Objective To propose a novel method based on three-dimensional depthwise separable convolution network(3D DSN)for the separation of PET images with dual tracers of 18F-FDG and 18F-FAPI.Methods A total of 120 pairs of 18F-FDG and 18F-FAPI PET images of the same patient scanned separately at different time points were collected,and the dual-tracer PET image was generated through simulation.After the image registration of PET images of two tracers for ensuring spatial position matching,the registered PET images were forward-projected to generate sinogram data,and the sinogram data of two tracers were accumulated to obtain mixed sinogram data.Subsequently,the dual-tracer PET image was reconstructed using maximum likelihood expectation maximization and input into a 3D DSN based network for image separation,thereby obtaining PET images of two single tracers.Results Compared with 3D CNN method,the proposed method increased the structure similarity index measure(SSIM)of the separated 18F-FDG images to the real 18F-FDG images by 0.87%,increased the peak signal-to-noise ratio(PSNR)by 11.8%,and reduced the normalized root mean square error(NRMSE)by 52%.The SSIM of the separated 18F-FAPI images to the real 18F-FAPI images increased by 1.1%,PSNR increased by 17.0%,and NRMSE decreased by 51%.Conclusion The proposed method can be effectively applied to simultaneous PET imaging with dual PET tracers,reducing the number of scans and costs in time and money,and providing clinical doctors more accurate and abundant diagnostic information.

Objective To develop a knowledge-attitude-practice assessment scale for home prevention and man-agement of parastostomy hernia in ostomy patients,and to test its reliability and validity,to provide a reliable tool for evaluating the knowledge and practice level of home prevention and management of parastostomy hernia in pa-tients with ostomy.Methods Based on the theory of knowledge,attitude and practice,the initial scale was generat-ed through literature review,semi-structured interviews,expert correspondence,research group discussion and pre-sur-vey.From May to December 2023,685 patients with ostomy from the ostomy clinic of a tertiary hospital in Tianjin were investigated by purpose sampling method,and the reliability and validity were tested.Results A total of 673 valid questionnaires were collected,the results showed that the knowledge-attitude-practice assessment scale for pre-venting and managing parastomal hernia of ostomy patients at home included 3 dimensions of knowledge,attitude and practice,with a total of 27 items.The response rates of 2 rounds of the questionnaire were both 100％;the au-thority coefficients were all 0.915;the Kendall's coefficients of concordance were 0.279 and 0.301,respectively.The content validity index of each item was 0.875～1.000;the content validity index of the average scale level was 0.988;after 2 exploratory factor analysis,the cumulative variance contribution rate was 65.920％.The results of con-firmatory factor analysis showed that the model had a good fit,with a chi-square degree of freedom ratio(/df)of 1.945,the fitting goodness index(GFI)of 0.851,the comparative goodness of fit index(CFI)of 0.919,the root means square error of approximation(RMSEA)of 0.060.The Cronbach's alpha coefficient result of the scale is 0.957,with a test-retest reliability of 0.826 and a half reliability of 0.934.Conclusion The knowledge-attitude-practice assessment scale has good reliability and validity,and can be used as an assessment tool for home prevention and management of parastostomy hernia in ostomy patients.

Objective To develop a knowledge-attitude-practice assessment scale for home prevention and man-agement of parastostomy hernia in ostomy patients,and to test its reliability and validity,to provide a reliable tool for evaluating the knowledge and practice level of home prevention and management of parastostomy hernia in pa-tients with ostomy.Methods Based on the theory of knowledge,attitude and practice,the initial scale was generat-ed through literature review,semi-structured interviews,expert correspondence,research group discussion and pre-sur-vey.From May to December 2023,685 patients with ostomy from the ostomy clinic of a tertiary hospital in Tianjin were investigated by purpose sampling method,and the reliability and validity were tested.Results A total of 673 valid questionnaires were collected,the results showed that the knowledge-attitude-practice assessment scale for pre-venting and managing parastomal hernia of ostomy patients at home included 3 dimensions of knowledge,attitude and practice,with a total of 27 items.The response rates of 2 rounds of the questionnaire were both 100％;the au-thority coefficients were all 0.915;the Kendall's coefficients of concordance were 0.279 and 0.301,respectively.The content validity index of each item was 0.875～1.000;the content validity index of the average scale level was 0.988;after 2 exploratory factor analysis,the cumulative variance contribution rate was 65.920％.The results of con-firmatory factor analysis showed that the model had a good fit,with a chi-square degree of freedom ratio(/df)of 1.945,the fitting goodness index(GFI)of 0.851,the comparative goodness of fit index(CFI)of 0.919,the root means square error of approximation(RMSEA)of 0.060.The Cronbach's alpha coefficient result of the scale is 0.957,with a test-retest reliability of 0.826 and a half reliability of 0.934.Conclusion The knowledge-attitude-practice assessment scale has good reliability and validity,and can be used as an assessment tool for home prevention and management of parastostomy hernia in ostomy patients.

Objective To propose a novel method based on three-dimensional depthwise separable convolution network(3D DSN)for the separation of PET images with dual tracers of 18F-FDG and 18F-FAPI.Methods A total of 120 pairs of 18F-FDG and 18F-FAPI PET images of the same patient scanned separately at different time points were collected,and the dual-tracer PET image was generated through simulation.After the image registration of PET images of two tracers for ensuring spatial position matching,the registered PET images were forward-projected to generate sinogram data,and the sinogram data of two tracers were accumulated to obtain mixed sinogram data.Subsequently,the dual-tracer PET image was reconstructed using maximum likelihood expectation maximization and input into a 3D DSN based network for image separation,thereby obtaining PET images of two single tracers.Results Compared with 3D CNN method,the proposed method increased the structure similarity index measure(SSIM)of the separated 18F-FDG images to the real 18F-FDG images by 0.87%,increased the peak signal-to-noise ratio(PSNR)by 11.8%,and reduced the normalized root mean square error(NRMSE)by 52%.The SSIM of the separated 18F-FAPI images to the real 18F-FAPI images increased by 1.1%,PSNR increased by 17.0%,and NRMSE decreased by 51%.Conclusion The proposed method can be effectively applied to simultaneous PET imaging with dual PET tracers,reducing the number of scans and costs in time and money,and providing clinical doctors more accurate and abundant diagnostic information.

【Objective】 To establish a risk model for predicting spontaneous rupture bleeding of renal angiomyolipoma (RAML) in order to better assess and deal with the risk. 【Methods】 The information of 436 RAML patients diagnosed during Jan.2018 and Dec.2022 was retrospectively analyzed.According to the inclusion and exclusion criteria, 216 patients were included and divided into the rupture bleeding group (n=35) and non-rupture bleeding group (n=181).The factors influencing spontaneous rupture bleeding were identified using univariate and multivariate analysis, and a nomogram was constructed accordingly with R language.The nomogram was evaluated using Calibration curve and area under the receiver operator characteristic curve (AUC). 【Results】 It was found that clinical manifestations, tumor diameter, tumor convexity, tumor blood supply, and tuberous sclerosis complex (TSC) were significantly correlated with rupture bleeding.The Calibration curve fitted well with the nomogram.The AUC was 0.956 (95%CI: 0.856-0.943), indicating that the nomogram had good statistical performance. 【Conclusion】 The model can effectively predict the risk of spontaneous rupture bleeding of renal angiomyolipoma.

Objective The prediction of RR intervals in hypertensive patients can help clinicians to analyze and warn patients'heart condition.Methods Using 8 patients'data as samples,the RR intervals of patients were predicted by long short-term memory network(LSTM)and gradient lift tree(XGBoost),and the prediction results of the two models were combined by the inverse variance method to overcome the disadvantage of single model prediction.Results Compared with the single model,the proposed combined model had a different degree of improvement in the prediction of RR intervals in 8 patients.Conclusion LSTM-XGBoost model provides a method for predicting RR intervals in hypertensive patients,which has potential clinical feasibility.

The intestinal flora and gut barrier function are of great significance for gut function and human health. When the intestinal flora is disrupted and the gut barrier structure is disrupted, it can lead to bacterial translocation, endotoxin influx into the bloodstream, and the production of pro-inflammatory factors, leading to various tissue damage in the body. Tongfu method in TCM can affect the intestinal environment by regulating intestinal permeability and immune response, restoring normal intestinal movement, and regulating the structure and metabolites of intestinal flora, thereby maintaining intestinal homeostasis and body health. The research on regulating intestinal flora and improving intestinal barrier function by Tongfu method can provide reference for further research on the relationship between TCM and intestinal microecology, and provide ideas for clinical treatment.

Objective To understand the implementation of the nursing group standards for oxygen inhalation therapy in clinical practice,and to provide a reference for improving the nursing practice of oxygen therapy.Methods A convenience sampling method was used to investigate nurses from 902 hospitals in 24 provinces and municipalities directly under the central government using a self-designed questionnaire from December 15th,2022,to January 14th,2023.The content of questionnaire included whether they had implemented the recommendations of the oxygen therapy standards,the knowledge of safety related to oxygen therapy,and the components of oxygen therapy prescriptions,the indications used for patients receiving oxygen therapy and practice status of oxygen therapy.Results A total of 10481 questionnaires were returned,of which 10447 were valid,with a valid questionnaire recovery rate of 99.68%.63.14%of the nurses indicated that the hospital had organized training on oxygen therapy standards.Only 47.82%of nurses know the correct use of the Venturi mask.41.90%of nurses could indicate the correct indicator of flow adjustment.31.88%of the nurses stated that they will adjust the oxygen flow rate based on the oxygenation status of carbon dioxide storage patients.Only 19.56%of nurses indicated that humidification is applied in oxygen therapy based on the oxygen flow and duration.Conclusion Even though nurses had received training related to oxygen therapy standards,the level of knowledge of oxygen therapy standards was still low;therefore continuous systematic training was needed,and the implementation of the content of oxygen therapy standards needed to be further standardized.Healthcare institutions would focus on organizing systematic training and maintaining the training effect,enhancing infrastructure and providing support for implementation.Recommendation to the nursing administration is to explore how to comprehensively and continuously implementing the oxygen therapy nursing standards with the ultimate goal of providing patients safer and more accurate oxygen therapy.

Objective : To study the best machine learning method for early prediction of hematoma expansion in hypertensive intracerebral hemorrhage based on head CT plain scan. Methods : The CT images of 130 patients with cerebral hemorrhage were retrospectively analyzed , and the texture features of the head CT plain scan were extracted. The classifier was trained by selecting the features , and the six classic machine learning methods were crossvalidated to evaluate the stability and performanceof predicting cerebral hemorrhage hematoma expansion. Results: The prediction performance of support vector machine (SVM⁃Radial) (AUC 0. 714 ± 0. 144 , accuracy 0. 723 ± 0. 109) , generalized linear model ( GLM) prediction performance ( AUC 0. 643 ± 0. 125 , accuracy 0. 587 ± 0. 136) , random forest (RF) prediction performance (AUC 0. 686 ± 0. 128 , accuracy 0. 680 ± 0. 130) , k ⁃nearest neighbor (kNN) prediction performance ( AUC 0. 657 ± 7C 15 , accuracy 0. 639 ± 39 performance 19) , gradient boosting tree algorithm (GBM) Prediction performance ( AUC 0. 718 ± 0. 141 , accuracy 0. 670 ± 0. 126) , neural network (NNet) prediction performance (AUC 0. 659 ± 0. 162 , accuracy 0. 680 ± 0. 130) , in which support vector machines showed high prediction performance , generalized linear model showed low predictive performance. Conclusion Among the six machine learning methods based on cranial CT radiomics to predict early hematoma expansion in hypertensive intracerebral hemorrhage , support vector machine (SVM⁃Radial) has the best predictive performance and has potential clinical application value.

Objective:To compare the optimal gridpercutaneous vertebroplasty (PVP) and conventional PVP in the treatment of osteoporotic vertebral compression fractures (OVCFs).Methods:A retrospective cohort study was conducted of 102 patients with OVCFs who had underwent PVP between May 2016 and May 2019 at department of spine surgery, General Hospital of Northern Theater Command. According to the different surgical methods, they were divided into the optimalgrid PVP group (102 cases) and conventional PVP group (94 cases). In the optimal grid PVP group, there were 38 males and 64 females with an average age of 67.3±8.5 years old, and the course of disease was 2.3±1.2 days; the injured sites were lumbar vertebra, including 59 cases of L 1 vertebra, 31 cases of L 2 vertebra, 8 cases of L 3 vertebra, 3 cases of L 4 vertebra and 1 case of L 5 vertebra. In the conventional PVP group, there were 26 males and 68 females with an average age of 71.5±5.6 years old, and the course of disease was 2.1±1.1 days; the injured sites were lumbar vertebra, including 52 cases of L 1 vertebra, 33 cases of L 2 vertebra, 7 cases of L 3 vertebra and 2 cases of L 4 vertebra. The patients were prepared before operation. Then the best puncture point was selected, and the guide wire and working channel were inserted. Finally the bone cement was pushed. The operation time, intraoperative fluoroscopy times, bone cement dosage and bone cement leakage were compared between the two groups. Visual analogue scale (VAS), anterior heights and median heights of injured vertebra were compared between the two groups at postoperative 3 days, 3 months and the final follow-up. Results:There were no significant differences in the general clinical data between the two groups before operation ( P>0.05). All patients had no complications such as wound infection,pulmonary embolism,spinal cord embolism or death. The operation time, fluoroscopy times, bone cement dosage and bone cement permeability of the two groups were statistically significant different ( P<0.05), and the optimal grid group was better than the conventional group. VAS at 3 days, 3 months and the final follow-up was statistically significantlower in the optimal grid group than the conventional group ( P<0.05). There was no significant difference in the recovery of the anterior and middle edge heights of injured vertebra in the two groups 3 days after operation ( P>0.05), but there were statistical significant difference between the two groups3 months after operation and at the last follow-up ( P<0.05), whilethe optimal grid group was better than the conventional group. Conclusion:Compared with conventional PVP, the optimal grid PVP is safer and more effective in the treatment of osteoporotic vertebral compression fractures.