Soylemez, E.Avci, I.Yildirim, E.Karaboya, E.Yilmaz, N.Ertugrul, S.Tokgoz-Yilmaz, S.2024-09-292024-09-2920240022-2151https://doi.org/10.1017/S002221512400094Xhttps://hdl.handle.net/20.500.14619/9549Objective: This study aims to determine which machine learning (ML) model is most suitable for predicting noise-induced hearing loss (NIHL) and the effect of tinnitus on the models' accuracy. Method: Two hundred workers employed in a metal industry were selected for this study and tested using pure tone audiometry. Their occupational exposure histories were collected, analysed, and used to create a dataset. Eighty percent of the data collected was used to train six ML models, and the remaining 20% was used to test the models. Results: Eight (40.5%) workers had bilaterally normal hearing, and 119 (59.5%) had hearing loss. Tinnitus was the second most important indicator after age for NIHL. The support vector machine (SVM) was the best-performing algorithm with 90% accuracy, 91% F1-score, 95% precision, and 88% recall. Conclusion: The use of tinnitus as a risk factor in the SVM model may increase the success of occupational health and safety programs. © 2024 Cambridge University Press. All rights reserved.eninfo:eu-repo/semantics/closedAccessMachine learningnoise-induced hearing lossoccupational diseaseworkersArticle10.1017/S002221512400094X2-s2.0-8519306902238719484Q2