Kim HY, Lampertico P, Nam JY, et al. - An artificial intelligence-assisted prediction model of hepatocellular carcinoma (HCC) in patients with chronic hepatitis B (CHB) was developed and validated.

• The model was developed using a gradient-boosting machine (GBM) algorithm; a total number of 6,051 patients with CHB who received entecavir or tenofovir therapy were involved from four hospitals in Korea.

• Korean (5,817 patients from 14 Korean centers) and Caucasian (1,640 from 11 Western centers) PAGE-B cohorts were independently established as two external validation cohorts.

• The new HCC prediction model (PLAN-B) included the following 10 baseline parameters: the presence of cirrhosis, age, platelet count, antiviral agent used (ETV or TDF), gender, serum ALT levels, serum HBV DNA, albumin, and bilirubin levels, and HBeAg status.

• In prediction of HCC development, PLAN-B model exhibited not only satisfactory performance but also outperformed other risk scores in the validation.