Background Clinically, prophylactic anti-recurrence treatments for hepatocellular carcinoma (HCC) patients after radical surgery are extremely limited. Neoantigen based vaccine can generate robust anti-tumor immune response in several solid tumors but whether it could induce anti-tumor immune response in HCC and serve as a safe and effective prophylactic strategy for preventing postoperative HCC recurrence still remain largely unclear. Methods Personalized neoantigen vaccine was designed and immunized for 10 HCC patients with high risk of postoperative recurrence in a prime-boost schedule. The safety and immune response were assessed through adverse events, tissue sequencing, ELISpot, TCR sequencing. The clinical response was evaluated by recurrence-free survival (RFS) and personalized circulating tumor DNA (ctDNA) sequencing. Results In the 10 enrolled patients, no obvious adverse events were observed during neoantigen vaccinations. Until the deadline of clinical trial, 8 of 10 patients were confirmed with clinical relapse by imaging, the other 2 patients remained relapse-free. From receiving first neoantigen vaccination, the median RFS of 10 patients were 7.4 months. Among 7 patients received all planned neoantigen vaccinations, 5 of them demonstrated neoantigen-induced T cell responses and have significantly longer RFS after radical surgery than other 5 patients without responsive neoantigens or only with prime vaccination and propensity scores matching control patients (p = 0.035). Moreover, tracking personalized neoantigen mutations in ctDNA could provide real-time evaluation of clinical response in HCC patients during neoantigen vaccination and follow up. Conclusion Personalized neoantigen vaccine is proved as a safe, feasible and effective strategy for HCC anti-recurrence, and its progression could be sensitively monitored by corresponding neoantigen mutations in ctDNA, and thus provided solid information for individualized medicine in HCC. Trial registration This study was registered at Chinese Clinical Trial Registry; Registration number: ChiCTR1900020990.

Surgical resection remains primary curative treatment for patients with hepatocellular carcinoma (HCC) while over 50% of patients experience recurrence, which calls for individualized recurrence prediction and early surveillance. This study aimed to develop a machine learning prognostic model to identify high-risk patients after surgical resection and to review importance of variables in different time intervals. The patients in this study were from two centers including Eastern Hepatobiliary Surgery Hospital (EHSH) and Mengchao Hepatobiliary Hospital (MHH). The best-performed model was determined, validated, and applied to each time interval (0–1 year, 1–2 years, 2–3 years, and 3–5 years). Importance scores were used to illustrate feature importance in different time intervals. In addition, a risk heat map was constructed which visually depicted the risk of recurrence in different years. A total of 7,919 patients from two centers were included, of which 3,359 and 230 patients experienced recurrence, metastasis or died during the follow-up time in the EHSH and MHH datasets, respectively. 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 < 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.