Machine Learning Model for Predicting Hepatocellular Carcinoma Development in Patients With Hepatitis B Virus‐Related Cirrhosis Receiving Antiviral Therapy

Few prediction models have been specifically designed to evaluate the risk of hepatocellular carcinoma (HCC) in patients with chronic hepatitis B and cirrhosis. This study aimed to develop a machine learning-based prediction model to assess the risk of developing HCC in patients with hepatitis B virus (HBV)-related cirrhosis undergoing nucleos(t)ide analogue (NA) therapy. We included 1592 patients with HBV-related cirrhosis who had received entecavir, tenofovir disoproxil fumarate, or tenofovir alafenamide for at least 1 year. Patients were randomized in a 2:1 ratio into derivation or validation groups, and the prediction model was developed using the eXtreme Gradient Boosting (XGBoost) algorithm. The cumulative incidence of HCC for all patients at 5, 8, and 10 years was 15.2%, 22.7%, and 25.7%, respectively. Our ML-HCC model incorporated six parameters: serum albumin and platelet count at treatment initiation, and age, platelet count, serum aspartate transaminase, and serum AFP after 1 year of NA therapy. In the validation group, the AUROCs of the ML-HCC model ranged from 0.79 to 0.80 over 3 to 10 years, outperforming extant models including APA-B, PLAN-B, PAGE-B, mPAGE-B, REACH-B, and CU-HCC (AUROCs: 0.61-0.73, p < 0.05). Risk stratification showed the 10-year incidences of HCC for the low-, intermediate-, and high-risk groups were 9%, 26%, and 67%, respectively. The proposed machine learning model for predicting development of HCC exhibited good predictive performance in patients with HBV-related cirrhosis undergoing NA therapy.