乙型肝炎表面抗原 (HBsAg) 血清清除后，肝细胞癌 (HCC) 和肝功能失代偿的风险仍然存在。本研究旨在开发和验证机器学习模型，以预测 HBsAg 血清清除后发生肝脏相关结局 (LRO) 的风险。 韩国和日本的 6 个中心连续招募了 4,787 名 2000 年至 2022 年间实现 HBsAg 血清清除的患者。香港全港范围的数据库，包括培训组 (n=944)、内部验证组 (n=1,102) 和外部验证组 (n=2,741)。在每个队列中开发并比较了三种基于机器学习的模型。主要结局是任何 LRO 的发生，包括 HCC、失代偿和肝脏相关死亡。在中位随访 55.2（四分位距 = 30.1-92.3）个月期间，确认了 123 例 LRO（1.1%/人年） ）在韩国队列中。选择训练队列中预测性能最佳的模型作为最终模型（指定为 PLAN-B-CURE），该模型使用梯度增强算法和 7 个变量（年龄、性别、糖尿病、饮酒、肝硬化、白蛋白和血小板计数）。与之前的 HCC 预测模型相比，PLAN-B-CURE 在训练队列中显示出显着优越的准确性（c 指数：0.82 vs. 0.63-0.70，所有 P<0.001；受试者工作特征曲线下面积：0.86 vs. 0.62- 0.72，所有 P<0.01；精确率-召回率曲线下面积：0.53 vs. 0.13-0.29，所有 P<0.01）。 PLAN-B-CURE 显示了可靠的校准功能（Hosmer-Lemeshow 检验 P>0.05），并且这些结果在内部和外部验证队列中得到了重现。这种由 7 个变量组成的新型机器学习模型提供了 HBsAg 血清清除后 LRO 的可靠风险预测可用于个性化监测。版权所有 © 2024 欧洲肝脏研究协会。由 Elsevier B.V. 出版。保留所有权利。

The risk of hepatocellular carcinoma (HCC) and hepatic decompensation persists after hepatitis B surface antigen (HBsAg) seroclearance. This study aimed to develop and validate a machine learning model to predict the risk of liver-related outcomes (LROs) following HBsAg seroclearance.A total of 4,787 consecutive patients who achieved HBsAg seroclearance between 2000 and 2022 were enrolled from 6 centers in South Korea and a territory-wide database in Hong Kong, comprising the training (n=944), internal validation (n=1,102), and external validation (n=2,741) cohorts. Three machine learning-based models were developed and compared in each cohort. The primary outcome was the development of any LRO, including HCC, decompensation, and liver-related death.During a median follow-up of 55.2 (interquartile range=30.1-92.3) months, 123 LROs were confirmed (1.1%/person-year) in the Korean cohort. A model with the best predictive performance in the training cohort was selected as the final model (designated as PLAN-B-CURE), which was constructed using a gradient boosting algorithm and 7 variables (age, sex, diabetes, alcohol consumption, cirrhosis, albumin, and platelet count). Compared to previous HCC prediction models, PLAN-B-CURE showed significantly superior accuracy in the training cohort (c-index: 0.82 vs. 0.63-0.70, all P<0.001; area under the receiver operating characteristic curve: 0.86 vs. 0.62-0.72, all P<0.01; area under the precision-recall curve: 0.53 vs. 0.13-0.29, all P<0.01). PLAN-B-CURE showed a reliable calibration function (Hosmer-Lemeshow test P>0.05) and these results were reproduced in the internal and external validation cohorts.This novel machine learning model consisting of 7 variables provides reliable risk prediction of LRO after HBsAg seroclearance that can be used for personalized surveillance.Copyright © 2024 European Association for the Study of the Liver. Published by Elsevier B.V. All rights reserved.