Clinical Research Directory

Development of a Dynamic Prediction Model for Crohn's Disease-Related Intestinal Surgery Using Longitudinal Indices of Routine Blood Tests: A Single-Center Retrospective Cohort Study

This single-center retrospective cohort study aims to develop and internally validate a dynamic prediction model that uses longitudinal data from routinely collected blood tests to continuously assess the risk of Crohn's disease (CD)-related intestinal surgery, and to construct a simplified tool for clinical application. Patients with a confirmed diagnosis of CD and serial routine blood tests available during long-term follow-up will be included. Longitudinal trajectories of laboratory markers will be characterized, and their association with CD-related intestinal surgery will be evaluated. A full-variable dynamic prediction model will be built using dynamic random survival forest methodology, and a parsimonious model incorporating only the core laboratory markers will be developed via Bayesian joint model. The goal is to establish a practical, non-invasive, and dynamic risk assessment framework to support the transition from reactive to proactive long-term management of CD.

Dynamic Prediction Model for Patients with Unresectable Biliary Malignancies Receiving Systemic Chemotherapy Combined with Immunotherapy: a Multicenter, Observational Study

This study focused on the longitudinal tumor burden profile (tumor macro features, histopathological types and imaging features, etc.), liver function, health status, tumor biomarkers, and serological indicators of patients with unresectable biliary malignancies before chemotherapy combined with immunotherapy to build a dynamic prediction model. Based on this model, risk stratification of BTC patients was realized to explore which specific populations could safely initiate combination therapy. By constructing a risk stratification model, it can help clinicians to screen the best treatment population and provide a basis for safe treatment of high-risk patients.