Construction of a Clinical Prediction Model for In-Hospital Rebleeding in Patients With Acute Non-Venous Upper Gastrointestinal Bleeding

ANVUGIB is a serious condition that can cause symptoms like vomiting blood or passing black stools. Although treatments have improved, about 10% to 30% of patients experience rebleeding shortly after their initial treatment, which increases the risk of death.

Currently, doctors use tools like the Glasgow-Blatchford Score, Rockall Score, and AIM65 Score to predict how patients with ANVUGIB might recover. However, these tools are not very effective at identifying patients who are at risk for rebleeding. This study aims to create a new, more accurate prediction model to help doctors identify high-risk patients earlier. The investigators believe that a new predictive model, which combines patient symptoms, lab test results, and imaging findings, will improve the ability to identify patients at high risk of rebleeding compared to existing tools.The goal is to provide doctors with a more reliable tool to guide their decisions, such as when to give preventive treatments or increase monitoring. This could lead to better outcomes and reduce the risk of complications or death.

This study uses patient data collected during routine care to develop and test the new model, ensuring the findings are directly applicable to real-world clinical settings.