Search

Background & Aims: Currently, patients with hepatocellular carcinoma (HCC) in the United States are assigned a uniform score relative to the median Model for End-Stage Liver Disease (MELD) at transplant after a minimum 6-month waiting period. The authors developed a risk stratification model for patients with HCC using the available and objective variables at time of listing., Methods: Adult liver transplant candidates with approved HCC exception in the Organ Procurement and Transplantation Network database from 2015-2022 were identified. Cox regression analysis, as well as machine learning models (random survival forest and neural network), were used to develop models predicting waitlist dropout. Predicted waitlist dropout for patients with HCC was scaled to patients without exception using MELD 3.0., Results: There were 18,273 patients with HCC listed for liver transplant with a median MELD 3.0 of 11 (interquartile range, 8-15) and α-fetoprotein of 6 ng/mL (interquartile range, 4-17 ng/mL). Because all models performed similarly, a parsimonious Cox-based model composed of MELD 3.0, α-fetoprotein, tumor burden, and Model for Urgency for Liver Transplantation in HCC, was selected, with a C-statistic of 0.71 (95% CI, 0.69-0.74) for 6-month dropout in the validation set, outperforming previous models, including HALT-HCC (Hazard Associated with Liver Transplantation for HCC), deMELD (Dropout Equivalent MELD), and MELD-Eq (MELD Equivalent)., Conclusions: An urgency-based priority system for patients with HCC, similar to MELD for patients with chronic liver disease, is achievable with a parsimonious model incorporating α-fetoprotein, MELD 3.0, and tumor size. This approach can be applied to the liver allocation system to prioritize patients with HCC and can inform decision making regarding urgency weights for exception cases in the upcoming continuous distribution system., (Copyright © 2024 AGA Institute. Published by Elsevier Inc. All rights reserved.)