Deng Yu, Cheng Sijing, Huang Hao, Liu Xi, Yu Yu, Gu Min, Cai Chi, Chen Xuhua, Niu Hongxia, Hua Wei
Cardiac Arrhythmia Center, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College, 100037 Beijing, China.
Rev Cardiovasc Med. 2023 Feb 2;24(2):37. doi: 10.31083/j.rcm2402037. eCollection 2023 Feb.
Previous studies have failed to implement risk stratification in patients with heart failure (HF) who are eligible for secondary implantable cardioverter-defibrillator (ICD) implantation. We aimed to evaluate whether machine learning-based phenomapping using routinely available clinical data can identify subgroups that differ in characteristics and prognoses.
A total of 389 patients with chronic HF implanted with an ICD were included, and forty-four baseline variables were collected. Phenomapping was performed using hierarchical k-means clustering based on factor analysis of mixed data (FAMD). The utility of phenomapping was validated by comparing the baseline features and outcomes of the first appropriate shock and all-cause death among the phenogroups.
During a median follow-up of 2.7 years for device interrogation and 5.1 years for survival status, 142 (36.5%) first appropriate shocks and 113 (29.0%) all-cause deaths occurred. The first 12 principal components extracted using the FAMD, explaining 60.5% of the total variability, were left for phenomapping. Three mutually exclusive phenogroups were identified. Phenogroup 1 comprised the oldest patients with ischemic cardiomyopathy; had the highest proportion of diabetes mellitus, hypertension, and hyperlipidemia; and had the most favorable cardiac structure and function among the phenogroups. Phenogroup 2 included the youngest patients, mostly those with non-ischemic cardiomyopathy, who had intermediate heart dimensions and function, and the fewest comorbidities. Phenogroup 3 had the worst HF progression. Kaplan-Meier curves revealed significant differences in the first appropriate shock ( = 0.002) and all-cause death ( 0.001) across the phenogroups. After adjusting for medications in Cox regression, phenogroups 2 and 3 displayed a graded increase in appropriate shock risk (hazard ratio [HR] 1.54, 95% confidence interval [CI] 1.03-2.28, = 0.033; HR 2.21, 95% CI 1.42-3.43, 0.001, respectively; for trend 0.001) compared to phenogroup 1. Regarding mortality risk, phenogroup 3 was associated with an increased risk (HR 2.25, 95% CI 1.45-3.49, 0.001). In contrast, phenogroup 2 had a risk ( = 0.124) comparable with phenogroup 1.
Machine-learning-based phenomapping can identify distinct phenotype subgroups in patients with clinically heterogeneous HF with secondary prophylactic ICD therapy. This novel strategy may aid personalized medicine for these patients.
既往研究未能对符合二级植入式心脏复律除颤器（ICD）植入条件的心力衰竭（HF）患者进行风险分层。我们旨在评估使用常规可得临床数据的基于机器学习的表型映射能否识别出特征和预后不同的亚组。
共纳入389例植入ICD的慢性HF患者，并收集了44项基线变量。基于混合数据因子分析（FAMD），使用分层k均值聚类进行表型映射。通过比较各表型组的基线特征以及首次恰当电击和全因死亡的结局，验证表型映射的效用。
在对设备问询进行中位数2.7年、对生存状态进行中位数5.1年的随访期间，发生了142次（36.5%）首次恰当电击和113例（29.0%）全因死亡。使用FAMD提取的前12个主成分（解释了总变异的60.5%）用于表型映射。识别出三个相互排斥的表型组。表型组1包括年龄最大的缺血性心肌病患者；糖尿病、高血压和高脂血症比例最高；且在各表型组中心脏结构和功能最有利。表型组2包括最年轻的患者，大多为非缺血性心肌病患者，其心脏大小和功能中等，合并症最少。表型组3的HF进展最差。Kaplan-Meier曲线显示各表型组在首次恰当电击（P = 0.002）和全因死亡（P = 0.001）方面存在显著差异。在Cox回归中对药物进行校正后，与表型组1相比，表型组2和3的恰当电击风险呈分级增加（风险比[HR]分别为1.54，95%置信区间[CI]为1.03 - 2.28，P = 0.033；HR 2.21，95% CI为1.42 - 3.43，P = 0.001；趋势P = 0.001）。关于死亡风险，表型组3的风险增加（HR 2.25，95% CI为1.45 - 3.49，P = 0.001）。相比之下，表型组2的风险（P = 0.124）与表型组1相当。
基于机器学习的表型映射可在接受二级预防性ICD治疗的临床异质性HF患者中识别出不同的表型亚组。这种新策略可能有助于为这些患者提供个性化医疗。
