文献速递心血管US

基于网络的「表型组学」方法:从高通量心脏影像数据中发现患者亚型

A Network-Based "Phenomics" Approach for Discovering Patient Subtypes From High-Throughput Cardiac Imaging Data.
PubMed 文献 · JACC Cardiovasc Imaging · 2020-03-16

研究纳入297例患者,获取42项超声心动图特征(含二维、多普勒、左室与心房斑点追踪及向量血流成像),构建患者相似性网络识别出4个表型聚类,并以神经网络模型区分各表型。聚类IV的C/D期心衰(78%)、NYHA III/IV级(61%)及短期主要心脑血管不良事件发生率均更高(p<0.001),独立留出验证集AUC为0.82–0.99。作者认为自动化计算表型分型可融合左室结构与功能的多维参数,识别具有不同临床特征、心脏结构与功能、血流动力学及结局的心脏表型组。

要点

  • 42项超声心动图特征经相似性网络分析可识别4个患者表型聚类(I–IV)。
  • 聚类IV的C/D期心衰占78%、NYHA III/IV级占61%,短期主要心脑血管不良事件发生率更高(p<0.001)。
  • 神经网络模型对表型聚类的预测在独立留出验证集AUC为0.82–0.99。

核心结论

  • 自动化计算表型分型方法可有效融合左室结构与功能的多维参数,识别在临床特征、心脏结构与功能、血流动力学及结局方面不同的心脏表型组。

研究设计与样本

  • 研究纳入297例患者,采集42项超声心动图特征,包括二维和Doppler测量、左室与心房斑点追踪及向量血流成像数据。
  • 构建患者相似性网络以描绘不同患者表型,并训练神经网络模型区分各表型表现。
  • 以美国心脏病学会/美国心脏协会心衰分期及短期主要心脑血管不良事件发生情况描述各聚类临床特征,并以独立留出验证集评估神经网络模型预测效能。

关键影像表现/征象

  • 相似性模型识别出4个聚类(I至IV),各聚类患者依据美国心脏病学会/美国心脏协会心衰分期及短期主要心脑血管不良事件发生情况呈现不同临床表型。
  • 与其他聚类相比,聚类IV的C期或D期心衰患病率更高(78%;p<0.001),NYHA心功能III级或IV级比例更高(61%;p<0.001),主要心脑血管不良事件发生率更高(p<0.001)。

诊断标准与关键数值

  • 聚类划分依据为42项超声心动图特征(二维和Doppler测量、左室与心房斑点追踪、向量血流成像)构建的患者相似性网络。
  • 各聚类临床特征以美国心脏病学会/美国心脏协会心衰分期及短期主要心脑血管不良事件发生情况描述。
  • 神经网络模型在独立留出验证集上区分患者聚类的AUC为0.82至0.99。

临床应用与阅片要点

  • 作者认为自动化计算表型分型可作为融合左室结构与功能多维参数的有效策略,并识别具有不同临床特征、心脏结构与功能、血流动力学及结局的心脏表型组。

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)。

英文原文(摘要)· 点击展开

OBJECTIVES: The authors present a method that focuses on cohort matching algorithms for performing patient-to-patient comparisons along multiple echocardiographic parameters for predicting meaningful patient subgroups.

BACKGROUND: Recent efforts in collecting multiomics data open numerous opportunities for comprehensive integration of highly heterogenous data to classify a patient's cardiovascular state, eventually leading to tailored therapies.

METHODS: A total of 42 echocardiography features, including 2-dimensional and Doppler measurements, left ventricular (LV) and atrial speckle-tracking, and vector flow mapping data, were obtained in 297 patients. A similarity network was developed to delineate distinct patient phenotypes, and then neural network models were trained for discriminating the phenotypic presentations.

RESULTS: The patient similarity model identified 4 clusters (I to IV), with patients in each cluster showed distinctive clinical presentations based on American College of Cardiology/American Heart Association heart failure stage and the occurrence of short-term major adverse cardiac and cerebrovascular events. Compared with other clusters, cluster IV had a higher prevalence of stage C or D heart failure (78%; p < 0.001), New York Heart Association functional classes III or IV (61%; p < 0.001), and a higher incidence of major adverse cardiac and cerebrovascular events (p < 0.001). The neural network model showed robust prediction of patient clusters, with area under the receiver-operating characteristic curve ranging from 0.82 to 0.99 for the independent hold-out validation set.

CONCLUSIONS: Automated computational methods for phenotyping can be an effective strategy to fuse multidimensional parameters of LV structure and function. It can identify distinct cardiac phenogroups in terms of clinical characteristics, cardiac structure and function, hemodynamics, and outcomes.

来源:JACC Cardiovasc Imaging,查看原文。版权归原作者所有。

引用

  1. Cho JS, Shrestha S, Kagiyama N, et al. A Network-Based "Phenomics" Approach for Discovering Patient Subtypes From High-Throughput Cardiac Imaging Data. JACC Cardiovasc Imaging. 2020. PMID: 32762883. doi:10.1016/j.jcmg.2020.02.008

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。