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.

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.

Global burden and trends of three common road injuries from 1990 to 2019 and the implications for prevention and intervention.

BACKGROUND: Analysis on the burden of specific types of road injuries (RIs) in the previous Global burden of disease (GBD) studies is lacking. The present work aimed to analyze the burden of three common RIs using the updated data of the GBD 2019, which would inform policy-making. METHODS: Data on cyclist road injuries (CRIs), motorcyclist road injuries (MRIs), and motor vehicle road injuries (MVRIs) were extracted from the GBD 2019. Trends of age-standardized rate (ASR) were predicted using estimated annual percentage change (EAPC) from 1990 to 2019. RESULTS: Over the past three decades, the global incident ASRs of CRIs and MRIs presented increasing trends, but that of MVRIs declined slightly. However, trends of death and disability adjusted life years (DALYs) caused by three common RIs decreased in most regions and countries. Particularly, trends in ASRs of years of life lost (YLLs) cuased by RIs decreased more pronouncedly than that of years of life lived with disability (YLDs). The burden of three common RIs showed significant social and demographic characteristics. Low-middle and middle socio-demographic index (SDI) areas had a heavy burden of RIs, particularly CRIs and MRIs. However, the high SDI area undertook a relatively low burden, and presented more pronounced downward trends in death and DALYs. CONCLUSIONS: The burden and changing trends of three common RIs were geographically heterogeneous. The findings highlighted that increasing incident trends of RIs needed more cost-effective measures of prevention and intervention.

Role of CASP7 polymorphisms in noise-induced hearing loss risk in Han Chinese population.

Genetic factors and gene-environment interaction may play an important role in the development of noise induced hearing loss (NIHL). 191 cases and 191 controls were selected by case-control study. Among them, case groups were screened from workers exposed to noise in binaural high-frequency hearing thresholds greater than 25 dB (A). Workers with hearing thresholds ≤ 25 dB (A) in any binaural frequency band were selected to the control group, based on matching factors such as age, exposure time to noise, and operating position. The blood samples from two groups of workers were subjected to DNA extraction and SNP sequencing of CASP3 and CASP7 genes using the polymerase chain reaction ligase detection reaction method. Conditional logistic regression correction was used to analyze the genetic variation associated with susceptibility to NIHL. There was an association between rs2227310 and rs4353229 of the CASP7 gene and the risk of NIHL. Compared with the GG genotype, the CC genotype of rs2227310 reduced the risk of NIHL. Compared with CC genotype, the TT genotype of rs4353229 reduced the risk of NIHL. Workers carrying the rs2227310GG and rs4353229CC genotype had an increased risk of NIHL compared to workers without any high-risk genotype. There were additive interaction and multiplication interaction between CASP7rs2227310 and CNE, and the same interaction between CASP7rs4353229 and CNE. The interaction between the CASP7 gene and CNE significantly increased the risk of NIHL. The genetic polymorphisms of CASP7rs2227310GG and CASP7rs4353229CC were associated with an increased risk of NIHL in Han Chinese population and have the potential to act as biomarkers for noise-exposed workers.