文献速递肝病

机器学习评估肝组织学预测NASH肝硬化临床显著门脉高压

A Machine Learning Approach to Liver Histological Evaluation Predicts Clinically Significant Portal Hypertension in NASH Cirrhosis.
PubMed 文献 · Hepatology · 2021-01-01

本研究基于NASH伴代偿期肝硬化患者的trichrome染色肝活检,用卷积神经网络构建ML-HVPG评分,在训练集130例和测试集88例中验证。ML-HVPG评分与HVPG相关性优于形态计量肝胶原,预测CSPH的AUROC在训练集和测试集分别为0.85和0.76,联合其他参数后测试集AUROC升至0.85。

要点

  • ML-HVPG评分可无创预测NASH肝硬化患者的临床显著门脉高压。
  • ML-HVPG评分与HVPG相关性优于形态计量肝胶原(ρ=0.47 vs 0.28)。
  • ML-HVPG评分变化可预测临床事件(HR=2.13),基线评分无预后价值。

核心结论

  • 基于trichrome染色肝活检切片的机器学习模型可预测NASH肝硬化患者的CSPH。

研究设计与样本

  • 纳入NASH伴代偿期肝硬化患者,来自一项2b期试验,基线和第48、96周HVPG和活检经中心审阅,活检用卷积神经网络评估。

主要发现

  • ML-HVPG评分与HVPG相关性优于形态计量肝胶原(ρ=0.47 vs 0.28;P<0.001)。
  • ML-HVPG评分可区分正常HVPG(0-5 mm Hg)、升高HVPG(5.5-9.5 mm Hg)和CSPH(中位数1.51 vs 1.93 vs 2.60;均P<0.05)。
  • ML-HVPG评分预测CSPH的AUROC在训练集为0.85(95%CI 0.80,0.90),测试集为0.76(95%CI 0.68,0.85)。
  • 联合结节性ML参数、ELF、血小板、AST和胆红素后,测试集AUROC提升至0.85(95%CI 0.78,0.92)。
  • 基线ML-HVPG评分无预后价值,但评分变化可预测临床事件(HR=2.13;95%CI 1.26,3.59),并与血流动力学应答和纤维化改善相关。

关键数值与推荐

  • CSPH定义为HVPG≥10 mm Hg。
  • 训练集n=130,测试集n=88。

临床怎么用

  • ML-HVPG评分可作为组织学评估工具,辅助识别NASH肝硬化患者中的CSPH。
  • 评分变化或可用于监测临床事件风险和治疗应答。

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 AND AIMS: The hepatic venous pressure gradient (HVPG) is the standard for estimating portal pressure but requires expertise for interpretation. We hypothesized that HVPG could be extrapolated from liver histology using a machine learning (ML) algorithm. APPROACH AND RESULTS: Patients with NASH with compensated cirrhosis from a phase 2b trial were included. HVPG and biopsies from baseline and weeks 48 and 96 were reviewed centrally, and biopsies evaluated with a convolutional neural network (PathAI, Boston, MA). Using trichrome-stained biopsies in the training set (n = 130), an ML model was developed to recognize fibrosis patterns associated with HVPG, and the resultant ML HVPG score was validated in a held-out test set (n = 88). Associations between the ML HVPG score with measured HVPG and liver-related events, and performance of the ML HVPG score for clinically significant portal hypertension (CSPH) (HVPG ≥ 10 mm Hg), were determined. The ML-HVPG score was more strongly correlated with HVPG than hepatic collagen by morphometry (ρ = 0.47 vs. ρ = 0.28; P < 0.001). The ML HVPG score differentiated patients with normal (0-5 mm Hg) and elevated (5.5-9.5 mm Hg) HVPG and CSPH (median: 1.51 vs. 1.93 vs. 2.60; all P < 0.05). The areas under receiver operating characteristic curve (AUROCs) (95% CI) of the ML-HVPG score for CSPH were 0.85 (0.80, 0.90) and 0.76 (0.68, 0.85) in the training and test sets, respectively. Discrimination of the ML-HVPG score for CSPH improved with the addition of a ML parameter for nodularity, Enhanced Liver Fibrosis, platelets, aspartate aminotransferase (AST), and bilirubin (AUROC in test set: 0.85; 95% CI: 0.78, 0.92). Although baseline ML-HVPG score was not prognostic, changes were predictive of clinical events (HR: 2.13; 95% CI: 1.26, 3.59) and associated with hemodynamic response and fibrosis improvement. CONCLUSIONS: An ML model based on trichrome-stained liver biopsy slides can predict CSPH in patients with NASH with cirrhosis.

来源:Hepatology,查看原文。版权归原作者所有。

引用

  1. Bosch J, Chung C, Carrasco-Zevallos OM, et al. A Machine Learning Approach to Liver Histological Evaluation Predicts Clinically Significant Portal Hypertension in NASH Cirrhosis. Hepatology. 2021. PMID: 34333790. doi:10.1002/hep.32087

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。