Yingji Sun

Abstract Liver transplant (LT) is a life-saving treatment for patients with cirrhosis and/or hepatocellular carcinoma (HCC), but organ shortages and suboptimal donor-recipient matching remain major challenges and existing donor-recipient matching risk models offer limited predictive accuracy. Our study aims to develop a machine-learning-based model to predict and rank long-term post-transplant survival.

1 Introduction Long-term outcomes of liver transplant (LT) patients are compromised by incidences of graft fibrosis (GF) and cirrhosis. Particularly, LT recipients can develop new or recurrent liver disease, including hepatitis C virus infection (HCV), metabolic dysfunction-associated steatotic liver disease (MASLD), or its aggressive form, metabolic dysfunction-associated steatohepatitis (MASH) [1, 2]. Thus, grafts can develop fibrosis and subsequently cirrhosis, leading to graft failure.