Machine learning-based phenogrouping in heart failure to identify responders to cardiac resynchronization therapy
Machine learning-based phenogrouping in heart failure to identify responders to cardiac resynchronization therapy
复制标题
DOI：
10.1002/ejhf.1333
复制
发表时间：
2019-01-01
影响因子：
18.2
通讯作者：
Bijnens, Bart
中科院分区：
文献类型：
--
作者：
Cikes, Maja;Sanchez-Martinez, Sergio;Bijnens, Bart
目的：我们验证了一个假设，即利用复杂超声心动图数据和临床参数的机器学习（ML）算法可用于对心力衰竭（HF）队列进行表型分析，并识别对心脏再同步化治疗（CRT）有有益反应的患者。方法和结果我们研究了来自心脏再同步化治疗的多中心自动除颤器植入试验（madt -CRT）（左室射血分数30%，QRS 130ms，纽约心脏协会II级）的1106例HF患者，随机分为带除颤器的CRT （CRT- d, n=677）或植入式心律转复除颤器（ICD, n=429）。使用无监督ML算法（多核学习和K-means聚类）根据临床参数的相似性，左心室体积和基线变形痕迹将受试者分类为相互排斥的组。比较两组间CRT-D对主要结局（全因死亡或心衰事件）和容量反应的治疗效果。我们的分析确定了四个表型组，在大多数基线临床特征，生物标志物值，左右心室结构和功能测量以及主要结局发生方面显着不同。两个表型组包含较高比例的预测CRT反应的已知临床特征，并且与CRT- d对主要结局的显著更好的治疗效果相关[风险比（HR） 0.35；95%置信区间（CI） 0.19-0.64；P=0.0005, HR = 0.36；95% ci 0.19-0.68；P=0.001]明显高于其他组（相互作用P=0.02）。通过整合临床参数和全心脏周期成像数据，无监督ML可以为表型异质性HF队列提供具有临床意义的分类，并可能有助于优化特定治疗的应答率。
AimsWe tested the hypothesis that a machine learning (ML) algorithm utilizing both complex echocardiographic data and clinical parameters could be used to phenogroup a heart failure (HF) cohort and identify patients with beneficial response to cardiac resynchronization therapy (CRT).Methods and resultsWe studied 1106 HF patients from the Multicenter Automatic Defibrillator Implantation Trial with Cardiac Resynchronization Therapy (MADIT-CRT) (left ventricular ejection fraction 30%, QRS 130ms, New York Heart Association class II) randomized to CRT with a defibrillator (CRT-D, n=677) or an implantable cardioverter defibrillator (ICD, n=429). An unsupervised ML algorithm (Multiple Kernel Learning and K-means clustering) was used to categorize subjects by similarities in clinical parameters, and left ventricular volume and deformation traces at baseline into mutually exclusive groups. The treatment effect of CRT-D on the primary outcome (all-cause death or HF event) and on volume response was compared among these groups. Our analysis identified four phenogroups, significantly different in the majority of baseline clinical characteristics, biomarker values, measures of left and right ventricular structure and function and the primary outcome occurrence. Two phenogroups included a higher proportion of known clinical characteristics predictive of CRT response, and were associated with a substantially better treatment effect of CRT-D on the primary outcome [hazard ratio (HR) 0.35; 95% confidence interval (CI) 0.19-0.64; P=0.0005 and HR 0.36; 95% CI 0.19-0.68; P=0.001] than observed in the other groups (interaction P=0.02).ConclusionsOur results serve as a proof-of-concept that, by integrating clinical parameters and full heart cycle imaging data, unsupervised ML can provide a clinically meaningful classification of a phenotypically heterogeneous HF cohort and might aid in optimizing the rate of responders to specific therapies.