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 analyze the clinical characteristics and prognostic risk factors of esophageal signet ring cell carcinoma(SRCC)patients and construct a column chart prediction model.Methods The training queue consists of 226 patients diagnosed with esophageal SRCC from 2010 to 2017 in the SEER database,and the validation queue consists of 21 patients diagnosed with esophageal SRCC in our hospital from January 2010 to January 2019.Use Cox proportional risk regression model for single factor and multivariate analysis.Use the"rms"software package of R software to generate column charts.Results Univariate analysis showed that age,gender,tumor location,local invasion,lymph node metastasis,distant metastasis,surgical treatment,chemotherapy,and radiotherapy were risk factors affecting the prognosis of SRCC patients(P＜0.05);In multivariate cox regression analysis,the results showed that tumor location,local invasion,lymph node metastasis,distant metastasis,surgical treatment,chemotherapy,and radiotherapy were independent risk factors affecting the prognosis of SRCC patients(P＜0.05);A nomogram prediction model was successfully constructed using multivariate cox regression analysis,with a certain degree of predictive accuracy.Conclusion The nomogram prediction model was successfully constructed based on the risk factors affecting the prognosis of esophageal signet ring cell adenocarcinoma patients in the SEER database,which can provide more accurate predictions for the prognosis of esophageal SRCC patients.

Pancreatogenic diabetes is a type of diabetes mellitus secondary to exocrine pancreatic disease,and it was officially proposed by the American Diabetes Association in 2014,with chronic pancreatitis as the most common etiology,followed by pancreatic cancer.At present,the misdiagnosis rate of this disease is extremely high,and patients with pancreatogenic diabetes have a higher risk of death and readmission than patients with type 2 diabetes.Therefore,it is of great significance to fully understand,correctly identify,and diagnose pancreatogenic diabetes in the early state,so as to reduce the disability rate and mortality rate of this disease.This article reviews the advances in the possible pathogenesis,diagnosis,treatment,and management of pancreatic diabetes secondary to pancreatitis and pancreatic cancer.

Objective:Applying bibliometrics to analyze the research history, hotspots and trends of Traditional Chinese Medicine (TCM) interventions in edema-related diseases, and to provide reference for the revision of diagnostic and therapeutic criteria for edema in TCM.Methods:The literature about edema treated with TCM was retrieved from CNKI, Wanfang, VIP, CBM from 1 st. Jan 1995 to 25 th. May 2022. CiteSpace and VOSviewer softwares were used to draw the knowledge map, and analyze the co-occurrence relationship and clustering characteristics of the institution, author, keywords and mechanism hotspots. Results:Totally 3 198 articles were included. The annual number of documents issued generally shows a spiral rise trend. Liaoning University of Chinese Medicine published the most articles. Core authors published the most articles were Sun Wei (13 articles); the team with the highest cooperation intensity was Yang Hongtao's team; keywords formed 7 clusters. Hotspot mechanisms included metabolic disorders, immune balance, anti-inflammation, calcium and phosphorus metabolism. Keywords in the past 7 years were membranous nephropathy, chronic heart failure, diabetes, lymphedema etc.Conclusions:The attention paid to the intervention of TCM in the field of edema is generally on the rise, and has decreased in the past two years. The research categories focus on the experience of famous doctors, clinical trials, and mechanistic studies, and nephropathy-related edema has been the focus of research; diabetic nephropathy, chronic heart failure, metabolomics, and immunotherapy are expected to be the focus of attention in the next stage.

Objective:To analyze the efficacy evaluation criteria of the existing TCM treatment for edema RCT research, and to provide reference for the construction of unified standards.Methods:The batabases CNKI, WanFang Data, VIP, CBM, Pubmed and Web of Science were retrieved. The randomized controlled trials for the treatment of edema of TCM research, from September 1, 1993 to July 31, 2022, were screened and included. The content of efficacy evaluation, performed statistics on evaluation standard, the curative effect evaluation indexes, as well as standard composition, usage were extracted. We analyzed the characteristics, application and problems of the existing efficacy evaluation criterion.Results:A total of 123 Chinese articles were included. The included literature involved nephrogenic edema, cardiogenic edema, idiopathic edema, apoplexy limb edema and other edema. In recent years, randomized controlled trials on the treatment of edema by TCM have mainly used four efficacy evaluation criteria. Of which the Guidelines for Clinical Research on New Chinese Medicines (Trial) in 2002 had the highest utilization rate of 29.27%. Secondly, the utilization rate of Standard for Diagnosis and Curative Effect of TCM Diseases and Syndromes was 21.14%. The rest of the criteria were used by less than 6%. While 39.02% of the literature did not use the standards or used self-designed standards. Among the composition of efficacy evaluation indices, the application rate of TCM syndrome or symptom efficacy index was the highest (91.87%), the utilization rate of the Minnesota Living with Heart Failure Questionnaire Indicators was only 4.88%; biochemical tests accounted for a large proportion of Western medical indicators, while the measurement of edema severity was rarely applied. Conclusions:At present, the evaluation criteria of edema curative effect are diversified and insufficiently popularized, which need to be further screened and improved. It is suggested to construct a TCM edema efficacy evaluation model based on the characteristics of edema syndrome, comprehensively evaluate the efficacy from multiple dimensions such as TCM syndromes, western medicine indicators, and quality of life, and improve the scientific indicators.

Objective : To investigate the clinical efficacy and application value of an improved 3D-printed guide plate for the treatment of primary trigeminal neuralgia (PTN) by percutaneous microballoon compression (PMC). Methods : This prospective study included 42 patients with primary trigeminal neuralgia treated at the Department of Stomatology, Xuzhou Central Hospital, from September 2019 to January 2022. The group was divided by the random number table method into the experimental group (adopting 3D printing technology to make guide plates to guide the puncture, 22 cases) and the control group (adopting the traditional Hartel anterior approach to position the puncture, 20 cases). The intraoperative success rate of the first puncture, puncture time, operative time, radiation exposure of patients and postoperative complications were compared between the two groups. Postoperative Barrow Neurological Institute Scale (BNI) scores, facial numbness, diminished corneal reflexes and chewing weakness were recorded. The t-test, rank-sum test and chi-square test were used for statistical analysis, with P<0.05 indicating a statistically significant difference. Results : The experimental group was significantly better than the control group in terms of the success rate of the first puncture (χ2 = 21.51, P<0.001), puncture time (Z = -5.51, P<0.001), operative time (t = 9.37, P<0.001), and the number of C-arm scans (Z = -4.59, P<0.001). Postoperative BNI scores of the experimental group included 21 cases of grade Ⅰ (91.5%) and 1 case of grade Ⅱ, while the control group included 17 cases of grade Ⅰ (85.0%), 2 cases of grade Ⅱ (10.0%) and 1 case of grade Ⅲ (5.0%), with no statistical significance (P>0.05). In the experimental group, 16 patients had postoperative masseter weakness, 1 had keratitis and 10 had perilabial herpes, while in the control group, 18 patients had postoperative masseter weakness, 2 had keratitis, 11 had perilabial herpes and 1 had monocular blindness. There was no significant difference in postoperative complications between the two groups (P>0.05). At 12 months of follow-up, there was no recurrence in either the experimental or control group. Conclusions 3D digital guide plate-guided percutaneous microballoon compression for primary trigeminal neuralgia can improve the accuracy and safety of puncture to a certain extent, obviously shorten the operation time, reduce radiation exposure of the patients, improve the success rate of the operation, meaning it has a high clinical application value.

Objective : investigate the correlation between the ossification of the styloid hyoid ligament and Bell’s facial paralysis and provide a reference for clinical diagnosis and treatment. Methods: A case of ossification of the bilateral stylohyoid ligament with Bell's facial palsy caused by ossification of the bilateral stylohyoid ligament was diagnosed by clinical manifestations, differential diagnosis and imaging examination. The surgical plan was determined, and combined surgical resection of the ossified area of the styloid hyoid ligament and the greater horn of the hyoid was performed. Postoperative cefoxitin sodium anti-inflammatory treatment, methylprednisolone hormone treatment, acyclovir antiviral treatment, mecobalamin nutritional neurotherapy, and the relevant literature were analyzed. Results: The patient experienced pain when swallowing before surgery, disappearance of right frontal ridges, incomplete eyelid closure, and ptosis of mouth corners. An MRI scan of the brain excluded intracranial space-occupying lesions and resulted in the diagnosis of Bell’s facial paralysis. High-resolution CT of the styloid process confirmed ossification of the styloid hyoid ligament. Styloid process shortening and partial hyoid resection were performed under general anesthesia. Half a month after discharge, the symptoms of sore throat and pain in swallowing disappeared, facial nerve function recovered well, right eyelid closure function recovered well, and right mouth droop improved. The facial nerve function basically returned to normal after 1 month of follow-up. A review of the relevant literature showed that ossification of the stylohyoid ligament to form pseudojoint dilation can locally stimulate the peripheral facial nerve and lead to facial paralysis symptoms. Conclusion Ossification of the styloid hyoid ligament is usually characterized by pharyngeal pain, which can be confirmed by imaging examination. Ossification of the styloid hyoid ligament with facial paralysis is rare in the clinic, so it is necessary to make a clear diagnosis and treat the symptoms.