ABSTRACT
Background/Aims@#The accuracy of endosonographers in diagnosing gastric subepithelial lesions (SELs) using endoscopic ultrasonography (EUS) is influenced by experience and subjectivity. Artificial intelligence (AI) has achieved remarkable development in this field. This study aimed to develop an AI-based EUS diagnostic model for the diagnosis of SELs, and evaluated its efficacy with external validation. @*Methods@#We developed the EUS-AI model with ResNeSt50 using EUS images from two hospitals to predict the histopathology of the gastric SELs originating from muscularis propria. The diagnostic performance of the model was also validated using EUS images obtained from four other hospitals. @*Results@#A total of 2,057 images from 367 patients (375 SELs) were chosen to build the models, and 914 images from 106 patients (108 SELs) were chosen for external validation. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the model for differentiating gastrointestinal stromal tumors (GISTs) and non-GISTs in the external validation sets by images were 82.01%, 68.22%, 86.77%, 59.86%, and 78.12%, respectively. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy in the external validation set by tumors were 83.75%, 71.43%, 89.33%, 60.61%, and 80.56%, respectively. The EUS-AI model showed better performance (especially specificity) than some endosonographers.The model helped improve the sensitivity, specificity, and accuracy of certain endosonographers. @*Conclusions@#We developed an EUS-AI model to classify gastric SELs originating from muscularis propria into GISTs and non-GISTs with good accuracy. The model may help improve the diagnostic performance of endosonographers. Further work is required to develop a multi-modal EUS-AI system.
ABSTRACT
Purpose@#Models for predicting perforation during endoscopic resection (ER) of gastric submucosal tumors (SMTs) originating from the muscularis propria (MP) are rare. Therefore, this study was conducted to determine important parameters in endoscopic ultrasonography (EUS) images to predict perforation and to build predictive models. @*Methods@#Consecutive patients with gastric SMTs originating from the MP who received ER from May 1, 2013 to January 15, 2021 were retrospectively reviewed. They were classified into case and control groups based on the presence of perforation. Logistic multivariate analysis was used to identify potential variables and build predictive models (models 1 and 2: with and without information on tumor pathology, respectively). @*Results@#In total, 199 EUS procedures (194 patients) were finally chosen, with 99 procedures in the case group and 100 in the control group. The ratio of the inner distance to the outer distance (I/O ratio) was significantly larger in the case group than in the control group (median ratio, 2.20 vs. 1.53; P<0.001). Multivariate analysis showed that age (odds ratio [OR], 1.036 in model 1; OR, 1.046 in model 2), the I/O ratio (OR, 2.731 in model 1; OR, 2.372 in model 2), and the pathology of the tumors (OR, 10.977 for gastrointestinal stromal tumors; OR, 15.051 for others in model 1) were risk factors for perforation. The two models to predict perforation had areas under the curve of 0.836 (model 1) and 0.755 (model 2). @*Conclusion@#EUS was useful in predicting perforation in ER for gastric SMTs originating from the MP. Two predictive models were developed.
ABSTRACT
Objective:To observe the value of tracer methodology combined case-based study (CBS) model in the standardized residency training of medical record writing.Methods:A total of 91 residents who were newly recruited from The Sixth Affiliated Hospital of Sun Yat-sen University in July 2019 were selected as the subjects and randomly divided into test group ( n=47) and control group ( n=44). The tracer methodology combined CBS model was used for test group while the traditional model was used for control group to compare the knowledge of medical record writing, performance of medical record writing and feedback to teaching in two groups. SPSS 21.0 was used for t test and chi-square test. Results:The correct response rate in knowledge of medical record writing, the normative scores and integrity scores after training were significantly higher than those before training ( P<0.05). The normative and integrity scores were significantly increased after training, and those in the test group were significantly higher than those in the control group [(90.3±3.5) and (91.3±3.2) vs. (88.6±3.5) and (89.8±3.0), P<0.05, respectively]. The test group was significantly superior to the control group in the autonomous learning ability [97.8% (44/45) vs. 82.9% (34/41)], communication ability [95.6% (43/45) vs. 78.0% (32/41)] and acceptance of teaching form [97.8% (44/45) vs. 82.9% (34/41)] ( P<0.05). Conclusion:The tracer methodology combined CBS model is a good way in the pre-job training of medical record writing for residents, which can mobilize the subjective initiative of the trainees and teachers, complete the teaching tasks and obtain better teaching value.
ABSTRACT
<p><b>OBJECTIVE</b>To investigate the safety, feasibility, clinical value, indication, and distribution of diagnostic diseases in different age groups of colonoscopy in pediatric patients.</p><p><b>METHODS</b>A retrospective analysis was performed on the data of pediatric patients receiving colonoscopy from April 2013 to June 2016 at The Sixth Affiliated Hospital of Sun Yat-sen University. Pediatric patients were divided into 0-6 years group (n=57) and 7-14 years group (n=172). Indication for colonoscopy, detective events and diagnostic diseases distribution were compared between two groups.</p><p><b>RESULTS</b>A total of 229 pediatric patients (male 157 and female 72) were divided into 0-6 years group (57/229, 24.9%) and 7-14 years group(172/229, 75.1%). The main Indications for colonoscopy included abdominal pain (81/229, 35.4%), hematochezia (64/229, 27.9%), crissum abscess or fistula (40/229, 17.5%). Hematochezia was the most common complaint in 0-6 years group (40/57, 70.2%), while abdominal pain in 7-14 years group (74/172, 43.0%). Completion rate between 0-6 years group and 7-14 years group was not significantly different (87.72% vs. 85.47%, χ=0.181, P=0.671). Only one pediatric patient (1/229, 0.4%) developed transient oxygen desaturation and recovered quickly after oxygen supply and aspiration of sputum. No serious complications such as bleeding, perforation or death occurred. Including 45 pediatric patients in 0-6 years group and 102 pediatric patients in 7-14 years group, a total of 147 pediatric patients (147/229, 64.2%) were found to have colorectal lesions. Inflammatory bowel disease (57/147, 38.8%), colonic polyps (40/147, 27.2%) and other intestinal inflammation (39/147, 26.5%) were the main findings. The most frequent diagnosis in 0-6 years group was colonic polyps (28/57, 49.1%), among them, 25 pediatric patients (25/28, 89.3%) were with the complaint of hematochezia. The most frequent diagnosis in 7-14 years group was Inflammatory bowel disease (54/172, 31.4%), among them, 29 pediatric patients (29/54, 53.7%) were with the complaint of abdominal pain.</p><p><b>CONCLUSIONS</b>Pediatric colonoscopy is safe and effective. Hematochezia and abdominal pain are the most common complaints in 0-6 years group and 7-14 years group respectively. Colonic polyps and inflammatory bowel disease are the most frequent diagnosis in 0-6 years group and 7-14 years group respectively.</p>