Predicting and Weighting the Factors Affecting Workers’ Hearing Loss Based on Audiometric Data Using C5 Algorithm

Abstract

Introduction: With the extensively spread of industrialization in the world, noise exposure is becoming more prevalent in the industrial settings. The most important and definite harmful effects of sound include hearing loss, both permanent and temporary. Objective: This study was designed aimed to use the C5 algorithm to determine the weight of factors affecting the workers’ hearing loss based on the audiometric data. Methods: This cross-sectional, descriptive, analytical study was conducted in 2018 in a mining industry in southeastern Iran. In this study, workers were divided into three exposed groups with different sound pressure levels (one control group and two case groups). Audiometry was conducted for each group of 50 persons; hence, the total number of subjects was 150. The stages of this study include: 1) selecting factors (predictive) to check and weigh them; 2) conducting the audiometry for both ears; 3) calculating the permanent hearing loss in each ear and permanent hearing loss of both ears; 4) classifying the types of hearing loss; and 5) investigating and determining the weight of factors affecting the hearing loss and their classification based on the C5 algorithm and determining the error and accuracy rate of each model. To assess and determine the factors affecting the hearing loss of workers, the C5 algorithm and IBM SPSS Modeler 18.0 were used. SPSS V.18 was used to analyze the linear regression and paired t-test tests, too. Results: The results showed that in the first model (SPL <70 dBA), the 8KHz frequency with the weight of 31% had the highest effect, the factors of work experience and the frequency of 250Hz each with the weight of 3%, had the least effect, and the accuracy of the model was 100%. In the second model (SPL 70–80 dBA) the frequency of 8KHz with the weight of 21% had the highest effect, the frequency of 250Hz and the working experience each had the lowest effect with the weight of 7% and the accuracy of the model was calculated as 100%. In the third model (SPL >85 dBA), the 4KHz frequency with the weight of 31% had the highest effect, and the work experience with a weight of 1% had the lowest effect, and the accuracy of the model was 94%. In the fourth model, the 4KHz frequency with the weight of 22% had the highest effect and 250Hz and age each with the weight of 8% had the lowest effects; the accuracy of this model was calculated to be 99.05%. Conclusions: During investigating and determining the weight of the factors affecting hearing loss by the C5 algorithm, the high weight and effect of the 4KHz frequency were predicted in hearing loss changes. Considering the high accuracy obtained in this modeling, this algorithm is a suitable and powerful tool for predicting and modeling the hearing loss.

Contributions and limitations of using machine learning to predict noise-induced hearing loss

“…As shown in Table 2 , the gender distribution was imbalanced with many more males than females in five studies (total male vs. female: 12,341 vs. 1869) (Aliabadi et al 2015 ; Farhadian et al 2015 ; Greenwell et al 2018 ; Zhao et al 2019a , b ). There was no information of gender in three included studies (ElahiShirvan et al 2020 ; Zare et al 2019 , 2020 ).…”

“…Different categorization approaches and grading systems of NIHL were used in the studies, e.g. 25 dB HL as a criterion defined by the National Institute for Occupational Safety and Health (NIOSH) (Zhao et al 2019a , b ), and the grade systems recommended by the World Health Organization (WHO) and Occupational Safety and Health Administration (OSHA) (ElahiShirvan et al 2020 ; Farhadian et al 2015 ; Greenwell et al 2018 ; Zare et al 2019 , 2020 ). By contrast, the averaged hearing thresholds of participants were also used as a variable in two studies (Aliabadi et al 2015 ; Zhao et al 2019a ).…”

“…The majority of included studies used accuracy to evaluate various ML models with the predictive ability for NIHL ranging from 75.3% to 99% due to the heterogeneity of datasets and model development. In particular, three studies with the accuracy over 90% provided limited information on input selection and no validation tools were applied (ElahiShirvan et al 2020;Zare et al 2019Zare et al , 2020. Two previous studies which did not meet the inclusion criteria demonstrated similar issues.…”

Weighing and modelling factors influencing serum cortisol and melatonin concentration among workers that are exposed to various sound pressure levels using neural network algorithm: An empirical study

“…The number of people who are in contact with excessive noise levels (>85 dBA) worldwide is estimated to be over 60 million. Additionally, around 22 million American workers are annually exposed to superfluous noise in their working milieu ( Safari Variani et al., 2018 ; Zare et al., 2019 ). On the other hand, following conservative estimations, more than one million healthy people began to develop some form of disease each year as a result of exposure to traffic noise in Western Europe ( Miedema et al., 2011 ).…”

“…In other words, DM aims to collect necessary information and transform it to an understandable structure for further use. Accordingly, the extracted data may be classified to predict outcomes after an intervention or the pattern construction may entail studying the association, group, or detection of variable deviation ( Zare et al., 2019 ). Different steps should be taken in data mining: (1) selection of focal variables.…”