文献速递心血管US

心电图波形机器学习改进无症状左心室功能障碍的检查筛选

Machine Learning of ECG Waveforms to Improve Selection for Testing for Asymptomatic Left Ventricular Dysfunction.
PubMed 文献 · JACC Cardiovasc Imaging · 2021-06-16

本研究在398例心衰风险人群中,利用连续波变换生成能量波形心电图(ewECG)并采用随机森林分类器构建左心室功能障碍(LVD)预测模型。在独立测试组中,模型敏感度85%、特异度72%(AUC 0.83;95%CI 0.74–0.92);若将ewECG整合到筛查中,可减少45%的超声心动图需求,同时漏诊12%的LVD病例。

要点

  • ewECG机器学习模型筛选LVD的敏感度85%、特异度72%,AUC 0.83(95%CI 0.74–0.92)。
  • 整合ewECG到心衰风险人群筛查可减少45%超声心动图需求,漏诊12%LVD病例。
  • 针对GLS降低和舒张异常的随机森林模型敏感度不适合筛查。

核心结论

  • 应用机器学习处理ewECG是筛查LVD的敏感方法,将其整合到心衰风险患者筛查中可使超声心动图数量减少近一半。

研究设计与样本

  • 研究纳入398例心衰风险参与者,进行ewECG和超声心动图检查;采用643个CWT衍生特征和ARIC心衰风险评分,通过随机森林分类器进行特征选择和监督机器学习,训练集n=287,独立测试组n=111。

诊断标准与关键数值

  • LVD定义:整体纵向应变(GLS)≤16%、舒张异常(E/e' >15、左房增大伴E/e' >10或松弛受损)或左室肥厚;测试组敏感度85%、特异度72%,AUC 0.83(95%CI 0.74–0.92);去除ARIC评分后敏感度88%、特异度70%,AUC 0.78(95%CI 0.70–0.86)。

临床应用与阅片要点

  • 作者认为ewECG机器学习可作为心衰风险人群筛查LVD的敏感方法,整合后可减少45%超声心动图需求,但需注意其漏诊12%LVD病例。

局限性

  • 针对GLS降低和舒张异常的随机森林模型敏感度不适合筛查。
  • 常规LVD筛查候选指标(ARIC评分、NT-proBNP和标准自动心电图分析)的判别能力较差。

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 purpose of this study was to identify whether machine learning from processing of continuous wave transforms (CWTs) to provide an "energy waveform" electrocardiogram (ewECG) could be integrated with echocardiographic assessment of subclinical systolic and diastolic left ventricular dysfunction (LVD).

BACKGROUND: Asymptomatic LVD has management implications, but routine echocardiography is not undertaken in subjects at risk of heart failure. Signal processing of the surface ECG with the use of CWT can identify abnormal myocardial relaxation.

METHODS: EwECG and echocardiography were undertaken in 398 participants at risk of heart failure (HF). Reduced global longitudinal strain (GLS ≤16%)), diastolic abnormalities (E/e' >15, left atrial enlargement with E/e' >10 or impaired relaxation) or LV hypertrophy defined LVD. EwECG feature selection and supervised machine-learning by random forest (RF) classifier was undertaken with 643 CWT-derived features and the ARIC (Atherosclerosis Risk In Communities) heart failure risk score.

RESULTS: The ARIC score and 18 CWT features were selected to build a RF predictive model for LVD in a training dataset (n = 287; 60% female, median age 71 [interquartile range: 68 to 74] years). Model performance was tested in an independent group (n = 111; 49% female, median age 61 years [59 to 66 years]), demonstrating 85% sensitivity and 72% specificity (area under the receiver-operating characteristic curve [AUC]: 0.83; 95% confidence interval [CI]: 0.74 to 0.92). With ARIC score removed, sensitivity was 88% and specificity, 70% (AUC: 0.78; 95% CI: 0.70 to 0.86). RF models for reduced GLS and diastolic abnormalities including similar features had sensitivities that were unsuitable for screening. Conventional candidates for LVD screening (ARIC score, N-terminal pro-B-type natriuretic peptide, and standard automated ECG analysis) had inferior discriminative ability. Integration of ewECG in screening of people at risk of HF would reduce need for echocardiography by 45% while missing 12% of LVD cases.

CONCLUSIONS: Machine learning applied to ewECG is a sensitive screening test for LVD, and its integration into screening of patients at risk for HF would reduce the number of echocardiograms by almost one-half.

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

引用

  1. Potter EL, Rodrigues CHM, Ascher DB, et al. Machine Learning of ECG Waveforms to Improve Selection for Testing for Asymptomatic Left Ventricular Dysfunction. JACC Cardiovasc Imaging. 2021. PMID: 34147443. doi:10.1016/j.jcmg.2021.04.020

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。