文献速递肝病消化道肿瘤与早癌

机器学习模型预测肝细胞癌预后的开发与验证

Development and Validation of a Machine Learning Model to Prognosticate Hepatocellular Carcinoma.
PubMed 文献 · Aliment Pharmacol Ther · 2026-06-18

该研究基于亚洲和美国五家三级医疗机构的1102例肝细胞癌(HCC)患者,构建并验证了整合肝功能生物标志物和肿瘤特征的LCRN指数(梯度提升决策树模型)。外部验证中,LCRN指数对1年、3年、5年预后的AUC分别为0.79、0.77、0.75,数值上高于ALBI分级和BCLC分期,且校准更优。

要点

  • LCRN指数纳入糖尿病、腹水、肝性脑病、白蛋白、胆红素、AFP及最大肿瘤结节直径。
  • 外部验证中LCRN指数1年、3年、5年AUC分别为0.79、0.77、0.75,高于ALBI和BCLC。
  • LCRN指数校准优于ALBI分级和BCLC分期,但需进一步验证。

核心结论

  • LCRN指数是预测HCC预后的有前景工具,若进一步验证可能对HCC管理有潜在临床意义。

研究设计与样本

  • 连续纳入来自亚洲和美国五家国际三级机构的1102例HCC患者,分为推导队列(n=627)、内部验证队列(n=270)和外部验证队列(n=205)。
  • 采用基于Cox比例风险框架的梯度提升决策树模型构建LCRN指数。
  • 使用Harrell一致性指数(C-index)评估区分度,并与ALBI分级、BCLC分期和Cox回归模型比较;使用积分Brier评分和校准图评估校准度。

主要发现

  • 中位(IQR)年龄为66.0(58.0-73.0)岁,中位(IQR)体重指数为23.9(22.1-26.1)kg/m2,男性占77.2%。
  • LCRN指数包含2型糖尿病、腹水、肝性脑病、白蛋白、胆红素、AFP和最大肿瘤结节直径。
  • 外部验证队列中,LCRN指数的1年AUC为0.79,3年AUC为0.77,5年AUC为0.75,数值上高于ALBI分级和BCLC分期。
  • LCRN指数的校准优于ALBI分级和BCLC分期。

关键数值与推荐

  • LCRN指数外部验证1年AUC 0.79、3年AUC 0.77、5年AUC 0.75。
  • LCRN指数包含2型糖尿病、腹水、肝性脑病、白蛋白、胆红素、AFP和最大肿瘤结节直径。

临床怎么用

  • LCRN指数可用于HCC患者预后分层,辅助临床管理决策,但需进一步外部验证。

局限性

  • 原文未明确报告局限性。

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: Prognostic models for hepatocellular carcinoma (HCC) may have limited accuracy. We aimed to construct and validate a novel prognostic model for HCC that incorporates biomarkers for liver function and tumour characteristics. METHODS: Consecutive participants (n = 1102) with HCC from five international tertiary institutions in Asia and the U.S. comprised the derivation (n = 627), internal validation (n = 270) and external validation (n = 205) cohorts. The Liver Cancer Risk predictioN (LCRN) Index was constructed using a gradient-boosted decision tree model based on the Cox proportional hazards framework. The discriminative performance of the LCRN Index was evaluated using Harrell's concordance index (C-index) and compared to the albumin bilirubin grade (ALBI), Barcelona Clinic for Liver Cancer (BCLC) staging and Cox regression model. Model calibration was assessed using the integrated Brier score and calibration plots. RESULTS: The median (IQR) age was 66.0 (58.0-73.0) years, median (IQR) body mass index was 23.9 (22.1-26.1) kg/m2 and 77.2% were male. The LCRN Index comprised type 2 diabetes mellitus, ascites, hepatic encephalopathy, albumin, bilirubin, AFP and diameter of largest tumour nodule. In the external validation cohort, the LCRN Index (1-year area under the receiver operating curve [AUC]: 0.79; 3-year AUC: 0.77; 5-year AUC: 0.75) was numerically higher than the ALBI grade and BCLC stage for prognosticating HCC. The LCRN Index demonstrated improved calibration compared to the ALBI grade and BCLC stage. CONCLUSION: The LCRN index is a promising tool for prognosticating HCC. If further validated, these data may have potential clinical implications for the management of HCC.

来源:Aliment Pharmacol Ther,查看原文。版权归原作者所有。

引用

  1. Lim RY, Selvakumar V, Syn N, et al. Development and Validation of a Machine Learning Model to Prognosticate Hepatocellular Carcinoma. Aliment Pharmacol Ther. 2026. PMID: 42311172. doi:10.1111/apt.70797

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。