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 construct a risk assessment model based on probabilistic hesitant fuzzy set(PHFS)for pressure-related injuries in medical equipment,and analyze its application value in control and management for risk of pressure-related injuries in medical equipment in the department of emergency.Methods:The frequency of events caused by pressure-related injuries of equipment was counted as statistical method.Combined with the risk assessment factors of pressure-related injuries,the technique for order preference by similarity to ideal solution(TOPSIS)based on PHFS was used to evaluate the risk level of pressure-related injuries of equipment,and formulate corresponding measures for risk management of pressure-related injuries.A total of 120 used medical equipment at the Department of Emergency of the First Affiliated Hospital of Xi'an Jiaotong University from January 2024 to December 2024 were selected.Using the random number table method,60 equipment were managed with the conventional risk management mode for pressure-related injuries(conventional management mode),and the other 60 equipment were managed with risk assessment model based on PHFS(model management mode)for pressure-related injuries in medical equipment.The incidence of pressure-related injuries of equipment,scores of operational quality of equipment,incidence of pressure-related injuries at different staging were compared between two kinds of management modes.A self-made questionnaire was used to investigate the satisfactions of emergency doctors,nurses,patients,and medical engineers in the department of equipment,who used and managed equipment.Results:The scores of operational standardization,pressure controllability,and diagnostic comfort in the model management mode were respectively(93.36±4.56),(90.54±3.69)and(93.65±4.69)points,which were significantly higher than those in the conventional management mode,while the score of material sensitivity was(30.23±3.26)points,which was significantly lower than that in the conventional management mode(t=15.941,11.896,11.511,17.200,P<0.05).The incidences of occurring pressure-related injuries in the referred logs of diagnosis and treatment of respiratory equipment,monitoring equipment,infusion equipment,and oxygen supply equipment in the model management mode were significantly lower than those in the conventional management mode(x2=9.924,9.493,9.796,8.075,P<0.05).The incidences of stage 1,2,3,and 4 of pressure-related injuries of equipment in the model management mode were significantly lower than those in the conventional management mode(x2=7.209,6.985,8.048,7.473,P<0.05).The satisfactions of emergency doctors,nurses,patients,and medical engineers in the department of equipment for the clinical use of equipment in the model management mode were significantly higher than those in the conventional management mode(t=12.499,13.200,14.410,9.226,P<0.05).Conclusion:The risk assessment model based on PHFS for pressure-related injury of medical equipment can reduce the incidences of pressure-related injuries of medical equipment in the department of emergency,and improve the safety of using medical equipment,and enhance the service quality of clinical equipment,and increase the satisfaction for equipment in clinical applications.

Objective:To construct a risk assessment model based on probabilistic hesitant fuzzy set(PHFS)for pressure-related injuries in medical equipment,and analyze its application value in control and management for risk of pressure-related injuries in medical equipment in the department of emergency.Methods:The frequency of events caused by pressure-related injuries of equipment was counted as statistical method.Combined with the risk assessment factors of pressure-related injuries,the technique for order preference by similarity to ideal solution(TOPSIS)based on PHFS was used to evaluate the risk level of pressure-related injuries of equipment,and formulate corresponding measures for risk management of pressure-related injuries.A total of 120 used medical equipment at the Department of Emergency of the First Affiliated Hospital of Xi'an Jiaotong University from January 2024 to December 2024 were selected.Using the random number table method,60 equipment were managed with the conventional risk management mode for pressure-related injuries(conventional management mode),and the other 60 equipment were managed with risk assessment model based on PHFS(model management mode)for pressure-related injuries in medical equipment.The incidence of pressure-related injuries of equipment,scores of operational quality of equipment,incidence of pressure-related injuries at different staging were compared between two kinds of management modes.A self-made questionnaire was used to investigate the satisfactions of emergency doctors,nurses,patients,and medical engineers in the department of equipment,who used and managed equipment.Results:The scores of operational standardization,pressure controllability,and diagnostic comfort in the model management mode were respectively(93.36±4.56),(90.54±3.69)and(93.65±4.69)points,which were significantly higher than those in the conventional management mode,while the score of material sensitivity was(30.23±3.26)points,which was significantly lower than that in the conventional management mode(t=15.941,11.896,11.511,17.200,P<0.05).The incidences of occurring pressure-related injuries in the referred logs of diagnosis and treatment of respiratory equipment,monitoring equipment,infusion equipment,and oxygen supply equipment in the model management mode were significantly lower than those in the conventional management mode(x2=9.924,9.493,9.796,8.075,P<0.05).The incidences of stage 1,2,3,and 4 of pressure-related injuries of equipment in the model management mode were significantly lower than those in the conventional management mode(x2=7.209,6.985,8.048,7.473,P<0.05).The satisfactions of emergency doctors,nurses,patients,and medical engineers in the department of equipment for the clinical use of equipment in the model management mode were significantly higher than those in the conventional management mode(t=12.499,13.200,14.410,9.226,P<0.05).Conclusion:The risk assessment model based on PHFS for pressure-related injury of medical equipment can reduce the incidences of pressure-related injuries of medical equipment in the department of emergency,and improve the safety of using medical equipment,and enhance the service quality of clinical equipment,and increase the satisfaction for equipment in clinical applications.

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 application effects of a two-way six-step nursing teaching model based on the Kolb's learning cycle in the teaching of nurse interns in an emergency department.Methods:We assigned 52 undergraduate nursing students interning at the department of emergency from February 2020 to February 2022 to receive conventional teaching (control group) and 50 nurse interns from March 2022 to February 2023 to receive two-way six-step nursing teaching based on the Kolb's model (observation group). We evaluated the changes in core competencies before and after learning using the Competency Inventory for Registered Nurses (CIRN); assessed self-learning abilities using a nursing student self-learning ability assessment scale; recorded the incidence rates of related errors in the emergency department after learning; and assessed the level of satisfaction with nursing using the Patient Satisfaction Questionnaire (PSQ-18). SPSS 22.0 was used to perform the chi-square test and t-test. Results:After learning, the scores of CIRN dimensions and self-learning ability dimensions were all increased in both groups, and these scores were significantly higher in the observation group [(31.78±2.34), (50.22±4.33), (28.56±2.09), (19.22±3.11), (22.34±2.78); (30.07±3.14), (24.11±2.99), (30.11±3.41), (33.33±3.09)] than in the control group [(30.88±2.22), (48.34±3.88), (27.59±2.52), (17.77±3.08), (20.88±2.55); (28.67±2.09), (22.56±2.44), (27.99±3.03), (31.33±3.44)]. Compared with the control group, the observation group showed significantly lower incidence rates of errors in the execution of medical orders (19.23% vs. 2.00%, P=0.008) and errors in practice in accordance with standards (15.38% vs. 0.00%, P=0.006). There were no significant differences in the incidence rates of poor response on the spot, medical record errors, and medical dispute errors between the observation group and the control group (all P>0.05). The PSQ-18 scores in all dimensions of the observation group were significantly higher than those of the control group ( P=0.002, 0.001, 0.014, 0.008, <0.001). Conclusions:The two-way six-step nursing teaching model based on the Kolb's model can significantly improve the core competencies and self-learning abilities of nursing students in the department of emergency, and reduce errors in the execution of medical orders and practice in accordance with standards, thus improving their nursing service levels.

Objective:To explore the effects of electroacupuncture combined with hyperbaric oxygen (HBO) therapy for the improvement of the neural function and cognitive ability in patients with hypertensive cerebral hemorrhage.Methods:A total of 180 patients with hypertensive cerebral hemorrhage admitted in Department of Neurology of the Sinopharm-Gezhouba Central Hospital of China Three Gorges University from the January of 2016 to the June of 2019 were selected and randomly divided into hyperbaric oxygen group (HBO group) ( n=60), electric acupuncture group (EA group) ( n=60), and EA combined HBO treatment group (EA+ HBO group) ( n=60) by random number table method. The clinical curative effect and the improvements of cerebral edema, neural function, and cognitive ability were compared in the three groups before and after treatment. Results:After 2 and 4 courses of the treatment, the absolute cerebral edema volume and relative cerebral edema volume of the patients were gradually decreased, and the absolute volumes in the EA+ HBO group were significantly decreased compared with those in the HBO group and the EA group with statistically significant differences ( P<0.05). After 4 courses of the treatment, the total effective rate of the EA+ HBO group was 91.67%, which was significantly higher than those of the HBO group (81.67%) and the EA group (76.67%) with statistically significant differences ( P<0.05). The serum neuron-specific enolase (NSE) and S100β levels of the three groups were significantly lower than those before the treatments, and the levels in the EA+ HBO group were lower than those in other two groups. The differences were statistically significant ( P<0.05). After treatment, the mini-mental state examination (MMSE) score and Barthel index score of the patients were significantly increased ( P<0.05), and the improvement of MMSE score in the EA+ HBO group was significantly better than those in the HBO group and the EA group with statistically significant differences ( P<0.05). Conclusion:Electroacupuncture combined with HBO can effectively reduce cerebral edema, repair cerebral nerve damage, and improve patients′ cognitive function through electrical stimulation and abatement of ischemia and hypoxia.

Objective:To explore the effects of electroacupuncture combined with hyperbaric oxygen (HBO) therapy for the improvement of the neural function and cognitive ability in patients with hypertensive cerebral hemorrhage.Methods:A total of 180 patients with hypertensive cerebral hemorrhage admitted in Department of Neurology of the Sinopharm-Gezhouba Central Hospital of China Three Gorges University from the January of 2016 to the June of 2019 were selected and randomly divided into hyperbaric oxygen group (HBO group) ( n=60), electric acupuncture group (EA group) ( n=60), and EA combined HBO treatment group (EA+ HBO group) ( n=60) by random number table method. The clinical curative effect and the improvements of cerebral edema, neural function, and cognitive ability were compared in the three groups before and after treatment. Results:After 2 and 4 courses of the treatment, the absolute cerebral edema volume and relative cerebral edema volume of the patients were gradually decreased, and the absolute volumes in the EA+ HBO group were significantly decreased compared with those in the HBO group and the EA group with statistically significant differences ( P<0.05). After 4 courses of the treatment, the total effective rate of the EA+ HBO group was 91.67%, which was significantly higher than those of the HBO group (81.67%) and the EA group (76.67%) with statistically significant differences ( P<0.05). The serum neuron-specific enolase (NSE) and S100β levels of the three groups were significantly lower than those before the treatments, and the levels in the EA+ HBO group were lower than those in other two groups. The differences were statistically significant ( P<0.05). After treatment, the mini-mental state examination (MMSE) score and Barthel index score of the patients were significantly increased ( P<0.05), and the improvement of MMSE score in the EA+ HBO group was significantly better than those in the HBO group and the EA group with statistically significant differences ( P<0.05). Conclusion:Electroacupuncture combined with HBO can effectively reduce cerebral edema, repair cerebral nerve damage, and improve patients′ cognitive function through electrical stimulation and abatement of ischemia and hypoxia.

Objective Toinvestigatetheincidenceofchronicrenalobstructiveexternalappendageinvolvementandtheresultsof MSCTdetection.Methods MSCTdataof120patientswithchronicurinarytractobstructionwereretrospectivelyanalyzed.Results Among120patients,75caseswerefoundwiththeextrarenalappendageinjury(62.5%).Theinjuryoftheextrarenalappendageincluded thickeningofrenalcapsule(8.00%),effusionofrenalsubcapsular(14.67%),thickeningofbridgingseptaoftheperinephricspace (100.00%),lamellarshadowoffatlayerintheperirenalspace(36.00%),thickeningofrenalfascia(96.00%),pararenalspaceeffusion (88.00%),thickeningperitoneal(76.00%),pseudocyst(1.33%),lamellarshadowoffatlayerinextraperitoneal(22.67%)andnapes(6.67%), increasedintraperitonealfatdensity(32.00%)andperitonealeffusion(4.00%).Conclusion MSCTcanclearlydemonstrateextentand rangeoftheperinephricspaceandpararenalspaceinvolvementinchronicurinarytractobstruction.CTscanplayanimportantrolein chronicurinarytractobstruction.

Objective To explore MSCT findings of pulmonary tuberculoma.Methods MSCT data of 62 patients with pulmonary tuberculoma confirmed by clinical and pathological results were analyzed retrospectively.Results Of the 62 patients,64 lesions were detected with single in 60 cases and multiple in 2 cases.The MSCT signs showed as follows:circumscribed round,oval,egg-like or irregular nodules or masses,size ranging from 2-3 cm,cavity in 31 lesions,calcification in 25 lesions,pleural indentation sign in 45 lesions and pleural tail sign in 1 2 lesions.Conclusion The MSCT features of pulmonary tuberculoma are relatively specific such as the multiple patch calcifications within mass,calcification of the whole mass and semilunar cavity on the lateral side of the hilum.The MSCT is a valuable examination for the accurate diagnosis of pulmonary tuberculoma.

Objective:To establish a calculation model of drug preparation difficulty coefficient for outpatient pharmacy intrave -nous admixture center ( OUIVA) in a children's hospital, and construct the performance model .Methods: All the prescriptions in a week in OUIVA of Shanghai children's medical center were randomly selected .According to the actual difficulty level in the process of outpatient and emergency drug preparation , a basic drug difficulty coefficient and difficulty coefficient addition method was constructed . The difficulty index of every prescription was calculated .All the prescriptions in a week were randomly selected , and according to the difficulty coefficient analysis method , the daily difficulty coefficient of the prescriptions was calculated in order to build a performance model for OUIVA in the hospital .Results:The difficulty coefficient of medicine mainly included four basic difficulty coefficients and nine difficulty addition coefficients .According to the statistics , the average difficulty coefficient of daily prescriptions was (3.83 ± 2.86 )with the highest difficulty coefficient of 35, and the prescription data showed that there was significant difference between outpa -tient and emergency prescriptions and daytime blood tumor prescriptions .Conclusion:A performance model based on the difficulty co-efficient for OUIVA in children ' s hospital is a more scientific reflection to the daily work .