https://www.selleckchem.com/products/BIBF1120.html The XGBoost model achieved the best discrimination with a c-index of 0.713 in internal validation cohort. Kaplan-Meier curves succeed to stratify external validation cohort into different risk groups (p less then 0.05 in all comparisons). Tumor characteristics contribute more to HCC relapse in 0 to 1 year while HBV infection and smoking affect patients' outcome largely in 3 to 5 years. Based on machine learning prediction model, the peak of recurrence can be predicted for individual HCC patients. Therefore, clinicians can apply it to personalize the management of postoperative survival.Recent studies have reported a close association between circRNAs and cancer development. CircRNAs have been recognized to be involved in various biological processes. Up to now, the function of circRNAs in hepatocellular carcinoma (HCC) is still poorly known. qRT-PCR was used to test circ_0014717 expression in HCC tissue samples and cells was determined. It was shown that circ_0014717 was significantly decreased in HCC. Then, we observed overexpression of circ_0014717 obviously repressed HCC cell growth, migration and invasion. Next, we predicted circ_0014717 acted as a sponge of miR-668-3p. miR-668-3p has been reported to participate in several diseases. In our work, it was shown miR-668-3p was greatly increased in HCC and the direct binding sites between circ_0014717 and miR-668-3p were validated. In addition, B-cell translocation gene 2 (BTG2) is closely involved in cellular carcinogenic processes. BTG2 was predicted as a target for miR-668-3p. By performing rescue assays, we demonstrated that circ_0014717 repressed HCC progression via inhibiting BTG2 expression and sponging miR-668-3p. It was manifested loss of circ_0014717 induced HCC progression, which was reversed by BTG2 in Hep3B cells. In conclusion, our findings illustrated a novel circ_0014717/miR-668-3p/BTG2 regulatory signaling pathway in HCC.Cellular ribonucleic acids (