Objective:To develop a deep learning model based on super-resolution endorectal ultrasound（ERUS）images for the preoperative prediction of perineural invasion（PNI）in patients with rectal cancer，thereby providing a reference for risk stratification and individualized treatment planning.Methods:A retrospective analysis was conducted on 382 patients with rectal cancer who underwent total mesorectal excision at Fujian Medical University Union Hospital between June 2019 and February 2024. Patients were randomly divided into a training set（ n=305）and a test set（ n=77）at a ratio of 8∶2，and further grouped into PNI-negative group and PNI-positive group subgroups based on pathological results. Super-resolution ultrasound images were generated from original ERUS images using a generative adversarial network（GAN）. Deep convolutional neural networks were developed based on features from intratumoral and peritumoral regions to identify the optimal region of interest（ROI）. The dSR5_ResNet18 and dSR5_ResNet50 models were constructed using the super-resolution images with a 5-pixel peritumoral extension. Representative clinical features were selected for subgroup analysis based on sample size and intergroup statistical differences between PNI-positive and PNI-negative patients. Forest plots were used to evaluate model applicability and robustness across subgroups. Results:The dSR5_ResNet18 model，built using super-resolution images of the tumor combined with a 5-pixel peritumoral region，achieved the best predictive performance，with an AUC of 0.867（95% CI=0.782 - 0.952）in the test set. Decision curve analysis demonstrated that the dSR5_ResNet18 model provided the greatest net clinical benefit. Forest plot analysis indicated strong generalizability of the models across subgroups such as pathological N stage，maximum lesion length，and lymph node enlargement，though relatively weaker performance was observed in the carcinoembryonic antigen（CEA）subgroup. Among all models，dSR5_ResNet18 exhibited the most consistent performance across subgroups，with the narrowest confidence intervals and highest robustness. Conclusions:The deep learning model incorporating ERUS-based super-resolution reconstruction demonstrated excellent performance in the preoperative prediction of PNI in rectal cancer. It offers significant advantages in image quality and generalizability，and may serve as a valuable tool to assist clinicians in formulating personalized treatment strategies.

Objective:To investigate the present situation and influencing factors of hearing loss among noise exposed workers in a gas production plant, and to provide basis and guidance for enterprises to prevent hearing loss.Methods:In November 2023, a cross-sectional survey was conducted among personnel exposed to noise in a gas production plant. A total of 380 questionnaires were collected, among which 319 were valid resulting in an effective recovery rate of 83.9%. Ultimately, 292 were included in the study. The questionnaire covered demographic characteristics, work conditions, behavioral and lifestyle habits, hearing loss, and medical history. The noise exposure levels of the research subjects were determined based on the occupational disease hazard factor detection reports provided by the gas production plant for 2022 and 2023. Whether hearing loss occurred was determined based on the pure tone audiometry results from the occupational health examination. Chi-square tests were used to analyze the influence of demographic characteristics, work conditions, and behavioral and lifestyle habits on hearing loss. A multivariate logistic regression model was used to analyze the relationship between hearing loss and related influencing factors.Results:Among the noise-exposed workers in the gas production plant, the incidence of high-frequency hearing loss was 14.4% (42/292) . The rate of hearing loss among men was higher than that among women ( P=0.010) , and the rate of hearing loss among those with a history of smoking was higher than that among those who had never smoked ( P=0.015) . Conclusion:Gas production enterprises should prioritize targeted interventions for workers with prolonged employment histories and smoking habits. Training programs should be implemented to cultivate proper ear protection practices, enhance knowledge of hearing conservation, and promote healthier lifestyle behaviors among employees.

Objective:To develop a deep learning model based on super-resolution endorectal ultrasound（ERUS）images for the preoperative prediction of perineural invasion（PNI）in patients with rectal cancer，thereby providing a reference for risk stratification and individualized treatment planning.Methods:A retrospective analysis was conducted on 382 patients with rectal cancer who underwent total mesorectal excision at Fujian Medical University Union Hospital between June 2019 and February 2024. Patients were randomly divided into a training set（ n=305）and a test set（ n=77）at a ratio of 8∶2，and further grouped into PNI-negative group and PNI-positive group subgroups based on pathological results. Super-resolution ultrasound images were generated from original ERUS images using a generative adversarial network（GAN）. Deep convolutional neural networks were developed based on features from intratumoral and peritumoral regions to identify the optimal region of interest（ROI）. The dSR5_ResNet18 and dSR5_ResNet50 models were constructed using the super-resolution images with a 5-pixel peritumoral extension. Representative clinical features were selected for subgroup analysis based on sample size and intergroup statistical differences between PNI-positive and PNI-negative patients. Forest plots were used to evaluate model applicability and robustness across subgroups. Results:The dSR5_ResNet18 model，built using super-resolution images of the tumor combined with a 5-pixel peritumoral region，achieved the best predictive performance，with an AUC of 0.867（95% CI=0.782 - 0.952）in the test set. Decision curve analysis demonstrated that the dSR5_ResNet18 model provided the greatest net clinical benefit. Forest plot analysis indicated strong generalizability of the models across subgroups such as pathological N stage，maximum lesion length，and lymph node enlargement，though relatively weaker performance was observed in the carcinoembryonic antigen（CEA）subgroup. Among all models，dSR5_ResNet18 exhibited the most consistent performance across subgroups，with the narrowest confidence intervals and highest robustness. Conclusions:The deep learning model incorporating ERUS-based super-resolution reconstruction demonstrated excellent performance in the preoperative prediction of PNI in rectal cancer. It offers significant advantages in image quality and generalizability，and may serve as a valuable tool to assist clinicians in formulating personalized treatment strategies.

Objective:To investigate the present situation and influencing factors of hearing loss among noise exposed workers in a gas production plant, and to provide basis and guidance for enterprises to prevent hearing loss.Methods:In November 2023, a cross-sectional survey was conducted among personnel exposed to noise in a gas production plant. A total of 380 questionnaires were collected, among which 319 were valid resulting in an effective recovery rate of 83.9%. Ultimately, 292 were included in the study. The questionnaire covered demographic characteristics, work conditions, behavioral and lifestyle habits, hearing loss, and medical history. The noise exposure levels of the research subjects were determined based on the occupational disease hazard factor detection reports provided by the gas production plant for 2022 and 2023. Whether hearing loss occurred was determined based on the pure tone audiometry results from the occupational health examination. Chi-square tests were used to analyze the influence of demographic characteristics, work conditions, and behavioral and lifestyle habits on hearing loss. A multivariate logistic regression model was used to analyze the relationship between hearing loss and related influencing factors.Results:Among the noise-exposed workers in the gas production plant, the incidence of high-frequency hearing loss was 14.4% (42/292) . The rate of hearing loss among men was higher than that among women ( P=0.010) , and the rate of hearing loss among those with a history of smoking was higher than that among those who had never smoked ( P=0.015) . Conclusion:Gas production enterprises should prioritize targeted interventions for workers with prolonged employment histories and smoking habits. Training programs should be implemented to cultivate proper ear protection practices, enhance knowledge of hearing conservation, and promote healthier lifestyle behaviors among employees.

Objective:To investigate the prevalence of pre-diabetes mellitus (PDM) and the impact of occupation-related factors on PDM, among workers from a steel company in Tangshan city, Hebei province.Methods:Clustering sampling method was used to select a steel company and to carry out occupational health-related physical checkup programs for eligible workers who had working in this company for longer than one year. The study began in February and ended up in June, 2017. Workers who were with FPG level as ≤6.9 mmol/L, and free from diabetes, were selected as the subjects for this study. Questionnaires were used and physical examinations and FPG testing conducted.Results:The total number of subjects in this study was 4 173, of which 2 648 appeared as pre-diabetic, with the prevalence rate as 63.4 %. Increase of the PDM prevalence was in parallel with the length of service, among the workers. The risk for the pre-diabetes in those who worked more than 8 hours per day was 1.696 times higher than those who worked less than or equal to 8 h/d (95 %CI:1.517-1.937). Compared with those workers without exposures to heat, noise or carbon monoxides, the proportion of pre-diabetes appeared higher in workers exposed to heat, noise or CO with OR=1.782 (95 %CI: 1.205-2.636), 1.815 (95 %CI: 1.209-2.794) and 1.653 (95 %CI: 1.158-2.361), respectively. Risks for those who were exposed to heat or noise were higher than those who were free from exposure to any occupational hazards ( OR=2.098, 95 %CI: 1.296-3.397). Prevalence rates of pre-diabetes in those who were exposed to heat, noise or CO, were higher than that those who were not. Conclusion:Working hours and exposures to heat, noise or CO appeared as influential factors on PDM.

Objective:To investigate the effect of occupational factor exposures on carotid atherosclerosis (CAS) in steel workers.Methods:A frequency matched case-control study was conducted by age and factory proportion. A total of 1 033 workers with carotid atherosclerosis diagnosed by ultrasonography examination from February to June 2017 were selected as case group, and 1 033 workers without carotid atherosclerosis indicated by physical examination at the same time were selected as control group. The basic information of the workers, such as diet pattern, lifestyle, serum biochemical index and occupation history, were collected. The effects of occupational hazards on carotid atherosclerosis were analyzed by univariate and multivariate logistic regression analyses. The combined effects of various occupational hazards on carotid atherosclerosis were evaluated by environmental risk score (ERS).Results:High temperature, noise, occupational stress and night shift days increased the risk of CAS. With the increase of cumulative high temperature and noise exposure, occupational stress and night shift days, the risk of CAS increased (trend text: χ2=37.53, P<0.01; χ2=16.98, P<0.01; χ2=13.93, P<0.01; χ2=5.59, P<0.05). After adjustment of covariates, compared with P 20 group, the risk of carotid artery in P 40, P 60, P 80 and P 100 groups were as follows: high temperature 1.61 (1.19-2.18), 1.69 (1.25-2.30), 1.84 (1.36-2.49), 2.43 (1.77-3.34); noise 1.70 (1.15-2.52), 1.68 (1.20-2.35), 1.80 (1.34-2.42), 2.23 (1.53-3.26); occupational stress 1.39 (1.04- 1.86), 1.41 (1.06-1.89), 1.45(1.09-1.95), 1.48 (1.10-1.98); night shift days 1.58 (1.08-2.33), 1.66 (1.12-2.47), 1.55 (1.04-2.31), 1.76 (1.17-2.64). The results of the environmental risk score showed that the risk of carotid atherosclerosis increased with the increase of ERS (ERS trend text χ2=51.61, P<0.01); RCS results showed that there was a linear relationship between ERS and CAS in steel workers( P<0.01). Linear dose-response relationship existed between ERS and CAS (nonlinear test P>0.05). Conclusions:High temperature, noise, occupational stress and night shift days were related to carotid atherosclerosis. Linear dose-response relationship existed between ERS and CAS in steel workers.

OBJECTIVE: To explore the effects of cumulative noise exposure(CNE) on the intima-media thickness(IMT) of carotid artery in steel workers. METHODS: A cluster random sampling method was used to select 1 437 noise exposed workers in a steel company as study subjects. The CNE was calculated according to the noise intensity of the workplace, and the occupational health check was carried out to construct the structural equation model of noise to IMT. RESULTS: The detection rate of carotid atherosclerosis(CAS) in these 1 437 subjects was 38.3%. The CAS detection rates of steel workers increased with the increasing CNE(P<0.01). The structural equation model had good fitting effect. Path analysis showed CNE can indirectly affect IMT through blood pressure, triglycerides, fasting blood glucose, homocysteine, high-density lipoprotein & apolipoprotein A, low-density lipoprotein & apolipoprotein B. The total effects were-0.375, 0.337, 0.248, 0.117, 0.056, 0.056 and 0.018 respectively. CONCLUSION: CNE can indirectly increase the IMT of steel workers by acting on the proximal cause.

OBJECTIVE: To explore the effect of occupational high temperature exposure on type 2 diabetes( T2 DM) in male steel workers. METHODS: A cluster random sampling method was used to select 684 male steel workers,who exposed to occupational high temperature in a steel enterprise in Tangshan City,as the high temperature group,and 1 153 male steel workers without occupational high temperature exposure as the control group. The high temperature level of workers in these two groups was measured. The cumulative exposure( CE) of high temperature was calculated,and occupational health exam was performed. The multivariate logistic regression analysis and restricted cubic splines were used to analyze the relationship between high temperature CE and T2 DM. RESULTS: The prevalence of T2 DM in high-temperature group was higher than that in the control group( 13. 0% vs 7. 9%,P < 0. 05). The multivariate logistic regression analysis results showed that the risk of T2 DM in the high temperature group was higher than that in the control group after adjusting for age,body mass index,smoking,drinking,physical exercise and parents with diabetes( P < 0. 05). The 95% confidence interval was 1. 65( 1. 17-2. 33). Restricted cubic spline analysis showed that the high temperature CE was correlated with the prevalence of T2 DM in workers( P < 0. 01) and showed a linear correlation( nonlinearity test,P > 0. 05). CONCLUSION: Occupational high temperature exposure is associated with the occurrence of T2 DM in male steel workers. The male steel workers with high temperature CE show high prevalence of T2 DM risk.