Ruan Y, Huang G, Zhang J, Mai S, Gu C, Rong X, Huang L, Zeng W, Wang Z. Risk analysis of noise-induced hearing loss of workers in the automobile manufacturing industries based on back-propagation neural network model: a cross-sectional study in Han Chinese population.
BMJ Open 2024;
14:e079955. [PMID:
38760055 PMCID:
PMC11103207 DOI:
10.1136/bmjopen-2023-079955]
[Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/13/2023] [Accepted: 04/30/2024] [Indexed: 05/19/2024] Open
Abstract
OBJECTIVES
This study aims to predict the risk of noise-induced hearing loss (NIHL) through a back-propagation neural network (BPNN) model. It provides an early, simple and accurate prediction method for NIHL.
DESIGN
Population based, a cross sectional study.
SETTING
Han, China.
PARTICIPANTS
This study selected 3266 Han male workers from three automobile manufacturing industries.
PRIMARY OUTCOME MEASURES
Information including personal life habits, occupational health test information and occupational exposure history were collected and predictive factors of NIHL were screened from these workers. BPNN and logistic regression models were constructed using these predictors.
RESULTS
The input variables of BPNN model were 20, 16 and 21 important factors screened by univariate, stepwise and lasso-logistic regression. When the BPNN model was applied to the test set, it was found to have a sensitivity (TPR) of 83.33%, a specificity (TNR) of 85.92%, an accuracy (ACC) of 85.51%, a positive predictive value (PPV) of 52.85%, a negative predictive value of 96.46% and area under the receiver operating curve (AUC) is: 0.926 (95% CI: 0.891 to 0.961), which demonstrated the better overall properties than univariate-logistic regression modelling (AUC: 0.715) (95% CI: 0.652 to 0.777). The BPNN model has better predictive performance against NIHL than the stepwise-logistic and lasso-logistic regression model in terms of TPR, TNR, ACC, PPV and NPV (p<0.05); the area under the receiver operating characteristics curve of NIHL is also higher than that of the stepwise and lasso-logistic regression model (p<0.05). It was a relatively important factor in NIHL to find cumulative noise exposure, auditory system symptoms, age, listening to music or watching video with headphones, exposure to high temperature and noise exposure time in the trained BPNN model.
CONCLUSIONS
The BPNN model was a valuable tool in dealing with the occupational risk prediction problem of NIHL. It can be used to predict the risk of an individual NIHL.
Collapse