Beijing Friendship Hospital

In managing bleeding gastroduodenal ulcers, endoscopic control of bleeding is the first line treatment-further bleeding after endoscopic hemostasis is associated with a 3-fold increase in mortality. Large ulcer size (> 20 mm) predicts further bleeding. These ulcers erode into arteries of significant size (>2 mm) from either the gastro-duodenal or left gastric arterial complexes. An over-the-scope clip is an endoscopic clamp device with a high tensile strength. It can compress sizeable arteries, and firmly anchor onto the ulcer base avoiding recurrent bleeding from clip dislodgement. It therefore offers secure and durable hemostasis.
In the proposed randomized controlled trial, the investigators hypothesize that after initial endoscopic control of bleeding from large gastro-duodenal ulcers (20 mm in size or more), adding an OTSC can prevent recurrent bleeding and improve patients' outcomes. Investigators enroll patients with bleeding from large ulcers as defined. After initial endoscopic control of bleeding using injection with diluted epinephrine, these patients are randomized, during endoscopy, to receive standard treatment (thermo-coagulation or hemo-clips) or an added OTSC. The primary endpoint is recurrent bleeding over 30 days confirmed on endoscopy. Secondary endpoints include the need for rescue treatment; endoscopic, angiographic embolization or surgery, red blood cell (RBC) transfusion, hospitalization, and bleeding related and all-cause mortality.

Ovarian tumors are a common disease that threatens women's health. They are insidious in onset, have over ten pathological types, and exhibit diverse biological behaviors, making accurate diagnosis a key factor in clinical decision-making and improving prognosis. Introducing AI technology to establish an auxiliary diagnosis system composed of multi-dimensional clinical data, including medical imaging and tumor markers, will greatly enhance diagnosis efficiency by predicting the pathological types of common ovarian tumors.
Our research group has innovatively developed an AI-based ultrasound intelligent auxiliary diagnosis software for ovarian tumors, which has been clinically validated to be effective. This project will build on this by: (1) utilizing a wealth of multi-center retrospective clinical data to combine ultrasound, MRI images, physiological, pathological, and laboratory data to form the first multi-modal ovarian tumor public dataset supporting AI tasks; (2) using convolutional neural network technology to realize multi-modal image multi-classification intelligent recognition on this dataset based on surgical pathology as the standard, and then fuse features at the level of clinical data with the intelligent recognition model to train and validate an auxiliary diagnosis model for predicting the top ten pathological types of ovarian tumors; (3) applying privacy computing and federated learning methods to conduct multi-center, prospective validation and optimization of the above model, ultimately forming a clinical auxiliary diagnosis system that can predict the pathological types of most ovarian tumors and apply it to clinical practice.

Prospective double blind randomized controlled trial. By randomizing patients undergoing kidney transplantation into a conventional catecholamine drug (dobutamine) blood pressure maintenance group and a terlipressin-complexed dobutamine group, we compared the effect of intraoperative blood pressure maintenance and the dosage of the vasoactive drug, postoperative graft function, delayed graft function, and other related complications between the two groups, in order to demonstrate whether the use of terlipressin for blood pressure regulation during kidney transplantation is superior to the existing treatments.