206P Development of a machine-learning model on pre-treatment characteristics to predict long-term survivorship to atezolizumab plus bevacizumab in advanced hepatocellular carcinoma

Combination immunotherapy with atezolizumab and bevacizumab (A+B) is one of the recommended first-line treatments for advanced hepatocellular carcinoma (aHCC). However, only a subset of patients derived long-term survival benefit. This study aimed to develop machine learning models to predict overall survival (OS), as well as long-term and short-term survivorship (LTS and STS, defined as OS > 24 or < 6 months from treatment initiation) in patients receiving A+B.