血浆蛋白质组学机器学习分类间质性肺疾病诊断
该研究纳入4个注册队列共1247例IPF和352例CTD-ILD患者,利用高通量血浆蛋白质组学数据构建37蛋白分类器(PC37),并训练多种机器学习模型区分CTD-ILD与IPF。验证显示测试队列AUC为0.85-0.90,单样本数据集AUC为0.94-0.96,复合分析准确率分别为78.2%和82.9%。
要点
- 基于37种血浆蛋白的机器学习分类器可区分CTD-ILD与IPF,测试队列AUC为0.85-0.90。
- 单样本分类数据集AUC达0.94-0.96,复合分析准确率82.9%。
- 分类器蛋白富集于细支气管发育、平滑肌增殖和免疫应答等生物过程。
核心结论
- 多种机器学习模型基于大规模蛋白质组学数据可一致区分CTD-ILD与IPF,所鉴定的蛋白多参与免疫通路。
- 研究开发的单样本分类方法有助于疑难ILD的鉴别诊断和临床决策。
研究设计与样本
- 研究纳入4个注册队列,共1247例IPF患者和352例CTD-ILD患者。
- 血浆样本进行高通量蛋白质组学检测,采用递归特征消除筛选蛋白特征构建分类器。
- 训练并测试支持向量机、LASSO回归、随机森林和不平衡随机森林等多种机器学习模型,并在独立队列及外部数据集中迭代分类。
主要发现
- 构建了含37种蛋白的分类器(PC37),富集于细支气管发育、平滑肌增殖和免疫应答等生物过程。
- 四种机器学习模型结合PC37与性别年龄评分生成连续分类值,测试队列AUC为0.85-0.90,单样本数据集AUC为0.94-0.96。
- 二分类在测试队列的灵敏度为78.6-80.4%、特异度为76-84.4%,在单样本分类数据集灵敏度为93.5-96.1%、特异度为69.5-77.6%。
- 所有机器学习模型的复合分析在测试队列准确率为78.2%(194/248),在单样本分类数据集为82.9%(208/251)。
临床怎么用
- 对于CTD-ILD与IPF鉴别困难的病例,可参考基于37蛋白血浆蛋白质组学的机器学习分类结果辅助诊断。
- 单样本分类方法有望在临床决策中帮助细化ILD的鉴别诊断。
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
Rationale: Distinguishing connective tissue disease-associated interstitial lung disease (CTD-ILD) from idiopathic pulmonary fibrosis (IPF) can be clinically challenging. Objectives: To identify proteins that separate and classify patients with CTD-ILD and those with IPF. Methods: Four registries with 1,247 patients with IPF and 352 patients with CTD-ILD were included in analyses. Plasma samples were subjected to high-throughput proteomics assays. Protein features were prioritized using recursive feature elimination to construct a proteomic classifier. Multiple machine learning models, including support vector machine, LASSO (least absolute shrinkage and selection operator) regression, random forest, and imbalanced Random Forest, were trained and tested in independent cohorts. The validated models were used to classify each case iteratively in external datasets. Measurements and Main Results: A classifier with 37 proteins (proteomic classifier 37 [PC37]) was enriched in the biological process of bronchiole development and smooth muscle proliferation and immune responses. Four machine learning models used PC37 with sex and age score to generate continuous classification values. Receiver operating characteristic curve analyses of these scores demonstrated consistent areas under the curve of 0.85-0.90 in the test cohort and 0.94-0.96 in the single-sample dataset. Binary classification demonstrated 78.6-80.4% sensitivity and 76-84.4% specificity in the test cohort and 93.5-96.1% sensitivity and 69.5-77.6% specificity in the single-sample classification dataset. Composite analysis of all machine learning models confirmed 78.2% (194 of 248) accuracy in the test cohort and 82.9% (208 of 251) in the single-sample classification dataset. Conclusions: Multiple machine learning models trained with large cohort proteomic datasets consistently distinguished CTD-ILD from IPF. Many of the identified proteins are involved in immune pathways. We further developed a novel approach for single-sample classification, which could facilitate honing the differential diagnosis of ILD in challenging cases and improve clinical decision making.
引用
- Huang Y, Ma SF, Oldham JM, et al. Machine Learning of Plasma Proteomics Classifies Diagnosis of Interstitial Lung Disease. Am J Respir Crit Care Med. 2024. PMID: 38422478. doi:10.1164/rccm.202309-1692OC
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。