65‐gene based risk score predicts recurrence and survival in hepatocellular carcinoma

We aimed to develop an easy‐to‐use risk score with a limited number of genes that can predict the prognosis of hepatocellular carcinoma (HCC) patients. In 139 patients, we identified 65 genes whose expression patterns were significantly associated with overall survival and recurrence in two independent HCC cohorts. The risk score was developed by using Cox coefficient values for the 65 genes from the training set. The risk score was a highly significant predictor of both overall survival and recurrence in the test cohort. The risk score also predicted the prognosis of 65‐base invasion. High‐risk HCC was characterized by activation of IGFR (P = 2.2 × 10–4) and AKT (P = 0.003), whereas low‐risk disease was associated with active mutations of CTNNB1 (P= 0.05). Our new risk score can identify two clinically distinct HCC subtypes in a simple and highly reproducible manner across multiple data sets.