Epigenetic Perspectives and Their Prognostic Value in Early Recurrence After Hepatocellular Carcinoma Resection

Background/Objectives: The post-hepatectomy survival of patients with hepatocellular carcinoma (HCC) faces challenges due to high recurrence rates, especially early recurrence (ER). We investigated DNA methylation in HCC and developed a methylation-based model for ER prediction (MER). Methods: We studied HCC patients with ER within a year post-hepatectomy, comparing them to those who remained recurrence-free (RF) for 5 years. In a testing set, we examined genome-wide methylation profiles to identify differences between ER and RF. Validation in an independent cohort confirmed candidate markers using real-time quantitative methylation-specific PCR (qMSP). We constructed MER by incorporating identified gene methylation, clinical information, and serum protein marker, and evaluated its predictive performance using ROC analysis and Cox regression. Results: Distinct signatures of hypermethylation and hypomethylation were observed between ER and RF, as well as between cirrhotic and non-cirrhotic groups. Significant aberrant methylation pathways, including FGFR signaling, the PI3K network, and the MAPK pathway, were observed in non-cirrhotic ER patients. Conversely, cirrhotic ER patients showed notable associations with Wnt/beta-catenin signaling, cell adhesion, and migration mechanisms. Through qMSP analysis, we identified ER-associated genes, including BDNF, FOXL2, LMO7, NCAM1, NEIS3, PLA2G7, and LTB4R. MER demonstrated strong predictive ability for ER, with an AUC of 0.855, surpassing current indicators such as AFP, tumor size, and BCLC stage. Combining different predictors resulted in heightened AUC values. Importantly, the inclusion of MER yielded to the highest AUC of 0.952, underscoring the substantial contribution of MER to predictive accuracy. Conclusions: This study discovered the involvement of aberrant DNA methylation in HCC with early recurrence. The MER outperforms clinicopathological predictors and achieves robust prediction capabilities in identifying patients at risk of ER.