated cardiac arrhythmia detection in ECG beat signals. Neural Comput Appl 29:679–693. CrossRefGoogle Scholar
  4. Albuquerque VHC, Papa J, Pereira DR (2017) Automatic identification of epileptic EEG signals through binary magnetic optimization algorithms. Neural Comput Appl 1:1–13. Google Scholar
  5. Benedetti D, Nunes E, Sarmento M, Porto C, Dos Santos CE, Dias JF, da Silva J (2013) Genetic damage in soybean workers exposed to pesticides: evaluation with the comet and buccal micronucleus cytome assays. Mutat Res 752(1–2):28–33. CrossRefGoogle Scholar
  6. Bing D, Ying J, Miao J, Lan L, Wang D, Zhao L, Yin Z, Yu L, Guan J, Wang Q (2018) Predicting the hearing outcome in sudden sensorineural hearing loss via machine learning models. Clin Otolaryngol 43:1–7. CrossRefGoogle Scholar
  7. Blair A, Freeman LB (2009) Epidemiologic studies of cancer in agricultural populations: observations and future directions. J Agromedicine 14(2):125–131. CrossRefGoogle Scholar
  8. Campo P, Morata TC, Hong O (2013) Chemical exposure and hearing loss. Dis Mon 59(4):119–138. CrossRefGoogle Scholar
  9. Chang CC, Lin CJ (2011) LIBSVM: A library for support vector machines. ACM Trans Intell Syst Technol 2:1–27 Software available at Accessed 10 Nov 2017
  10. Chari DA, Limb CJ (2018) Tinnitus. Med Clin North Am 102(6):1081–1093. CrossRefGoogle Scholar
  11. Chen H, Hu L, Li H, Hong G, Zhang T, Ma J, Lu Z (2017) An effective machine learning approach for prognosis of paraquat poisoning patients using blood routine indexes. Basic Clin Pharmacol Toxicol 120(1):86–96. CrossRefGoogle Scholar
  12. Cogo LA, Santos Filha VAV, Murashima AAB, Hyppolito MA, Silveira AF (2016) Morphological analysis of the vestibular system of Guinea pigs poisoned by organophosphate. Braz J Otorhinolaryngol 82(1):11–16. CrossRefGoogle Scholar
  13. Crawford JM, Hoppin JA, Alavania MC, Blair A, Sandler DP, Kamel F (2008) Hearing loss among licensed pesticide applicators in the agricultural health study running title: hearing loss among licensed pesticide applicators. J Occup Environ Med 7:817–826. CrossRefGoogle Scholar
  14. Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines and other kernel-based learning methods. University Press, CambridgeCrossRefGoogle Scholar
  15. Damalas CA, Abdollahzadeh G (2015) Farmer’s use of personal productive equipment during handling of plant protection products: determinants of implementation. Sci Environ Total 571:730–736. CrossRefGoogle Scholar
  16. Deziel NC, Beane Freeman LE, Graubard BI, Jones RR, Hoppin JA, Thomas K, Hines CJ, Blair A, Sandler DP, Chen H, Lubin JH, Andreotti G, Alavanja MC, Friesen MC (2017) Relative contributions of agricultural drift, Para-occupational, and residential use exposure pathways to house dust pesticide concentrations: meta-regression of published data. Environ Health Perspect 125(3):296–305. CrossRefGoogle Scholar
  17. Donkor U, Osei-Fosu P, Dubey B, Kingsford-Adaboh R, Ziwu C, Asante I (2016) Pesticide residues in fruits and vegetables in Ghana: a review. Environ Sci Pollut Res Int 23(19):18966–18987. CrossRefGoogle Scholar
  18. Dutta S, Bahadur M (2016) Cytogenetic analysis of micronuclei and cell death parameters in epithelial cells of pesticide exposed tea garden workers. Toxicol Mech Methods 26(8):627–634. CrossRefGoogle Scholar
  19. Embrandiri A, Kiyasudeen SK, Rupani PF, Ibrahim MH (2016) Environmental xenobiotics and its effects on natural ecosystem. In: Singh A, Prasad S, Singh R (eds) Plant responses to xenobiotics. Springer, Singapore, pp 1–18. Google Scholar
  20. Finkler AD, Silveira AF, Munaro G, Zanrosso CD (2012) Otoprotection in guinea pigs exposed to pesticides and Ginkgo biloba. Bras J Otorhinolaryngol 3:122–128. CrossRefGoogle Scholar
  21. Gelfand SA (1984) The contralateral acoustic reflex threshold. In: Silman S (ed) The acoustic reflex: basic principles and clinical aplications, Academic Press, Orlando, pp 137–186Google Scholar
  22. Gomez MI, Hwang SA, Sobotova L, Stark AD, Maio JJ (2001) A comparison of self-reported hearing loss and audiometry in a cohort of New York farmers. J Speech Lang Hear Res 6:1201–1208. CrossRefGoogle Scholar
  23. Hall P, Park BU, Samworth RJ (2008) Choice of neighbor order in nearest-neighbor classification. Ann Statist 6(5):2135–2152. CrossRefGoogle Scholar
  24. Haykin S (1999) Neural networks: a Comprehensive Foundation, 2nd edn. Prentice Hall, New JerseyGoogle Scholar
  25. Hoshino AC, Pacheco-Ferreira H, Taguchi CK, Tomita S, Miranda MF (2008) Ototoxicity study in workers exposed to organophosphate. Braz J Otorhinolaryngol 6:912–918. CrossRefGoogle Scholar
  26. Hu L, Li H, Cai Z, Lin F, Hong G, Chen H, Lu Z (2017a) A new machine-learning method to prognosticate paraquat poisoned patients by combining coagulation, liver, and kidney indices. PLoS One 12(10):e0186427. CrossRefGoogle Scholar
  27. Hu L, Lin F, Li H, Tong C, Pan Z, Li J, Chen H (2017b) An intelligent prognostic system for analyzing patients with paraquat poisoning using arterial blood gas indexes. J Pharmacol Toxicol Methods 84:78–85. CrossRefGoogle Scholar
  28. Jerger J (1970) Clinical experience with impedance audiometry. Arch Otolaryngol 92(4):311–324. CrossRefGoogle Scholar
  29. Jerger J, Speaks C, Trammell J (1968) A new approach to speech audiometry. J Speech Hear Disord 33:318–328. CrossRefGoogle Scholar
  30. Kim KH, Kabir E, Jahan SA (2017) Exposure to pesticides and the associated human health effects. Sci Total Environ 575:525–535. CrossRefGoogle Scholar
  31. Konrad-Martin D, Reavis KM, McMillan GP, Dille MF (2012) Multivariate DPOAE metrics for identifying changes in hearing: perspectives from ototoxicity monitoring. Int J Audiol 51:51–62. CrossRefGoogle Scholar
  32. Li-Korotky HS (2012) Age-related hearing loss: quality of care for quality of life. Gerontologist 52(2):265–271. CrossRefGoogle Scholar
  33. Lloyd LL, Kaplan H (1978) Audiometric interpretation: a manual of basic audiometry. University Park Press, BaltimoreGoogle Scholar
  34. Nakanishi N, Okamoto M, Nakamura K, Suzuki K, Tatara K (2000) Cigarette smoking and risk for hearing impairment: a longitudinal study in Japanese male office workers. J Occup Environ Med 42(11):1045–1049. CrossRefGoogle Scholar
  35. Nissen S (2003) Implementation of a Fast Artificial Neural Network Library (FANN). Department of Computer Science University of Copenhagen (DIKU), Copenhagen Software available at Accessed 09 Nov 2017
  36. Papa JP, Albuquerque VHC, Falcão AX, Tavares JMRS (2012) Efficient supervised Optimum-Path Forest classification for large datasets. Pattern Recognit 45:512–520. CrossRefGoogle Scholar
  37. Pereira CR, Pereira DR, Silva FA, Masieiro JP, Weber SA, Hook C, Papa JP (2016) A new computer vision-based approach to aid the diagnosis of Parkinson's disease. Comput Methods Programs Biomed 136:79–88. CrossRefGoogle Scholar
  38. Pereira DR, Pisani RJ, Souza AN, Papa JP (2017) An ensemble-based stacked sequential learning algorithm for remote sensing imagery classification. IEEE J Sel Top Appl Earth Obs Remote Sens 10(4):525–1541. CrossRefGoogle Scholar
  39. Pereira DR, Papa JP, Saraiva GFR, Souza GM (2018) Automatic classification of plant electrophysiological responses to environmental stimuli using machine learning and interval arithmetic. Comput Electron Agric 145:35–42. CrossRefGoogle Scholar
  40. Ponchio APS, Oliveira JTA (2013) Relations between communication and development of family farmers. Eng Agric 33(6):1301–1311. Google Scholar
  41. Popp J, Pető K, Nagy J (2013) Pesticide productivity and food security. A review. Agron Sustain Dev 33:243–255. CrossRefGoogle Scholar
  42. Rigotto RM, Vasconcelos DP, Rocha MM (2014) Pesticide use in Brazil and problems for public health. Cad Saúde Pública 30(7):1360–1362. CrossRefGoogle Scholar
  43. Rogha M, Hashemi M, Askari N, Abtahi SH, Sepehrnejad M, Nilforoush MH (2015) Cigarette smoking effect on human cochlea responses. Adv Biomed Res 4:1–9. CrossRefGoogle Scholar
  44. Schölkopf B, Smola A (2002) Learning with kernels. MIT Press, CambridgeGoogle Scholar
  45. Searchfield GD, Jerram C, Wise K, Raymond S (2007) The impact of hearing loss on tinnitus severity. Aust New Zealand J Audiol 29(2):67–76. CrossRefGoogle Scholar
  46. Sharabi Y, Reshef-Haran I, Burstein M, Eldad A (2002) Cigarette smoking and hearing loss: lessons from the young adults periodic examinations in Israel (YAPEIS) database. Isr Med Assoc J 4(12):1118–1120Google Scholar
  47. Silman S, Silverman CA (1997) Basic audiologic testing. In: Silman S, Silverman CA (eds) Auditory diagnosis: principles and applications. Singular Publishing Group, San Diego, pp 44–52Google Scholar
  48. Silvério ACP, Machado SC, Azevedo L, Nogueira DA, de Castro Graciano MM, Simões JS, Viana ALM, Martins I (2017) Assessment of exposure to pesticides in rural workers in southern of Minas Gerais, Brazil. Environ Toxicol Pharmacol 55:99–106. CrossRefGoogle Scholar
  49. Silvestre RAA, Ribas A, Hammerschmidt R, de Lacerda ABM (2016) High-frequency profile in adolescents and its relationship with the use of personal stereo devices. J Pediatr 92:206–211. CrossRefGoogle Scholar
  50. Sulaiman AH, Seluakumaran K, Husain R (2013) Hearing risk associated with the usage of personal listening devices among urban high school students in Malaysia. Public Health 8:710–715. CrossRefGoogle Scholar
  51. Teixeira CF, Augusto GSL, Morata TC (2003) Hearing health of workers exposed to noise and insecticides. Rev Saúde Pública 37(4):417–423. CrossRefGoogle Scholar
  52. Tomiazzi JS, Judai MA, Nai GA, Pereira DR, Antunes PA, Favareto APA (2018) Evaluation of genotoxic effects in Brazilian agricultural workers exposed to pesticides and cigarette smoke using machine-learning algorithms. Environ Sci Pollut Res Int 25(2):1259–1269. CrossRefGoogle Scholar
  53. Ukaegbe O, Ezeanolue B, Oriji F (2016) The influence of tinnitus on the audiometric threshold of sufferers. Int Arch Otorhinolaryngol 4:339–343. Google Scholar
  54. Vapnik V (1999) An overview of statistical learning theory. IEEE Trans Neural Netw 10(5):988–999. CrossRefGoogle Scholar
  55. Zhao X, Zhang X, Cai Z, Tian X, Wang X, Huang Y, Chen H, Hu L (2018) Chaos enhanced grey wolf optimization wrapped ELM for diagnosis of paraquat-poisoned patients. Comput Biol Chem.
  56. Zhou S, Li GB, Huang LY, Xie HZ, Zhao YL, Chen YZ, Li LL, Yang SY (2014) A prediction model of drug-induced ototoxicity developed by an optimal support vector machine (SVM) method. Comput Biol Med 51:122–127. CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Graduate Program in Environment and Regional DevelopmentUniversity of Western São Paulo – UNOESTEPresidente PrudenteBrazil
  2. 2.Faculty of Health SciencesUniversity of Western São Paulo – UNOESTEPresidente PrudenteBrazil

Personalised recommendations