Objective:To develop a deep learning-based system for real-time recognition and classification of portal hypertensive gastropathy (PHG) and evaluate its ability to assist junior endoscopists.Methods:A total of 2 848 gastroscopy images from 832 patients with liver cirrhosis were selected from Digestive Endoscopy Center databases of Renmin Hospital of Wuhan University, Wuhan Hospital of Traditional Chinese and Western Medicine, and the Second Hospital of Jingzhou from January 2015 to October 2023. This system referred to 3 endoscopic features of Baveno Ⅱ scoring system. Three models were developed respectively for gastric antral vascular ectasia (GAVE), mosaic-like pattern (MLP), and red marks (RM). The specific classification references were as follows: (1) GAVE model: 0 no, 1 yes; (2) MLP model: 0 no, 1 mild, 2 severe; (3) RM model: 0 no, 1 isolated, 2 fused. The classification results for endoscopic characteristics of PHG of 3 endoscopy experts were taken as the gold standard. The yolov8-m model was used for training. The training dataset, validation dataset, and test dataset were allocated at a ratio of 8∶1∶1. The test dataset was used to evaluate the performance of models and their auxiliary effects on endoscopists. The accuracy, recall, precision, specificity and Kappa coefficient were calculated. Results:The accuracy, recall, specificity of GAVE model were 96.0% (48/50), 87.5% (7/8) and 97.6% (41/42). There was no significant difference between its accuracy and the gold standard ( χ2=316.226, P=1.000). The precision of GAVE1 and GAVE0 were 87.5% (7/8) and 97.6% (41/42) respectively. The accuracy of MLP model was 84.1% (132/157), and there was no significant difference compared with the gold standard ( χ2=3.286, P=0.193). The precision and recall of MLP2 were 88.2% (15/17) and 75.0% (15/20). The precision and recall of MLP1 were 77.9% (60/77) and 88.2% (60/68). The precision and recall of MLP0 were 90.5% (57/63) and 82.6% (57/69). The accuracy of RM model was 87.9% (123/140), and there was no significant difference compared with the gold standard ( χ2=2.891, P=0.409). The precision and recall of RM2 were 94.7% (18/19) and 78.3% (18/23). The precision and recall of RM1 were 72.2% (26/36) and 81.3% (26/32). The precision and recall of RM0 were 92.9% (79/85) and 92.9% (79/85). The mean accuracy of the three junior endoscopists, with and without the assistance of the GAVE model, MLP model, and RM model, respectively increased from 95.3% to 99.3%, from 83.9% to 91.9%, and from 81.9% to 83.1%. The overall consistency analysis of the 3 junior endoscopists with the gold standard indicated that the consistency of the GAVE model before and after assistance was extremely strong (both an overall Kappa of 1.000); the consistency before assistance of the MLP model was moderate (with an overall Kappa of 0.601), which increased to extremely strong after assistance (with an overall Kappa of 0.964); and the consistency of the RM model before and after assistance was also relatively strong (with an overall Kappa of 0.792 before and 0.798 after). Conclusion:The deep learning system accurately identifies and classifies PHG features and significantly enhances diagnostic performance of junior endoscopists.

Objective:To develop a deep learning-based system for real-time recognition and classification of portal hypertensive gastropathy (PHG) and evaluate its ability to assist junior endoscopists.Methods:A total of 2 848 gastroscopy images from 832 patients with liver cirrhosis were selected from Digestive Endoscopy Center databases of Renmin Hospital of Wuhan University, Wuhan Hospital of Traditional Chinese and Western Medicine, and the Second Hospital of Jingzhou from January 2015 to October 2023. This system referred to 3 endoscopic features of Baveno Ⅱ scoring system. Three models were developed respectively for gastric antral vascular ectasia (GAVE), mosaic-like pattern (MLP), and red marks (RM). The specific classification references were as follows: (1) GAVE model: 0 no, 1 yes; (2) MLP model: 0 no, 1 mild, 2 severe; (3) RM model: 0 no, 1 isolated, 2 fused. The classification results for endoscopic characteristics of PHG of 3 endoscopy experts were taken as the gold standard. The yolov8-m model was used for training. The training dataset, validation dataset, and test dataset were allocated at a ratio of 8∶1∶1. The test dataset was used to evaluate the performance of models and their auxiliary effects on endoscopists. The accuracy, recall, precision, specificity and Kappa coefficient were calculated. Results:The accuracy, recall, specificity of GAVE model were 96.0% (48/50), 87.5% (7/8) and 97.6% (41/42). There was no significant difference between its accuracy and the gold standard ( χ2=316.226, P=1.000). The precision of GAVE1 and GAVE0 were 87.5% (7/8) and 97.6% (41/42) respectively. The accuracy of MLP model was 84.1% (132/157), and there was no significant difference compared with the gold standard ( χ2=3.286, P=0.193). The precision and recall of MLP2 were 88.2% (15/17) and 75.0% (15/20). The precision and recall of MLP1 were 77.9% (60/77) and 88.2% (60/68). The precision and recall of MLP0 were 90.5% (57/63) and 82.6% (57/69). The accuracy of RM model was 87.9% (123/140), and there was no significant difference compared with the gold standard ( χ2=2.891, P=0.409). The precision and recall of RM2 were 94.7% (18/19) and 78.3% (18/23). The precision and recall of RM1 were 72.2% (26/36) and 81.3% (26/32). The precision and recall of RM0 were 92.9% (79/85) and 92.9% (79/85). The mean accuracy of the three junior endoscopists, with and without the assistance of the GAVE model, MLP model, and RM model, respectively increased from 95.3% to 99.3%, from 83.9% to 91.9%, and from 81.9% to 83.1%. The overall consistency analysis of the 3 junior endoscopists with the gold standard indicated that the consistency of the GAVE model before and after assistance was extremely strong (both an overall Kappa of 1.000); the consistency before assistance of the MLP model was moderate (with an overall Kappa of 0.601), which increased to extremely strong after assistance (with an overall Kappa of 0.964); and the consistency of the RM model before and after assistance was also relatively strong (with an overall Kappa of 0.792 before and 0.798 after). Conclusion:The deep learning system accurately identifies and classifies PHG features and significantly enhances diagnostic performance of junior endoscopists.

Literature analysis,expert consultation,case analysis and other methods were used to establish a public hospital specialty operation evaluation system suitable for high-quality development,including 2 first-level indicators of medical ability and economic operation and 13 second-level indicators.Urology surgery in the pilot hospital was taken as an example to carry out surgical operation effect evaluation.To strengthen the evaluation of public hospital specialized operation,it should pay attention to the evaluation of medical capacity,strengthen the cooperation of functional departments,and improve the supporting policies of operation,for better promoting the development of high-quality operation of hospitals.

Hand osteoarthritis(HOA)is a disease of hand joint disorders,mainly manifested by hand interphalangeal joint and thumb carpal metacarpal joint pain,swelling,morning stiffness,limited movement,and even deformity,belonging to the category of TCM"bone arthralgia".The authors believe that HOA is more common with Taiyang Shaoyang disease,suitable for simultaneous treatment for Taiyang and Shaoyang,to operate the cardinal,regulate qi,blood,nutritive and defensive levels,dispel wind and cold,remove dampness and arthralgia,using modified Chaihu Guizhi Decoction,with confirmed efficacy.

Lumbar disc herniation is mainly manifested as lower back pain,numbness,weakness,and radiating pain in the lower limbs,which seriously affects the patients'work and quality of life.In clinical practice,it has been found that this disease always belongs to the category of deficiency in healthy qi and excess in pathogenic factors,often accompanied by kidney deficiency and cold dampness.Kidney deficiency is the root cause,while cold dampness is the symptoms.The two factors interact with each other and cause back pain.The treatment is based on dispersing cold and dampness,tonifying the kidneys and strengthening the waist,and the classic ancient formula Shenzhuo Powder is safe and effective.

Objective:To investigate the clinical effect of focused ultrasound ablation surgery (FUAS) combined with suction curettage for mass-type cesarean scar pregnancy (CSP) and to analyze the influencing factors of vaginal bleeding and readmission.Methods:From January 2014 to December 2020, 88 patients with mass-type CSP were treated by FUAS combined with suction curettage in the Third Xiangya Hospital of Central South University. The clinical results and the influencing factors of bleeding and readmission for mass-type CSP were analyzed.Results:All the patients underwent one time FUAS treatment successfully. Immediately after FUAS treatment, color Doppler ultrasound showed obvious necrosis and no perfusion area in all lesions, and the blood flow in the mass-type CSP tissue significantly decreased. The median volume of blood loss in the procedure was 20 ml (range: 5-950 ml). Thirteen patients (15%, 13/88) had vaginal bleeding≥200 ml, and 15 patients (17%, 15/88) were hospitalized again. The average time for menstruation recovery was (28±8) days (range: 18-66 days). The average time needed for serum human chorionic gonadotropin-beta subunit to return to normal levels was (22±6) days (range: 7-59 days). The risk of large vaginal bleeding of patients were related to the blood supply of the mass ( OR=5.280, 95% CI: 1.335-20.858, P=0.018) and the largest diameter of the mass ( OR=1.060, 95% CI: 1.010-1.120, P=0.030). The risk of readmission were related to the largest diameter of the mass ( OR=1.055, 95% CI: 1.005-1.108, P=0.030) and the depth of the uterus cavity ( OR=1.583, 95% CI: 1.015-2.471, P=0.043). No serious complications such as intestinal and nerve injury occurred during and after FUAS treatment. Conclusions:FUAS combined with suction curettage is safe and effective in treating patients with mass-type CSP through this preliminary study. The volume of vaginal bleeding are associated with the blood supply of the mass and the largest diameter of the mass, the risk of readmission are related to the largest diameter of the mass and the depth of the uterus cavity.

Present study aimed to investigate the eff ect of curcumin-pretreatment on intestinal I/R injury and on intestinal mucosa barrier. Thirty Wistar rats were randomly divided into: sham, I/R, and curcumin groups (n=10). Animals in curcumin group were pretreated with curcumin by gastric gavage (200 mg/kg) for 2 days before I/R. Small intestine tissues were prepared for Haematoxylin & Eosin (H&E) staining. Serum diamine oxidase (DAO) and tumor necrosis factor (TNF)-alpha levels were measured. Expression of intestinal TNF-alpha and tight junction protein (ZO-1) proteins was detected by Western blot and/or immunohistochemistry. Serum DAO level and serum and intestinal TNF-alpha leves were signifi cantly increased after I/R, and the values were markedly reduced by curcumin pretreatment although still higher than that of sham group (p<0.05 or p<0.001). H&E staining showed the significant injury to intestinal mucosa following I/R, and curcumin pretreatment signifi cantly improved the histological structure of intestinal mucosa. I/R insult also induced significantly down-regulated expression of ZO-1, and the eff ect was dramatically attenuated by curcumin-pretreatment. Curcumin may protect the intestine from I/R injury through restoration of the epithelial structure, promotion of the recovery of intestinal permeability, as well as enhancement of ZO-1 protein expression, and this eff ect may be partly attributed to the TNF-alpha related pathway.
Amine Oxidase (Copper-Containing) ; Animals ; Blotting, Western ; Curcumin* ; Eosine Yellowish-(YS) ; Immunohistochemistry ; Intestinal Mucosa ; Intestine, Small ; Intestines ; Permeability ; Rats, Wistar ; Reperfusion Injury* ; Tight Junctions* ; Tumor Necrosis Factor-alpha* ; Zonula Occludens-1 Protein*

OBJECTIVETo establish a prognostic model for predicting extracorporeal circulation clotting in patients with continuous renal replacement therapy (CRRT).

METHODS425 patients with CRRT were involved in the study. We built a predictive risk model of extracorporeal blood clotting with the 302 participants, and 103 participants were used to validate the model. The primary endpoint of CRRT was extracorporeal circulation pipe blockage.

RESULTSWe used a score of 0-5 point evaluating system to predict the risk of 24 hours CRRT integral model of cardiopulmonary bypass clogging. The area under the CRRT predictive model of cardiopulmonary bypass clogging integral system ROC curve was 0.790 (95% CI 0.719-0.826) (P<0.001). The evaluating system can determine the blockage of 24 hours CRRT extracorporeal circulation. The results showed that CRRT extracorporeal plugging prediction fitted the integral model and could predict the chance of plugging. The actual plugging rate showed no significant difference from the predicted rate (R² = 0.301, P=0.232). The cardiopulmonary pipe survival time between the 3 groups(low risk, intermediate risk, and high risk) showed a significant difference (P<0.05).

CONCLUSIONWe established a continuity extracorporeal blood purification plugging risk score model, to predict plugging risks during CRRT treatment.

Objective To establish a prognostic model for predicting extracorporeal circulation clotting in patients with continuous renal replacement therapy(CRRT). Methods 425 patients with CRRT were involved in the study. We built a predictive risk model of extracorporeal blood clotting with the 302 participants, and 103 participants were used to validate the model. The primary endpoint of CRRT was extracorporeal circulation pipe blockage. Results We used a score of 0-5 point evaluating system to predict the risk of 24 hours CRRT integral model of cardiopulmonary bypass clogging. The area under the CRRT predictive model of cardiopulmonary bypass clogging integral system ROC curve was 0.790 (95%CI 0.719-0.826)(P<0.001). The evaluating system can determine the blockage of 24 hours CRRT extracorporeal circulation. The results showed that CRRT extracorporeal plugging prediction fitted the integral model and could predict the chance of plugging. The actual plugging rate showed no significant difference from the predicted rate (R2=0.301, P=0.232). The cardiopulmonary pipe survival time between the 3 groups(low risk, intermediate risk, and high risk) showed a significant difference (P<0.05). Conclusion We established a continuity extracorporeal blood purification plugging risk score model, to predict plugging risks during CRRT treatment.