Early relapse after hepatectomy is a significant challenge in treating hepatocellular carcinoma (HCC). This study aimed to develop and validate a novel nomogram model for predicting early relapse and survival post-hepatectomy. A multicenter retrospective analysis of 1,505 patients with HCC was conducted, with patients divided into training (1,053) and validation (452) cohorts. A machine learning-based nomogram was created using preoperative clinical data and postoperative pathological characteristics to predict early relapse and survival.

Results showed a median time to early relapse of 7 months and a median time from early relapse to death of 19 months. The nomogram’s concordance indexes for disease-free and overall survival were 0.741 and 0.739, respectively, demonstrating good predictive accuracy. This model outperformed preoperative models and seven other HCC staging systems. Patients in intermediate- and high-risk groups had higher probabilities of early and critical recurrence, while low-risk patients had higher probabilities of late and local recurrence. The postoperative nomogram is a valuable tool for predicting early recurrence and survival, aiding clinical treatment decisions for patients with HCC.

Reference: He Y, Luo L, Shan R, et al. Development and Validation of a Nomogram for Predicting Postoperative Early Relapse and Survival in Hepatocellular Carcinoma. J Natl Compr Canc Netw. 2023;22(1D):e237069. doi: 10.6004/jnccn.2023.7069.