文献速递心力衰竭与心肌病

机器学习聚类分型下射血分数保留心衰的特定表型药物疗效

Medications for specific phenotypes of heart failure with preserved ejection fraction classified by a machine learning-based clustering model.
PubMed 文献 · Heart · 2023-07-27

本研究为PURSUIT-HFpEF注册登记的事后分析,纳入1100例射血分数保留心衰患者,按机器学习聚类分为四种表型,评估出院后ACEI/ARB、β受体阻滞剂、MRA和他汀的疗效。中位随访734天,主要终点发生528例(48.0%);MRA对表型2有效(wHR 0.40,95%CI 0.21-0.75,p=0.005),ACEI/ARB和.statin对表型3有效(wHR分别为0.66和0.43)。结论提示机器学习聚类可能识别特定药物有效的HFpEF人群。

要点

  • MRA对机器学习聚类表型2的HFpEF患者主要终点有显著疗效。
  • ACEI/ARB和他汀对表型3的HFpEF患者主要终点有显著疗效。
  • 其他药物在四种表型中均未显示显著治疗效果。

核心结论

  • 机器学习聚类可能有助于识别特定药物有效的HFpEF表型人群。
  • MRA、ACEI/ARB和他汀对特定HFpEF表型显示出疗效。

研究设计与样本

  • PURSUIT-HFpEF注册登记的事后分析,为前瞻性、多中心、观察性研究。
  • 共1231例患者,其中1100例符合分析条件,年龄83岁(IQR 77-87),女性604例。
  • 中位随访734天(IQR 398-1108)。
  • 评估出院后ACEI/ARB、β受体阻滞剂、MRA和他汀四类药物在四种表型中的疗效。
  • 主要终点为全因死亡和心衰住院的复合终点。

主要发现

  • 主要终点发生于528例患者(48.0%)。
  • MRA对表型2有效:加权HR 0.40(95%CI 0.21-0.75,p=0.005)。
  • ACEI/ARB对表型3有效:加权HR 0.66(95%CI 0.48-0.92,p=0.014)。
  • 他汀对表型3有效:加权HR 0.43(95%CI 0.21-0.88,p=0.020)。
  • 其他药物在四种表型中均无显著治疗效果。

关键数值与推荐

  • 采用Cox比例风险模型联合逆概率治疗加权(IPTW)评估疗效。
  • HFpEF按既往建立的机器学习聚类模型分为四种表型。

临床怎么用

  • 对HFpEF患者可考虑机器学习聚类分型以指导个体化用药选择。
  • 表型2患者使用MRA可能获益,表型3患者使用ACEI/ARB或他汀可能获益。

局限性

  • 本研究为观察性研究的事后分析,存在残余混杂可能。
  • 原文未报告其他局限性。

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)。

原文

OBJECTIVE: Our previously established machine learning-based clustering model classified heart failure with preserved ejection fraction (HFpEF) into four distinct phenotypes. Given the heterogeneous pathophysiology of HFpEF, specific medications may have favourable effects in specific phenotypes of HFpEF. We aimed to assess effectiveness of medications on clinical outcomes of the four phenotypes using a real-world HFpEF registry dataset. METHODS: This study is a posthoc analysis of the PURSUIT-HFpEF registry, a prospective, multicentre, observational study. We evaluated the clinical effectiveness of the following four types of postdischarge medication in the four different phenotypes: angiotensin-converting enzyme inhibitors (ACEi) or angiotensin-receptor blockers (ARB), beta blockers, mineralocorticoid-receptor antagonists (MRA) and statins. The primary endpoint of this study was a composite of all-cause death and heart failure hospitalisation. RESULTS: Of 1231 patients, 1100 (83 (IQR 77, 87) years, 604 females) were eligible for analysis. Median follow-up duration was 734 (398, 1108) days. The primary endpoint occurred in 528 patients (48.0%). Cox proportional hazard models with inverse-probability-of-treatment weighting showed the following significant effectiveness of medication on the primary endpoint: MRA for phenotype 2 (weighted HR (wHR) 0.40, 95% CI 0.21 to 0.75, p=0.005); ACEi or ARB for phenotype 3 (wHR 0.66 0.48 to 0.92, p=0.014) and statin therapy for phenotype 3 (wHR 0.43 (0.21 to 0.88), p=0.020). No other medications had significant treatment effects in the four phenotypes. CONCLUSIONS: Machine learning-based clustering may have the potential to identify populations in which specific medications may be effective. This study suggests the effectiveness of MRA, ACEi or ARB and statin for specific phenotypes of HFpEF. TRIAL REGISTRATION NUMBER: UMIN000021831.

来源:Heart,查看原文。版权归原作者所有。

引用

  1. Sotomi, Hikoso, Nakatani, et al. Medications for specific phenotypes of heart failure with preserved ejection fraction classified by a machine learning-based clustering model. Heart. 2023. PMID: 36822821. doi:10.1136/heartjnl-2022-322181

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。