Identifying Cardiogenic Shock Sub-Phenotypes with Machine Learning: A Multicenter Study Combining Clinical and Echocardiographic Data
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Background
Sub-phenotyping cardiogenic shock (CS) patients using non-traditional clustering methods represents a step toward precision medicine, potentially improving outcomes in this heterogeneous and high-mortality condition. This study aimed to apply an unsupervised machine learning approach to integrate clinical and advanced echocardiographic data, identifying CS sub-phenotypes associated with different outcomes and features, beyond etiology.
Methods
This multicenter observational study prospectively analyzed 172 patients admitted to Cardiac Intensive Care Units with overt CS, from 2021. An exploratory statistical analysis preceded patient clustering using the Elbow Method and K-Means algorithm, based on clinical presentation. Dimensionality reduction was performed with Principal Component Analysis. Phenotypes were further stratified according to the Society for Cardiovascular Angiography and Interventions (SCAI) stages.
Results
Five distinct Phenotypes (labeled from I to V) were identified, showing progressively increasing in-hospital mortality rates: 25% (I), 32% (II), 39% (III), 41% (IV), and 60% (V). Kaplan-Meier analysis demonstrated a stepwise increase in mortality risk. Phenotypes IV and V had significantly higher mortality than Phenotype I (HR: 2.78 [95% CI, 1.07-7.19] and HR: 2.80 [95% CI, 1.10-7.14]; P < 0.05). Mortality prediction remained independent after adjustment for confounding factors, and independently of SCAI stage. Phenotype I had the lowest mortality, with higher arterial pressure and moderate left ventricular (LV) dysfunction, whereas Phenotype II exhibited marked LV failure. Oppositely, Phenotypes IV and V had severe congestion despite only mild LV impairment.
Conclusions
Machine learning, newly integrating echocardiographic data, identified five distinct CS Phenotypes, each with unique clinical/echocardiographic features and mortality risks. These insights could support personalized treatment strategies in CS patients, pending further validation.
WHAT IS NEW?
This machine learning-based analysis, newly integrating echocardiographic data, identified 5 distinct CS Phenotypes. These Phenotypes have been shown to be easily feasible at the bedside, each with unique mortality risks and features, including varying patterns of cardiac dysfunction and dilatation.
WHAT ARE THE CLINICAL IMPLICATIONS?
The 5 CS Phenotypes lay the foundation for personalized treatment strategies and improve risk stratification beyond SCAI staging in CS patients. Further external validation of the 5 Phenotypes to other independent CS cohorts, and additional investigations that account for trajectories of patients across Phenotypes, could establish their role in enhancing clinical outcomes.
