直接作用抗病毒药物 (DAA) 显着改善了慢性丙型肝炎 (HCV) 的治疗；然而，持续病毒学应答（SVR）后的随访通常会忽略肝脏相关事件（LRE）的风险。本研究引入并验证了人工智能安全评分（AI-Safe-C评分）来评估非肝硬化患者在成功进行DAA治疗后发生LRE的风险。训练随机生存森林模型来预测913例非肝硬化HCV中的LRE在韩国进行 SVR 后的患者，并在来自香港和法国的联合队列中进行了进一步测试（N = 1264）。该模型的性能使用 Harrell 的 C 指数和时间依赖性受试者工作特征曲线 (AUROC) 下面积进行评估。AI-Safe-C 评分包含肝脏硬度测量 (LSM)、年龄、性别和其他六项指标生化测试（LSM 被列为 9 个临床特征中最重要的）在外部验证队列中预测 LRE 的 C 指数为 0.86（95% 置信区间 [CI]：0.82-0.90）。其 3 年和 5 年 LRE AUROC 分别为 0.88（95% CI，0.84-0.92）和 0.79（95% CI，0.71-0.87），对于肝细胞癌，C 指数为 0.87（95% CI） ，0.81-0.92），3 年和 5 年 AUROC 分别为 0.88（95%CI，0.84-0.93）和 0.82（95%CI，0.75-0.90）。使用 0.7 的截止值，高危组内的 5 年 LRE 发生率在 3.2% 至 6.2% 之间，反映了在晚期纤维化个体中观察到的发生率，与显着较低的 0.2% 至 6.2% 发生率形成鲜明对比。低风险组为 0.6%。AI-Safe-C 评分是一个有用的工具，可用于识别患有 LRE 的较高风险的无肝硬化患者。 SVR 后 LSM 集成在 AI-Safe-C 评分中，在预测未来 LRE 方面发挥着关键作用。AI-Safe-C 评分引入了 DAA 治疗后非肝硬化患者管理的范式转变，传统上不包括在 LRE 常规监测方案中的队列。通过准确识别 LRE 风险相对较高的亚组（类似于晚期纤维化患者），该预测模型有助于战略性地重新分配监测和临床资源。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。

Direct-acting antivirals (DAAs) have considerably improved chronic hepatitis C (HCV) treatment; however, post-sustained virological response (SVR) follow-up typically neglects the risk of liver-related events (LREs). This study introduces and validates artificial intelligence-safe score (AI-Safe-C score) to assess the risk of LREs in non-cirrhotic patients after successful DAA treatment.The random survival forest model was trained to predict LREs in 913 non-cirrhotic HCV patients after SVR in Korea and was further tested in a combined cohort from Hong Kong and France (N = 1264). The model's performance was assessed using Harrell's C-index and the area under the time-dependent receiver operating characteristic curve (AUROC).The AI-Safe-C score, which incorporated liver stiffness measurement (LSM), age, sex, and six other biochemical tests-with LSM being ranked as the most important among 9 clinical features-demonstrated a C-index of 0.86 (95% confidence interval [CI]: 0.82-0.90) in predicting LREs in an external validation cohort. It achieved 3- and 5-year LRE AUROCs of 0.88 (95%CI, 0.84-0.92) and 0.79 (95%CI, 0.71-0.87), respectively, and for hepatocellular carcinoma, a C-index of 0.87 (95%CI, 0.81-0.92) with 3- and 5-year AUROCs of 0.88 (95%CI, 0.84-0.93) and 0.82 (95%CI, 0.75-0.90), respectively. Using a cut-off of 0.7, the 5-year LRE rate within a high-risk group was between 3.2% and 6.2%, mirroring the incidence observed in individuals with advanced fibrosis, in stark contrast to the significantly lower incidence of 0.2% to 0.6% in a low-risk group.AI-Safe-C score is a useful tool for identifying patients without cirrhosis who are at higher risk of developing LREs. The post-SVR LSM, as integrated within the AI-Safe-C score, plays a critical role in predicting future LREs.The AI-Safe-C score introduces a paradigm shift in the management of non-cirrhotic patients post-DAA treatment, a cohort traditionally not included in routine surveillance protocols for LREs. By accurately identifying a subgroup at a comparably high risk of LREs, akin to those with advanced fibrosis, this predictive model facilitates a strategic reallocation of surveillance and clinical resources.Copyright © 2024 European Association for the Study of the Liver. Published by Elsevier B.V. All rights reserved.