Machine learning stratifies HCC recurrence risk after surgery

A new model predicts recurrence and mortality for hepatocellular carcinoma (HCC) patients post-surgery, enhancing patient management.

  • The Random Survival Forest model identifies high-risk patients, showing a 5-year recurrence rate of 87.3% vs. 51.5% in low-risk patients (training) and 75.9% vs. 64.8% (validation).
  • High-risk patients have a 5-year mortality rate of 56.0% vs. 15.3% (training) and 50.0% vs. 23.1% (validation).

This model guides adjuvant therapy decisions, potentially improving long-term outcomes.

  • Key factors include diabetes, tumor numbers, and albumin levels.

Journal Article by Jia JJ, Wang YY (…) Jiang HJ et 3 al. in Hepatobiliary Pancreat Dis Int

Copyright © 2025 First Affiliated Hospital, Zhejiang University School of Medicine in China. Published by Elsevier B.V. All rights reserved.

read the whole article in Hepatobiliary Pancreat Dis Int

open it in PubMed