文献速递肝病

使用集成机器学习对临床风险预测算法进行基准测试以无创诊断NAFLD中的肝纤维化

Benchmarking clinical risk prediction algorithms with ensemble machine learning for the noninvasive diagnosis of liver fibrosis in NAFLD.
PubMed 文献 · Hepatology · 2024-04-30

本研究利用23个人口学/临床变量在NASH临床研究网络观察性研究(n=648)中训练超级学习器,并在FLINT试验(n=270)和NHANES参与者(n=1244)中验证,比较其与FIB-4、NAFLD纤维化评分、Forns、APRI、BARD和SAFE等模型对NAFLD患者显著肝纤维化的识别能力,发现超级学习器在验证集中AUC分别为0.79和0.74,SAFE评分表现相似,两者均优于FIB-4、APRI、Forns和BARD评分。

要点

  • 超级学习器在FLINT验证集AUC为0.79(95%CI: 0.73-0.84),在NHANES验证集AUC为0.74(95%CI: 0.68-0.79)。
  • SAFE评分与超级学习器表现相似,两者在验证数据集中均优于FIB-4、APRI、Forns和BARD评分。
  • 由12个基础模型衍生的超级学习器与由90个基础模型衍生的超级学习器表现相当。

核心结论

  • 超级学习器作为最佳机器学习预测器在检测纤维化性NASH方面表现出色,该方法可用于对常规临床风险预测模型进行基准测试。

研究设计与样本

  • 利用23个人口学/临床变量在NASH临床研究网络观察性研究(n=648)中训练超级学习器,并在FLINT试验(n=270)和NHANES参与者(n=1244)中验证模型。

主要发现

  • 超级学习器在FLINT验证集AUC为0.79(95%CI: 0.73-0.84),在NHANES验证集AUC为0.74(95%CI: 0.68-0.79)。
  • SAFE评分表现与超级学习器相似,两者在验证数据集中均优于FIB-4、APRI、Forns和BARD评分。
  • 由12个基础模型衍生的超级学习器与由90个基础模型衍生的超级学习器表现相当。

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 AND AIMS: Ensemble machine-learning methods, like the superlearner, combine multiple models into a single one to enhance predictive accuracy. Here we explore the potential of the superlearner as a benchmarking tool for clinical risk prediction, illustrating the approach to identifying significant liver fibrosis among patients with NAFLD. APPROACH AND RESULTS: We used 23 demographic/clinical variables to train superlearner(s) on data from the NASH-clinical research network observational study (n = 648) and validated models with data from the FLINT trial (n = 270) and National Health and Nutrition Examination Survey (NHANES) participants with NAFLD (n = 1244). Comparing the superlearner's performance to existing models (Fibrosis-4 [FIB-4], NAFLD fibrosis score, Forns, AST to Platelet Ratio Index [APRI], BARD, and Steatosis-Associated Fibrosis Estimator [SAFE]), it exhibited strong discriminative ability in the FLINT and NHANES validation sets, with AUCs of 0.79 (95% CI: 0.73-0.84) and 0.74 (95% CI: 0.68-0.79) respectively. CONCLUSIONS: Notably, the SAFE score performed similarly to the superlearner, both of which outperformed FIB-4, APRI, Forns, and BARD scores in the validation data sets. Surprisingly, the superlearner derived from 12 base models matched the performance of one with 90 base models. Overall, the superlearner, being the "best-in-class" machine-learning predictor, excelled in detecting fibrotic NASH, and this approach can be used to benchmark the performance of conventional clinical risk prediction models.

来源:Hepatology,查看原文。版权归原作者所有。

引用

  1. Charu V, Liang JW, Mannalithara A, et al. Benchmarking clinical risk prediction algorithms with ensemble machine learning for the noninvasive diagnosis of liver fibrosis in NAFLD. Hepatology. 2024. PMID: 38687634. doi:10.1097/HEP.0000000000000908

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。