Objective To compare the performance of 3 risk prediction models based on machine learning in predicting the risk of compassion fatigue among obstetrics and gynaecology nurses.Methods Using the convenience sampling method,1 323 obstetrics and gynaecology nurses from 11 tertiary hospitals in 9 cities were selected from December 2022 to March 2023,and were randomly divided into a training set and a test set according to 7∶3 ratio.Compassion Fatigue Scale,Five Facet Mindfulness Questionnaire and Emotional Intelligence Scale were used for the survey.A total of 3 types of risk prediction models were constructed for the factors affecting the compassion fatigue of obstetrics and gynaecology nurses,namely,Logistic Regression,Decision Tree,and Random Forest.The accuracy,precision,specificity,sensitivity,Fl score and AUC were used to compare the predictive performance of the 3 models.Results Finally 1 276 maternity nurses completed the survey.All 3 models showed that nature of employment,years of experience,mindfulness and emotional intelligence were independent risk factors for compassion fatigue in obstetrics and gynaecology nurses(P＜0.05).The results of model comparison showed that the accuracy of Logistic regression,decision tree and random forest were 0.804,0.806,0.796;the precision was 0.821,0.827,0.823;the sensitivity was 0.956,0.949,0.939;the Fl score was 0.883,0.884,0.877;the AUC was 0.704(95％CI:0.701～0.713),0.760(95％CI:0.751～0.771),0.742(95％CI:0.723～0.762)respectively.Conclusion The risk prediction model of factors affecting compassion fatigue among obstetrics and gynaecology nurses constructed by decision tree performed the best,and the predictive performance was better than that of the random forest and logistic regression models.The multi-model effectively predicts the risk of compassion fatigue in obstetrics and gynecology nurses,explores the interaction of influencing factors in multiple dimensions,and it can inform the early identification and prevention of compassion fatigue and the development of related interventions.

Objective To compare the performance of 3 risk prediction models based on machine learning in predicting the risk of compassion fatigue among obstetrics and gynaecology nurses.Methods Using the convenience sampling method,1 323 obstetrics and gynaecology nurses from 11 tertiary hospitals in 9 cities were selected from December 2022 to March 2023,and were randomly divided into a training set and a test set according to 7∶3 ratio.Compassion Fatigue Scale,Five Facet Mindfulness Questionnaire and Emotional Intelligence Scale were used for the survey.A total of 3 types of risk prediction models were constructed for the factors affecting the compassion fatigue of obstetrics and gynaecology nurses,namely,Logistic Regression,Decision Tree,and Random Forest.The accuracy,precision,specificity,sensitivity,Fl score and AUC were used to compare the predictive performance of the 3 models.Results Finally 1 276 maternity nurses completed the survey.All 3 models showed that nature of employment,years of experience,mindfulness and emotional intelligence were independent risk factors for compassion fatigue in obstetrics and gynaecology nurses(P＜0.05).The results of model comparison showed that the accuracy of Logistic regression,decision tree and random forest were 0.804,0.806,0.796;the precision was 0.821,0.827,0.823;the sensitivity was 0.956,0.949,0.939;the Fl score was 0.883,0.884,0.877;the AUC was 0.704(95％CI:0.701～0.713),0.760(95％CI:0.751～0.771),0.742(95％CI:0.723～0.762)respectively.Conclusion The risk prediction model of factors affecting compassion fatigue among obstetrics and gynaecology nurses constructed by decision tree performed the best,and the predictive performance was better than that of the random forest and logistic regression models.The multi-model effectively predicts the risk of compassion fatigue in obstetrics and gynecology nurses,explores the interaction of influencing factors in multiple dimensions,and it can inform the early identification and prevention of compassion fatigue and the development of related interventions.

Objective:To explore the efficacy and safety of endoscopic radial incision (ERI) for congenital membranous duodenal stenosis (MDS).Methods:The clinical data of 13 children with MDS receiving ERI in the Department of Gastroenterology of Xi'an Children's Hospital from May 2017 to December 2021 were reviewed and analyzed. The perioperative management, surgical procedures, postoperative complications and follow-up were summarized.Results:There were 5 boys and 8 girls with a median disease duration of 8 (2-20) months, and the median age of diagnosis was 13 months (5-30 months). The septum of 10 cases (10/13) was located in the descending part of the duodenum, and that of 3 cases (3/13) in the horizontal part. The papilla of 1 case (1/13) opened on the septum, that of 3 cases (3/13) within 5 cm of the mouth side of the septum, and that of 9 cases (9/13) within 5 cm of the anal side of the septum. The median diameter of the septal aperture was 3 mm (2-6 mm). All 13 children successfully underwent ERI with a median operation time of 20 min (15-32 min). The average surgical incision was 3 strokes (2-4 strokes), and the endoscope with outer diameter 9.9 mm could pass stenosis after ERI. The median incision diameter was 10 mm (10-12 mm). All patients achieved relief of clinical symptoms after ERI. One patient (1/13) suffered from the postoperative delayed bleeding, which was stopped by endoscopic titanium clamping. No intestinal perforation or duodenal papilla injury occurred, and median postoperative hospital stay was 6 days (5-10 days). The upper gastrointestinal angiogram and gastroscopy were repeated 3 months after ERI, and the median diameter of stenosis was 12 mm (10-15 mm), which was significantly dilated compared with before. The mean body weight increase at 1 month after ERI was 1.20 kg (0.50-1.80 kg), and the mean body weight increase at 3 months was 3.50 kg (2.50-4.00 kg), which reached the normal body weight of the same age.Conclusion:ERI is safe and effective for the treatment of MDS in children, and shows good clinical application and promotion value.

Objective:To explore the effectiveness of SECI (socialization, externalization, combination, and internalization) model in clinical practice training of hematology nurses.Methods:A total of 86 students from the clinical practice training course for hematology nurses from October 2022 to September 2023 were selected as the research subjects. The 43 trainees who received practical training from October 1, 2022 to March 31, 2023 were included in the traditional group, and the 43 trainees who received practical training from April 1, 2023 to September 30, 2023 were included in the observation group. The traditional group received traditional teaching, while the observation group received SECI teaching. After the training, basic assessment and satisfaction evaluation were conducted, and a long-term evaluation was conducted at 6 months after the training. The t test and chi-square test were performed using SPSS 25.0. Results:The observation group had higher scores in case reports [(92.03±2.21) vs. (88.14±2.36)], theoretical assessments [(95.61±3.79) vs. (86.58±3.75)], and operational assessments [(96.24±1.45) vs. (90.13±1.41)] compared with the traditional group (all P<0.05). The observation group had higher scores for teaching plans, teaching methods, teaching effectiveness, teaching atmosphere, internship content, and overall satisfaction with practical training than the traditional group ( P<0.05). The long-term evaluation showed that the theoretical and operational assessment scores of the observation group were higher than those of the traditional group at 6 months after training (both P<0.05). Conclusions:The application of SECI teaching in the clinical practice training of hematology nurses has shown good results, which can help nurses better grasp clinical theoretical knowledge and significantly improve their practical operation ability and training satisfaction.

Objective To review the application of intelligent robots in the pain intervention of children,and identify the elements of the intervention,so as to guide future research and practice.Methods A literature search was performed in the PubMed,Cochrane Library,Embase,Web of Science,CINAHL,CNKI,Wanfang database,and CBM.Following the methodology of the scoping review,the retrieval time was from the establishment of the database to November 2023.The included studies were summarized and analyzed.Results A total of 10 articles were included,including 7 randomized controlled trials,2 quasi-experimental studies,and 1 mixed method research study.The working principles of intelligent robots in pain intervention for pediatric patients include distraction and pain empathy.Functions of intelligent robots included verbal interaction,limb motion,facial expression,and haptic recognition.Interventions included pre-intervention preparation,intervention content,and intervention duration,of which the intervention content included question-and-answer conversations,breathing exercises,recreation,and verbal encouragement,and the duration of the intervention ranged from 3 to 11 minutes.The outcome indicators included pain level,negative emotions,and feasibility.The results showed the positive feasibility of the application of intelligent robots in pain intervention for children,which may help to reduce the level of pain and improve children's negative emotions such as anxiety and distress.Conclusion Intelligent robots in the field of pain intervention of children present preliminary effects and feasibility.It is recommended that researchers should enrich the functions of intelligent robots,enhance human-robot interaction,carry out personalized interventions,and add physiological indexes as effect evaluation indexes to further validate its application effects.

Objective:To investigate the diagnostic and therapeutic value of one-time biliopancreatic-duct-imaging-system (eyeMax)-assisted endoscopic retrograde appendicitis therapy (ERAT) for children.Methods:A total of 11 children who were diagnosed as having uncomplicated acute appendicitis by imaging in Xi′an Children′s Hospital from August to November 2022 were enrolled. All patients received subscope-assisted ERAT. Subscope was intubated into the appendix cavity to observe the mucosa directly. Appendicitis was treated through cleansing, fecalith extraction, stent drainage. The clinical manifestations under subscope were recorded, as well as the treatment success rate, intubation success rate, the effective rate, complication incidence during and after the operation.Results:The age of 11 children was 7.93±2.67 years old. Appendix intubation was successful in all patients. Congestion and swelling of the mucosa in appendiceal orifice and appendix cavity were seen under the subscope in 11 children. There were 6 cases with appendiceal fecaliths, 8 cases with pus and 6 cases with luminal distortion or stenosis. Perforation was observed in 1 case during the operation and no other complication occurred. All patients were treated under subscope, including flushing appendiceal cavity (11 cases), fecalith extraction with extraction basket (3 cases), and appendiceal drainage with stenting (2 cases). The symptoms and signs were relieved after the operation, and the effective rate within 48 hours was 10/11. There were no procedure-related complications or recurrence during postoperative follow-up for 1 week to 4 months.Conclusion:Acute appendicitis could be diagnosed by observing the appendix cavity directly under one-time biliopancreatic-duct-imaging-system-assisted ERAT, and also could be treated with the system, where appendix could be preserved and radiation damage could be avoided with safety and effectiveness.

Objective:To evaluate the safety and effectiveness of capsule endoscopy for the diagnosis of intestinal diseases in children.Methods:Clinical data of 113 pediatric patients who received capsule endoscopy in Xi'an Children's Hospital from October 2018 to September 2020 were retrospectively analyzed. The completion rate, passage time of stomach and small intestine, lesion detection rate, adverse reactions and complications of capsule endoscopy were analyzed.Results:Among 113 pediatric patients, 78 (69.03%) were male and 35 (30.97%) were female. The age was (99.8±44.7) months (9-195 months), and 31 (27.43%) were under 7 years old. The minimum weight was 9 kg and the minimum height was 70 cm. Eighty-seven pediatric patients (76.99%) swallowed capsules orally (the oral group) with the minimum age of 4 years and 3 months. Capsules were implanted in 26 pediatric patients (23.01%) under gastroscopy (the gastroscopic group), with the maximum age of 9 years and 2 months. Unexplained abdominal pain (47.79%) and unexplained gastrointestinal bleeding (31.89%) were common in the pediatric patients. The completion rate of capsule endoscopy was 97.35% (110/113), and the detection rate of lesions in small intestine was 31.81% (35/110). The passage time of small intestine in the gastroscopic group was significantly longer than that of the oral group (461.04±129.27 min VS 288.23±107.84 min, t=5.646, P<0.01). There was no significant difference in the passage time of stomach or small intestine among different genders, different ages or different endoscopic examination results ( P>0.05). The positive results of capsule were not correlated with the method of ingestion ( P=0.401, OR=2.562, 95% CI:0.284-23.077), gender ( P=0.154, OR=2.352, 95% CI:0.726-7.616), age ( P=0.949, OR=1.007, 95% CI:0.816-1.242), examination reason ( P=0.246) or small intestine passage time ( P=0.219, OR=1.003, 95% CI:0.998-1.008). No complications such as capsule retention occurred in any pediatric patient. Conclusion:Capsule endoscopy in children is noninvasive, rapid and simple, which can improve the diagnostic rate of small intestinal diseases in children, and can be further promoted in pediatric patients.

Objective:To evaluate high resolution esophageal manometry (HREM) in peroral endoscopic myotomy (POEM) for pediatric achalasia of cardia (AC).Methods:Data of 30 AC children who received POEM in Xi′an Children′s Hospital from January 2013 to September 2019 were reviewed. HREM was performed before and 6 months after POEM. Preoperative and postoperative lower esophageal sphincter pressure (LESP), 4-second integrated relaxation pressure (4sIRP), Eckardt scores and nutritional status were compared.Results:Children with AC aged between 4-14 years. Postoperative LESP was 5.50±1.13 mmHg (1 mmHg=0.133 kPa), which was significantly lower than that before operation (26.23±4.47 mmHg) with significant difference ( t=-24.623, P<0.001). Postoperative median 4sIRP was 5 mmHg, which was 20 mmHg lower than that before operation (25 mmHg) with significant difference ( Z=-4.786, P<0.001). Postoperative median Eckardt symptom score decreased significantly compared with that before (1 VS 8, Z=-4.796, P<0.001). Severe malnutrition of the AC children improved evidently to normal( Z=-5.166, P<0.001). Conclusion:POEM can significantly improve the characteristics of esophageal dynamics in children with AC, and HREM can be an important indicator for follow-up evaluation of POEM.

Objective:To explore the similarities and differences between children and adults with eosinophilic gastroenteritis (EGE), and to guide the diagnosis and treatment of EGE.Methods:From February 2013 to August 2018 at Xi′ an Children′ s Hospital, 18 children with EGE (child group) and from June 2008 to June 2018 at Xijing Hospital of Digestive Diseases, Air Force Medical University, 24 adults with EGE (adult group) were retrospectively selected as study subjects. The general data, clinical symptoms, laboratory examinations, imaging, endoscopy manifestations, pathological biopsy, treatment and prognosis of the two groups were analyzed. Chi-square test was used for statistical analysis. Results:The proportion of child group with allergic history was higher than that of adult group (9/18 vs. 20.8%, 5/24), the incidence of nausea and vomiting was higher than that of adult group (13/18 vs. 29.2%, 7/24), the incidence of diarrhea and weight loss were both lower than those of adult group (4/18 vs. 58.5%, 14/24; 3/18 vs. 54.2%, 13/24), and the proportion of patients with elevated peripheral blood eosinophil count was lower than that of adult group (4/18 vs. 58.3%, 14/24), and the differences were statistically significant ( χ2=3.938, 7.644, 5.477, 6.133 and 5.477, P=0.047, 0.006, 0.019, 0.013 and 0.029). The main endoscopic manifestations of the two groups were mucosal congestion and edema (13 cases of child group and 22 cases of adult group). Mucosal roughness (7 cases) and erosion (6 cases) were also common in child group, while mucosal erosion (18 cases, 75.0%) and ulcer (8 cases, 33.3%) were more common in adult group. There was a statistically significant difference in the incidence of mucosal erosion between the two groups ( χ2=7.292, P=0.007). The positive rates of biopsy in the terminal ileum, colorectum and duodenum of child group and adult group were both high (6/6, 14/15, 9/18 and 8/10, 12/15, 6/8, respectively). The response time of glucocorticoid treatment was 4.5 d (2.0 to 27.0 d) and 3.7 d (1.0 to 14.0 d) in child group (8 cases) and adult group (13 cases), respectively. There was no statistically significant difference in the recurrence rate after glucocorticoid treatment between the two groups (5/8 vs. 6/13, P > 0.05). Conclusions:The clinical characteristics of children and adults with EGE are different, which may provide references for clinicians to understand, diagnose and treat EGE.

Objective:To explore the new generation of intelligent ICU Unit based on 5G and artificial intelligence technology.Methods:This study was conducted at the Second Affiliated Hospital, Zhejiang University School of Medicine from May 2019 to August 2020. Based on a multidisciplinary team including medical, nursing, hospital management, clinical medical engineering, 5G technology, information technology, artificial intelligence technology, logistics service, etc, was assembled to intelligently design and reconstruct an intelligent ICU Unit of Emergency ICU.Results:Based on 5G technology, a new intelligent ICU unit environment was constructed to realize remote and high-speed interaction of multi-dimensional information in ICU, including intelligent assistance of remote monitoring, remote ward rounds, remote consultation and family visits. An intelligent hospital infection prevention and control system was established including automatic identification and alarm of hand hygiene and personal protection.Conclusions:The new generation of intelligent ICU unit combined with 5G and artificial intelligence technology has changed the mode of medical service for critically ill patients and improved the service level, which is worthy of further exploration and application.