Contributions and limitations of using machine learning to predict noise-induced hearing loss
Grais, Emad M.
MetadataShow full item record
Purpose Noise-induced hearing loss (NIHL) is a global issue that impacts people’s life and health. The current review aims to clarify the contributions and limitations of applying machine learning (ML) to predict NIHL by analyzing the performance of different ML techniques and the procedure of model construction. Methods The authors searched PubMed, EMBASE and Scopus on November 26, 2020. Results Eight studies were recruited in the current review following defined inclusion and exclusion criteria. Sample size in the selected studies ranged between 150 and 10,567. The most popular models were artificial neural networks (n = 4), random forests (n = 3) and support vector machines (n = 3). Features mostly correlated with NIHL and used in the models were: age (n = 6), duration of noise exposure (n = 5) and noise exposure level (n = 4). Five included studies used either split-sample validation (n = 3) or ten-fold cross-validation (n = 2). Assessment of accuracy ranged in value from 75.3% to 99% with a low prediction error/root-mean-square error in 3 studies. Only 2 studies measured discrimination risk using the receiver operating characteristic (ROC) curve and/or the area under ROC curve. Conclusion In spite of high accuracy and low prediction error of machine learning models, some improvement can be expected from larger sample sizes, multiple algorithm use, completed reports of model construction and the sufficient evaluation of calibration and discrimination risk.
International Archives of Occupational and Environmental Health;
Chen, F., Cao, Z., Grais, E.M., Zhao, F. (2021) 'Contributions and limitations of using machine learning to predict noise-induced hearing loss', International Archives of Occupational and Environmental Health. https://doi.org/10.1007/s00420-020-01648-w
Article published in International Archives of Occupational and Environmental Health available open access at https://doi.org/10.1007/s00420-020-01648-w
Cardiff Metropolitan University (Grant ID: Cardiff Metropolian (Internal))
Showing items related by title, author, subject and abstract.
Relationship between Internal Corporate Governance Mechanisms and Shareholder Value in the Banking Sector in Bangladesh: The Mediating Effect of Non-Equity Stakeholders Hossain, Mohammad Kamal (Cardiff Metropolitan University, 2020)Contemporary corporate governance models, namely the shareholder and stakeholder models, offer different advice on how best to manage and maximise the interests of the shareholders in a firm. While the shareholder model ...
Richards, Justine Bess (Cardiff Metropolitan University, 2013)Introduction: Neurolinguistic programming (NLP) is a psychological paradigm in use in many professional fields, including speech and language therapy. One aspect of this theory is the eye accessing cues (EAC) model which ...
Do contrasting SOI types and sexes differ in their perceptions of eye contact as flirtatious behaviour? And does exhibiting eye contact effect attractiveness? Bowen, Lloyd (Cardiff Metropolitan University, 2013)Background Eye contact is argued to be a predominant form of nonverbal communication, serving many functions (Kleinke, 1986) including expressing emotions (Knapp and Hall, 2010) and communicating intimacy (Kleinke, 1986). ...