基于肝脏硬度的病因非依赖性机器学习算法预测肝细胞癌
在韩国5155例多种慢性肝病成人中训练机器学习模型预测肝细胞癌,并在香港2732例和欧洲2384例前瞻性队列中验证,构建出以肝脏硬度测量为首要特征的SMART-HCC评分。该评分在香港和欧洲验证队列的Harrell C指数分别为0.89(95%CI 0.85-0.92)和0.91(95%CI 0.87-0.95),5年ROC曲线下面积均≥0.89,性能显著优于aMAP评分、Toronto HCC风险指数及7种乙型肝炎相关风险评分。
要点
- SMART-HCC评分基于9项临床特征,其中肝脏硬度测量重要性排名第一。
- 香港和欧洲验证队列的Harrell C指数分别为0.89和0.91,5年ROC曲线下面积均≥0.89。
- 采用0.043和0.080双截断值,低危组年肝细胞癌发生率0.09%-0.11%,高危组2.54%-4.64%。
核心结论
- SMART-HCC评分是一种有用的基于机器学习的工具,可帮助临床医生对慢性肝病患者进行肝细胞癌风险分层。
研究设计与样本
- 机器学习模型在韩国5155例患有各种慢性肝病的成人中训练以预测肝细胞癌,并在来自香港(N=2732)和欧洲(N=2384)的2个前瞻性队列中进一步测试。
- 模型性能根据Harrell C指数和时间依赖受试者工作特征(ROC)曲线评估。
主要发现
- 开发了SMART-HCC评分,这是一种基于肝脏硬度的机器学习肝细胞癌风险评分,肝脏硬度测量在9项临床特征中排名最重要。
- SMART-HCC评分在香港和欧洲验证队列中的Harrell C指数分别为0.89(95%CI 0.85-0.92)和0.91(95%CI 0.87-0.95)。
- SMART-HCC评分在香港和欧洲两个验证队列中预测5年肝细胞癌的ROC曲线下面积均≥0.89。
- SMART-HCC评分的性能显著优于现有肝细胞癌风险评分,包括aMAP评分、Toronto HCC风险指数和7种乙型肝炎相关风险评分。
- 使用0.043和0.080双截断值,在香港和欧洲验证队列中,低危组年肝细胞癌发生率为0.09%-0.11%,高危组为2.54%-4.64%。
关键数值与推荐
- SMART-HCC评分采用0.043和0.080双截断值进行风险分层。
- 低危组年肝细胞癌发生率为0.09%-0.11%,高危组为2.54%-4.64%。
临床怎么用
- 作者认为SMART-HCC评分是一种有用的基于机器学习的工具,可帮助临床医生对慢性肝病患者进行肝细胞癌风险分层。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND & AIMS: The existing hepatocellular carcinoma (HCC) risk scores have modest accuracy, and most are specific to chronic hepatitis B infection. In this study, we developed and validated a liver stiffness-based machine learning algorithm (ML) for prediction and risk stratification of HCC in various chronic liver diseases (CLDs). METHODS: MLs were trained for prediction of HCC in 5155 adult patients with various CLDs in Korea and further tested in 2 prospective cohorts from Hong Kong (HK) (N = 2732) and Europe (N = 2384). Model performance was assessed according to Harrell's C-index and time-dependent receiver operating characteristic (ROC) curve. RESULTS: We developed the SMART-HCC score, a liver stiffness-based ML HCC risk score, with liver stiffness measurement ranked as the most important among 9 clinical features. The Harrell's C-index of the SMART-HCC score in HK and Europe validation cohorts were 0.89 (95% confidence interval, 0.85-0.92) and 0.91 (95% confidence interval, 0.87-0.95), respectively. The area under ROC curves of the SMART-HCC score for HCC in 5 years was ≥0.89 in both validation cohorts. The performance of SMART-HCC score was significantly better than existing HCC risk scores including aMAP score, Toronto HCC risk index, and 7 hepatitis B-related risk scores. Using dual cutoffs of 0.043 and 0.080, the annual HCC incidence was 0.09%-0.11% for low-risk group and 2.54%-4.64% for high-risk group in the HK and Europe validation cohorts. CONCLUSIONS: The SMART-HCC score is a useful machine learning-based tool for clinicians to stratify HCC risk in patients with CLDs.
引用
- Lin H, Li G, Delamarre A, et al. A Liver Stiffness-Based Etiology-Independent Machine Learning Algorithm to Predict Hepatocellular Carcinoma. Clin Gastroenterol Hepatol. 2023. PMID: 37993034. doi:10.1016/j.cgh.2023.11.005
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。