指南与共识复苏、休克与脓毒症重症综合管理与镇静镇痛

应用机器学习共识聚类方法识别心源性休克的不同临床表型

Identification of distinct clinical phenotypes of cardiogenic shock using machine learning consensus clustering approach.
指南 / 共识 · BMC Cardiovasc Disord · 2023-08-29
一句话结论在eICU数据库21,925例心源性休克患者中,机器学习共识聚类识别出两种表型,其中Cluster 2与较低的住院死亡率、ICU死亡率和AKI发生率相关。

研究基于eICU协作研究数据库纳入21,925例入院时诊断心源性休克的患者,采用无监督机器学习共识聚类分析识别表型,通过共识矩阵热图、累积分布函数、聚类共识图和模糊聚类对比例分析确定最佳聚类数,并以标准化均数差±0.3为界值识别各聚类关键特征。结果识别出两个聚类(Cluster 1 n=9,848;Cluster 2 n=12,077),Cluster 1患者血压更低、eGFR更低、BUN和肌酐更高、白蛋白更低、钾更高、碳酸氢盐更低、红细胞更低、RDW更高、SOFA评分、APS III评分和APACHE IV评分更高。逻辑回归显示Cluster 2与较低的住院死亡率(OR 0.374;95%CI 0.347-0.402;P<0.001)、ICU死亡率(OR 0.349;95%CI 0.318-0.382;P<0.001)和入院后急性肾损伤发生率(OR 0.478;95%CI 0.452-0.505;P<0.001)相关。作者认为机器学习共识聚类分析综合临床和实验室数据模式,揭示了具有不同临床结局的不同心源性休克表型。

要点

  • 在21,925例心源性休克患者中,无监督机器学习共识聚类分析识别出两个表型(Cluster 1 n=9,848;Cluster 2 n=12,077)。
  • Cluster 1的关键特征包括血压更低、eGFR更低、BUN更高、肌酐更高、白蛋白更低、钾更高、碳酸氢盐更低。
  • Cluster 1还包括红细胞更低、RDW更高,以及SOFA评分、APS III评分和APACHE IV评分更高。
  • 逻辑回归显示Cluster 2与较低的住院死亡率相关(OR 0.374;95%CI 0.347-0.402;P<0.001)。
  • Cluster 2还与较低的ICU死亡率(OR 0.349;95%CI 0.318-0.382;P<0.001)和较低的急性肾损伤发生率(OR 0.478;95%CI 0.452-0.505;P<0.001)相关。

适用人群与场景

  • 于入院时诊断为心源性休克并录入电子ICU(eICU)协作研究数据库的患者,共21,925例。

研究设计与关键结果

  • 研究类型:基于电子ICU协作研究数据库的无监督机器学习共识聚类分析,纳入21,925例入院时诊断心源性休克的患者。
  • 聚类方法:通过共识矩阵热图、累积分布函数、聚类共识图和模糊聚类对比例分析确定最佳聚类数;以标准化均数差±0.3为界值识别各聚类的关键特征。
  • 共识别出两个聚类:Cluster 1 n=9,848,Cluster 2 n=12,077。
  • 与Cluster 2相比,Cluster 1的关键特征包括:血压更低、eGFR更低、BUN更高、肌酐更高、白蛋白更低、钾更高、碳酸氢盐更低。
  • Cluster 1的其他关键特征包括:红细胞更低、RDW更高,以及入院时SOFA评分、APS III评分和APACHE IV评分更高。
  • 逻辑回归分析显示,Cluster 2与较低的住院死亡率相关(OR 0.374;95%CI 0.347-0.402;P<0.001)。
  • Cluster 2与较低的ICU死亡率相关(OR 0.349;95%CI 0.318-0.382;P<0.001)。
  • Cluster 2与较低的入院后急性肾损伤发生率相关(OR 0.478;95%CI 0.452-0.505;P<0.001)。

证据类型、等级与局限

  • 证据类型:基于电子ICU协作研究数据库的机器学习共识聚类分析。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,机器学习共识聚类分析综合临床和实验室数据模式,揭示了具有不同临床结局的不同心源性休克表型。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开

BACKGROUND: Cardiogenic shock (CS) is a complex state with many underlying causes and associated outcomes. It is still difficult to differentiate between various CS phenotypes. We investigated if the CS phenotypes with distinctive clinical profiles and prognoses might be found using the machine learning (ML) consensus clustering approach.

METHODS: The current study included patients who were diagnosed with CS at the time of admission from the electronic ICU (eICU) Collaborative Research Database. Among 21,925 patients with CS, an unsupervised ML consensus clustering analysis was conducted. The optimal number of clusters was identified by means of the consensus matrix (CM) heat map, cumulative distribution function (CDF), cluster-consensus plots, and the proportion of ambiguously clustered pairs (PAC) analysis. We calculated the standardized mean difference (SMD) of each variable and used the cutoff of ± 0.3 to identify each cluster's key features. We examined the relationship between the phenotypes and several clinical endpoints utilizing logistic regression (LR) analysis.

RESULTS: The consensus cluster analysis identified two clusters (Cluster 1: n = 9,848; Cluster 2: n = 12,077). The key features of patients in Cluster 1, compared with Cluster 2, included: lower blood pressure, lower eGFR (estimated glomerular filtration rate), higher BUN (blood urea nitrogen), higher creatinine, lower albumin, higher potassium, lower bicarbonate, lower red blood cell (RBC), higher red blood cell distribution width (RDW), higher SOFA score, higher APS III score, and higher APACHE IV score on admission. The results of LR analysis showed that the Cluster 2 was associated with lower in-hospital mortality (odds ratio [OR]: 0.374; 95% confidence interval [CI]: 0.347-0.402; P < 0.001), ICU mortality (OR: 0.349; 95% CI: 0.318-0.382; P < 0.001), and the incidence of acute kidney injury (AKI) after admission (OR: 0.478; 95% CI: 0.452-0.505; P < 0.001).

CONCLUSIONS: ML consensus clustering analysis synthesized the pattern of clinical and laboratory data to reveal distinct CS phenotypes with different clinical outcomes.

来源:BMC Cardiovasc Disord,查看原文。版权归原作者所有。

参考来源

  1. Wang L, Zhang Y, Yao R, et al. Identification of distinct clinical phenotypes of cardiogenic shock using machine learning consensus clustering approach. BMC Cardiovasc Disord. 2023. PMID: 37644414. doi:10.1186/s12872-023-03380-y

供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。