Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Public Health and Surveillance

Date Submitted: May 9, 2024
Date Accepted: Aug 30, 2024

The final, peer-reviewed published version of this preprint can be found here:

Optimizing a Classification Model to Evaluate Individual Susceptibility in Noise-Induced Hearing Loss: Cross-Sectional Study

Li S, Yu X, Ma X, Wang Y, Guo J, Wang J, Shen W, Dong H, Salvi RJ, Wang H, Yin S

Optimizing a Classification Model to Evaluate Individual Susceptibility in Noise-Induced Hearing Loss: Cross-Sectional Study

JMIR Public Health Surveill 2024;10:e60373

DOI: 10.2196/60373

PMID: 39629704

PMCID: 11615998

Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.

Optimizing a Classification Model to Evaluate Individual Susceptibility to Noise-induced Hearing Loss

  • Shiyuan Li; 
  • Xiao Yu; 
  • Xinrong Ma; 
  • Ying Wang; 
  • Junjie Guo; 
  • Jiping Wang; 
  • Wenxin Shen; 
  • Hongyu Dong; 
  • Richard J. Salvi; 
  • Hui Wang; 
  • Shankai Yin

ABSTRACT

Background:

Noise-induced hearing loss (NIHL), one of the leading causes of hearing loss in young adults, is a major health care problem that has negative social and economic consequences. Among those exposed to the detrimental effects of workplace noise, some are especially vulnerable and develop NIHL after only a short time in the workplace, while other are extremely resistant and develop NIHL after many years of work.

Objective:

To determine an optimal model for detecting susceptible/resistant to NIHL and further explore phenotypic traits uniquely associated with susceptibility profiles.

Methods:

This study was performed from 2015 to 2021 at shipyards in Shanghai, China. Six methods were applied to our dataset to evaluated their classification performance. An machine learning (ML)-based diagnostic model employing frequencies from 0.25 to 12 kHz were developed to determine the most reliable frequencies, considering accuracy and area under the curve (AUC). An optimal method with most reliable frequencies was then constructed for detecting susceptible/resistant to NIHL. Phenotypic characteristics such as age, exposure time, cumulative noise exposure (CNE), and HTs, were explored for these group.

Results:

A total of 6276 participants (median [interquartile range (IQR)] age, 41.0 [33.0-47.0] years; 5372 [84.9%] men) were included in the analysis. An ML-based NIHL diagnostic model with misclassified subjects showed the most promising performance for identifying workers in NIHL susceptible group (NIHL-SG) and NIHL resistant group (NIHL-RG). The mean hearing thresholds (HTs) at 4 and 12.5 kHz frequencies demonstrates the highest predictive value for detecting NIHL-SG and NIHL-RG (accuracy = 0.78, AUC = 0.81). Individuals in the NIHL-SG selected by the optimized model were younger (28.0 [25.0-31.0] versus 35.0 [32.0-39.0] years old, p<0.001), with less duration of noise exposure (5.0 [2.0-8.0] versus 8.0 [4.0-12.0] years, p<0.001)and lower CNE (90.3 [85.7-92.4] versus 92.2 [89.2-94.7] dBA-year, p<0.001) but greater HTs than those in NIHL-RG (4&12.5 kHz: 58.8 [53.8-63.8] versus 8.8 [7.5-11.3] dB, p<0.001).

Conclusions:

An ML-based NIHL diagnostic model with misclassified subjects, employing the mean HTs of 4 and 12.5kHz, was regarded as the most reliable method for identifying individuals susceptible or resistant to NIHL, proceeding with future studies on genetic that govern susceptibility to NIHL. Clinical Trial: This study was granted by the Institutional Ethics Review Board at Shanghai Sixth People’s Hospital affiliated with Shanghai Jiao Tong University and was registered in the Chinese Clinical Trial Registry under the identifier ChiCTR-RPC-17012580.


 Citation

Please cite as:

Li S, Yu X, Ma X, Wang Y, Guo J, Wang J, Shen W, Dong H, Salvi RJ, Wang H, Yin S

Optimizing a Classification Model to Evaluate Individual Susceptibility in Noise-Induced Hearing Loss: Cross-Sectional Study

JMIR Public Health Surveill 2024;10:e60373

DOI: 10.2196/60373

PMID: 39629704

PMCID: 11615998

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.