1.Comparative analysis of endoscopic treatment and conservative treatment in 197 cases of gastric stones
Rong SU ; Ruirui HOU ; Xiangkun MENG ; Yu MIAO ; Feixiong ZHANG ; Jigang RUAN ; Shaoqi YANG
The Journal of Practical Medicine 2024;40(10):1389-1395
Objective To compare different treatment methods for patients with gastric calculi and provide data support for clinical treatment.Methods A total of 197 patients diagnosed with gastric calculi by gastroscopy at the General Hospital of Ningxia Medical University and Cardio-Cerebrovascular Disease Hospital of General Hospital of Ningxia Medical University from July 2013 to January 2024 were enrolled.The study collected general information and other data of the patients,and divided them into groups based on the selected treatment method using a real-world research approach.The subjects were divided into four groups:drug conservative treatment group,endoscopic homemade snare treatment group,disposable snare treatment group,and stone fragmentation treatment group.Statistical analysis was performed using one-way analysis of variance.Results Gastric calculi were more common in men,with an average age of(55.45±14.21).85.3%of the patients had a history of eating persimmon,86.3%had ulcers,and 65.9%were located in the gastric angle.The self-made snare group had the lowest treatment cost,while the stone fragmentation group had the highest.There was no significant difference in the remission time of clinical symptoms among the three endoscopic treatment methods.The self-made snare had the highest patient satisfaction,but the drug combined with carbonated beverage group had the longest remission time of clinical symptoms and the lowest patient satisfaction.The frequency and duration of endoscopic treatment of dark green gastric stones were significantly higher than those of mottled and golden yellow gastric stones.Conclusion When treating patients with gastric stones,it is important to consider the size and color of the stone,as well as the patient's preferences.Patients should be fully informed about their condition and the advantages of different treatments.For patients with larger stones(about 5 cm),endoscopic snare treatment is recommended as the first choice.
2.Application of artificial intelligence based on data enhancement and hybrid neural network to site identification during esophagogastroduodenoscopy
Shixu WANG ; Yan KE ; Jiangtao CHU ; Shun HE ; Yueming ZHANG ; Lizhou DOU ; Yong LIU ; Xudong LIU ; Yumeng LIU ; Hairui WU ; Feixiong SU ; Feng PENG ; Meiling WANG ; Fengying ZHANG ; Lin WANG ; Wei ZHANG ; Guiqi WANG
Chinese Journal of Digestive Endoscopy 2023;40(3):189-195
Objective:To evaluate artificial intelligence constructed by deep convolutional neural network (DCNN) for the site identification in upper gastrointestinal endoscopy.Methods:A total of 21 310 images of esophagogastroduodenoscopy from the Cancer Hospital of Chinese Academy of Medical Sciences from January 2019 to June 2021 were collected. A total of 19 191 images of them were used to construct site identification model, and the remaining 2 119 images were used for verification. The performance differences of two models constructed by DCCN in the identification of 30 sites of the upper digestive tract were compared. One model was the traditional ResNetV2 model constructed by Inception-ResNetV2 (ResNetV2), the other was a hybrid neural network RESENet model constructed by Inception-ResNetV2 and Squeeze-Excitation Networks (RESENet). The main indices were the accuracy, the sensitivity, the specificity, positive predictive value (PPV) and negative predictive value (NPV).Results:The accuracy, the sensitivity, the specificity, PPV and NPV of ResNetV2 model in the identification of 30 sites of the upper digestive tract were 94.62%-99.10%, 30.61%-100.00%, 96.07%-99.56%, 42.26%-86.44% and 97.13%-99.75%, respectively. The corresponding values of RESENet model were 98.08%-99.95%, 92.86%-100.00%, 98.51%-100.00%, 74.51%-100.00% and 98.85%-100.00%, respectively. The mean accuracy, mean sensitivity, mean specificity, mean PPV and mean NPV of ResNetV2 model were 97.60%, 75.58%, 98.75%, 63.44% and 98.76%, respectively. The corresponding values of RESENet model were 99.34% ( P<0.001), 99.57% ( P<0.001), 99.66% ( P<0.001), 90.20% ( P<0.001) and 99.66% ( P<0.001). Conclusion:Compared with the traditional ResNetV2 model, the artificial intelligence-assisted site identification model constructed by RESENNet, a hybrid neural network, shows significantly improved performance. This model can be used to monitor the integrity of the esophagogastroduodenoscopic procedures and is expected to become an important assistant for standardizing and improving quality of the procedures, as well as an significant tool for quality control of esophagogastroduodenoscopy.