文献速递肝病

机器学习算法提高非酒精性脂肪性肝炎(基于NAS)及高危非酒精性脂肪性肝炎的检测:一项开发与验证研究

Machine learning algorithm improves the detection of NASH (NAS-based) and at-risk NASH: A development and validation study.
PubMed 文献 · Hepatology · 2023-03-31

本研究基于肝脏研究:测试脂肪性肝炎标志物效用元队列中966例经活检证实的非酒精性脂肪性肝病成人,采用监督机器学习构建预测模型,用于分期和分级。针对NASH(NAS≥4,53%)、高危NASH(NASH伴F≥2,35%)、显著纤维化(F≥2,47%)和晚期纤维化(F≥3,28%)分别建立临床模型和扩展模型(临床+生物标志物)。复合NASH模型AUC为0.71,复合高危NASH模型AUC为0.83,均优于直接模型;生物标志物仅改善纤维化模型的准确性。

要点

  • 复合NASH模型AUC为0.71,优于直接NASH模型(临床0.61/扩展0.65)。
  • 复合高危NASH模型AUC为0.83(临床和扩展),优于直接模型。
  • 扩展晚期纤维化模型AUC为0.86,显著优于临床版本(0.82)。

核心结论

  • 通过为每个组成部分构建独立的机器学习模型并仅使用临床预测因子,可改善NASH和高危NASH的检测。
  • 加入生物标志物仅改善了纤维化的准确性。

研究设计与样本

  • 学习数据来自肝脏研究:测试脂肪性肝炎标志物效用元队列,共966例经活检证实的非酒精性脂肪性肝病成人,按NASH CRN标准进行分期和分级。
  • 数据随机分为训练集/验证集(75/25),应用梯度提升机为每种情况开发临床模型和扩展模型(临床+生物标志物)。
  • 针对NASH和高危NASH构建了直接模型和复合模型两种变体。

主要发现

  • 临床梯度提升机模型对脂肪变性/炎症/气球样变的AUC分别为0.94/0.79/0.72,加入生物标志物后无改善。
  • 直接NASH模型的AUC(临床/扩展)为0.61/0.65;复合NASH模型两种变体的AUC均为0.71,显著更好。
  • 复合高危NASH模型AUC为0.83(临床和扩展),优于直接模型。
  • 显著纤维化模型的AUC(临床/扩展)为0.76/0.78。
  • 扩展晚期纤维化模型AUC为0.86,显著优于临床版本(0.82)。

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: Detecting NASH remains challenging, while at-risk NASH (steatohepatitis and F≥ 2) tends to progress and is of interest for drug development and clinical application. We developed prediction models by supervised machine learning techniques, with clinical data and biomarkers to stage and grade patients with NAFLD. APPROACH AND RESULTS: Learning data were collected in the Liver Investigation: Testing Marker Utility in Steatohepatitis metacohort (966 biopsy-proven NAFLD adults), staged and graded according to NASH CRN. Conditions of interest were the clinical trial definition of NASH (NAS ≥ 4;53%), at-risk NASH (NASH with F ≥ 2;35%), significant (F ≥ 2;47%), and advanced fibrosis (F ≥ 3;28%). Thirty-five predictors were included. Missing data were handled by multiple imputations. Data were randomly split into training/validation (75/25) sets. A gradient boosting machine was applied to develop 2 models for each condition: clinical versus extended (clinical and biomarkers). Two variants of the NASH and at-risk NASH models were constructed: direct and composite models.Clinical gradient boosting machine models for steatosis/inflammation/ballooning had AUCs of 0.94/0.79/0.72. There were no improvements when biomarkers were included. The direct NASH model produced AUCs (clinical/extended) of 0.61/0.65. The composite NASH model performed significantly better (0.71) for both variants. The composite at-risk NASH model had an AUC of 0.83 (clinical and extended), an improvement over the direct model. Significant fibrosis models had AUCs (clinical/extended) of 0.76/0.78. The extended advanced fibrosis model (0.86) performed significantly better than the clinical version (0.82). CONCLUSIONS: Detection of NASH and at-risk NASH can be improved by constructing independent machine learning models for each component, using only clinical predictors. Adding biomarkers only improved the accuracy of fibrosis.

来源:Hepatology,查看原文。版权归原作者所有。

引用

  1. Lee J, Westphal M, Vali Y, et al. Machine learning algorithm improves the detection of NASH (NAS-based) and at-risk NASH: A development and validation study. Hepatology. 2023. PMID: 36994719. doi:10.1097/HEP.0000000000000364

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。