Prospective Validation of AI Models for Predicting Recurrence in Early-Stage Liver Cancer After Surgery

What this Trial Is About

Researchers are evaluating a deep learning model to predict aggressive patterns of cancer recurrence in patients with early-stage hepatocellular carcinoma (HCC) after liver surgery. This observational study aims to find out if the AI model can accurately identify patients at high risk of cancer returning within two years after surgery. The study is sponsored by Tongji Hospital and focuses on patients undergoing curative liver resection without prior or additional therapies, as well as those receiving real-world neoadjuvant or adjuvant treatments. Participants will be divided into two groups: one receiving standard curative liver resection alone and another receiving surgery combined with various physician-directed therapies such as targeted drugs or immunotherapy. Before surgery, patients will undergo MRI scans and provide clinical and pathological data to help the AI model predict recurrence risk. After surgery, all participants will have standard imaging follow-up for two years to validate how well the AI predicts recurrence. During the study, participants will provide clinical information and undergo routine imaging surveillance to monitor cancer recurrence and overall survival for up to five years. Researchers will measure the accuracy of the AI model in predicting aggressive recurrence within two years as the primary outcome. Secondary outcomes include recurrence-free and overall survival over longer periods. The study involves no experimental treatments but carefully observes real-world outcomes and AI predictions over time.

AI-Based Prediction of HCC Recurrence Patterns After Resection (APAR)