Objective:To compare the clinical effect of three indwelling methods of plastic biliary stent on relieving obstructive jaundice caused by unresectable hilar cholangiocarcinoma.Methods:A retrospective study was performed on data of 61 patients with obstructive jaundice caused by unresectable hilar cholangiocarcinoma from April 2014 to December 2020 in Cancer Hospital, Chinese Academy of Medical Sciences. Plastic biliary stent placement was used to relieve jaundice, including 18 cases of intragastric indwelling at the end of biliary stent, 31 cases of duodenal papilla indwelling at the end of biliary stent, and 12 cases of horizontal portion of duodenum indwelling at the end of biliary stent. Incidence of fever within 2 weeks, perioperative mortality, 90-day obstruction rate, and median stent patency period were followed up and the results were analyzed.Results:The incidence of fever within 2 weeks of the three groups were significantly different [66.7% (12/18), 58.1% (18/31) and 16.7% (2/12), χ2=7.30, P=0.026]. There were no statistically differences in the perioperative mortality [0 (0/16), 3.2% (1/31) and 0 (0/10), χ2=1.09, P=1.000], 90-day obstruction rate [52.9% (9/17), 48.3% (14/29) and 40.0% (4/10), χ2=1.91, P=0.589], or median stent patency period (66.0 d, 91.5 d and 94.0 d, Z=4.96, P=0.084) among three groups. Conclusion:Patients with biliary plastic stents with ends placed at the horizontal portion of the duodenum show lower incidence of fever within two weeks after implantation, and similar median stent patency period, 90-day obstruction rate and perioperative mortality compared with intragastric indwelling and duodenal papilla indwelling groups. Therefore, biliary plastic stents with ends placed at the horizontal portion of the duodenum should be recommended as the preferred procedure.

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.