Five-year on-treatment variables-based PPACS model predicts subsequent hepatocellular carcinoma in entecavir/tenofovir-treated patients

Abstract

Considering the lower risk of hepatocellular carcinoma (HCC) in chronic hepatitis B (CHB) patients receiving long-term potent antiviral therapy, models predicting HCC after 5 years of therapy are needed. We conducted a multicenter retrospective cohort study to construct and validate a model predicting HCC after 5 years of entecavir (ETV) or tenofovir (TFV) therapy for CHB. The endpoint was HCC after 5 years of ETV/TFV therapy. Information on age, sex, liver cirrhosis (assessed by diagnosis code and confirmed by clinical findings) and type of antiviral agent was obtained at baseline (initiation of ETV/TFV). Laboratory values were collected at baseline and 5 years. Risk factors for HCC were identified in the training set and the final prediction model was validated using the test set. Among 7542 patients, 345 (4.6%) developed HCC after 5 years of ETV/TFV therapy. HCC risk after 5 years of ETV/TFV therapy was increased by 4-fold in patients with liver cirrhosis than in those without cirrhosis at baseline. Furthermore, Platelet counts and Prothrombin time at 5 years, Age at baseline and Sex were associated with risk of HCC and were incorporated into a prediction model, PPACS. PPACS showed a good performance with a time-dependent area under the curve of 0.80 (95% confidence interval, 0.75-0.85) at 8-year of ETV/TFV therapy, a Brier score of 0.031 and an integrated Brier score of 0.006 in the test set. In conclusion, the PPACS model provides a reliable assessment of HCC risk after 5 years of ETV/TFV therapy (https://ppacs.shinyapps.io/shiny_app_up/).

Keywords: chronic hepatitis B; hepatocellular carcinoma; long-term; prediction; validation.