Fusion Gene Detection Enhances Clinical Outcome Prediction of Hepatocellular Carcinoma Through Machine Learning Analyses.

Hepatocellular carcinoma (HCC) is one of the most lethal malignancies for humans. Assessing the clinical outcomes of HCC remains challenging. In this study, a panel of 20 fusion genes in 200 HCC samples was analyzed to predict the recurrence and survival rates of patients with HCC undergoing surgical interventions using machine learning models. The results showed that fusion genes, Milan criteria, serum α-fetoprotein (AFP), and pathology grade had moderate predictive accuracy for HCC recurrence. However, the combination of selected fusion genes with these clinical parameters significantly enhanced the prediction accuracy of each parameter. When models of fusion genes were applied to predict the 3-year survival rate of patients with HCC, they yielded a prediction accuracy of 72.4% in both the training and the testing cohorts. These results outperformed those from the Milan criteria (61.2% training and 58.8% testing), pathology grade (50% training and 49% testing), and serum AFP (66.3% training and 70.2% testing). The combination of a fusion gene panel with Milan criteria, pathology grade, or serum AFP level yielded significantly improved results compared to those produced by these clinical parameters alone. As a result, examining the fusion gene status of HCC samples may hold promise as a new and improved approach to assessing the clinical outcomes of this disease.