RESUMO
ObjectiveTo explore the relationship between the occupational noise exposure and arteriosclerosis in mechanical manufacturing workers. Methods A total of 453 employees of a machinery manufacturing enterprise were selected as the study subjects using the judgment sampling method. The noise exposure levels in their workplaces were measured, and their cumulative noise exposure (CNE) was assessed based on the type of job-noise exposure matrix and occupational hazard exposure history. Pure-tone audiometry was performed on the research subjects, and their brachial-ankle pulse wave velocity (baPWV) was measured. Results The CNE was (91±11) dB(A) per year and the median baPWV was 1 278.0 cm/s in the research subjects. The results of the generalized linear regression model analysis showed that for every one dB(A) per year increase in CNE, the baPWV of the general population increased by 0.20% ［95% confidence interval (CI) 0.10%-0.30%, P<0.01］, with an increase of 0.17% in males (95%CI 0.06%-0.28%, P<0.01) and 0.28% in females (95%CI 0.07%-0.49%, P<0.01). Using the hearing loss as an outcome indicator for high intensity noise exposure, the results showed that baPWV increased by 7.04% (95%CI 2.42%-11.87%, P<0.01) in individuals with bilateral hearing loss, and by 9.84% and 6.53% (95%CI 3.07%-17.07% and 2.13%-11.11%, all P<0.01) in individuals with elevated high-frequency hearing thresholds in both ears and in either ear, respectively. There was no significant association in elevated speech-frequency hearing thresholds and arteriosclerosis (P>0.05). Conclusion Occupational noise exposure may increase the risk of arteriosclerosis.
RESUMO
Objective:To realize the accurate prediction of the fall risk of the elderly by a convolutional neural network prediction model.Methods:Stratified random cluster sampling was used from June 2019 to February 2020, Python′s Matlabplot library and Opencv library were used to perform data preprocessing on the plantar pressure data of 1 093 subjects who had come from medical institutionsand community or elderly care institutions of Chongqing and Nanjing, such as data visualization, compression and clipping, grayscale, Gaussian blur, etc., and then the data were divided into training set (983 cases) and verification set (110 cases), the training set data were used to train the convolutional neural network model, the verification set was used to verify the model, and the ReLU function was used to suppress overfitting to obtain the final prediction model.Results:The sensitivity of the fall warning model to the validation set for predicting falls was 91.2%, the specificity was 81.4%, the accuracy was 91.5%, and the AUC was 0.865.Conclusions:The fall prediction model can predict the fall risk of the elderly in a specific scenario. In the subsequent improvement, the software and hardware construction should be comprehensively improved to further improve the prediction accuracy.