Related Experiment Video
Updated: Sep 10, 2025
Use of a Percutaneous Ventricular Assist Device/Left Atrium to Femoral Artery Bypass System for Cardiogenic Shock
Published on: August 16, 2021
CSWG-SCAI Stages Combined With Machine Learning-Based Phenotypes for Serial Risk Stratification in Cardiogenic Shock
Elric Zweck1, Van-Khue Ton2, Manreet Kanwar3
1The CardioVascular Center, Tufts Medical Center, Boston, Massachusetts, USA; Department of Cardiology, Pulmonology, and Vascular Medicine, University Hospital Duesseldorf, Duesseldorf, Germany.
Insights
Combining machine learning phenotypes with SCAI stages improves risk stratification for cardiogenic shock (CS) patients. This approach offers a mechanistic classification reflecting CS heterogeneity, aiding clinical decision-making.
Area of Science:
- Cardiology
- Medical Informatics
- Critical Care Medicine
Background:
- Cardiogenic shock (CS) severity is currently classified using Society for Cardiovascular Angiography and Interventions (SCAI) stages (A-E) or machine learning (ML)-based phenotypes (I: noncongested, II: cardiorenal, III: cardiometabolic).
- These classification systems aim to define and stratify patients based on their clinical status.
Purpose of the Study:
- To evaluate the sequential applicability and prognostic relevance of combining SCAI stages and ML-based phenotypes for risk stratification in CS patients.
- To determine if a combined classification approach offers improved accuracy in predicting outcomes compared to individual systems.
Main Methods:
- Retrospective analysis of 7,716 patients from the Cardiogenic Shock Working Group (CSWG) registry.
- Application of both SCAI staging and ML-based phenotypes at 6- to 12-hour intervals for the first 72 hours.
- Primary outcome assessed was in-hospital mortality.
Main Results:
- Within 6 hours of admission, 78% of patients showed changes in SCAI stages and 77% in phenotypes, with relative stability thereafter.
- Combining ML-based phenotypes with SCAI stages significantly improved risk stratification, with distinct mortality rates for combined categories (e.g., C-I: 12%-14% vs. D-III: 37%-40%).
- Phenotypes II and III were strong predictors of CS progression and in-hospital mortality (Phenotype III: OR 11.4, P < 0.0001).
Conclusions:
- Most CS patients reach phenotype I and stage D within 6 hours of admission.
- Integrating ML-based phenotypes with SCAI staging provides a more mechanistic classification of CS.
- This combined approach may enhance clinical decision-making by better reflecting the heterogeneity within CS populations.
Background:
Cardiogenic shock (CS) severity can be defined by the SCAI (Society for Cardiovascular Angiography and Interventions) stages (A to E), or machine learning-based phenotypes (I: noncongested, II: cardiorenal, III: cardiometabolic).
Objectives:
This study aims to evaluate sequential applicability and prognostic relevance of combining SCAI stages and ML-based phenotypes for risk stratification of patients with CS.
Methods:
The authors retrospectively applied both classification systems at 6- to 12-hour intervals for the first 72 hours to patients from the multicenter CSWG (Cardiogenic Shock Working Group) registry. The primary outcome was in-hospital mortality.
Results:
A total of 7,716 CS patients were included (admission CSWG-SCAI stages A to E: n = 1,526, n = 1,602, n = 838, n = 2,445, and n = 1,305, respectively; phenotypes I to III: n = 2,963, n = 3,266, n = 1,487, respectively). Within 6 hours from admission, CSWG-SCAI stages and phenotypes changed in 78% and 77% of patients, respectively, then remained relatively unchanged throughout the first 72 hours. Combining ML-based phenotypes with CSWG-SCAI stages to subclassify patients improved risk stratification (mortality for stages C-I: 12%-14%, C-II: 22%-26%, D-I: 21%-23%, D-II: 31%-34%, and D-III: 37%-40%). Admission phenotypes II and III strongly increased the odds of CS progression from stages A-C to D-E or death within 72 hours of admission (phenotype II: OR: 1.2 [95% CI: 0.99-1.39]; P = 0.051; phenotype III: OR: 11.4 [95% CI: 3.50-36.95]; P < 0.0001).
Conclusions:
Most patients with CS reached phenotype I and stage D within 6 hours after admission. Combining ML-based phenotypes with CSWG-SCAI staging may facilitate the transition from typical treatment intensity-based approaches to mechanistic classification that reflects the heterogeneity within CS populations.
Related Concept Videos
01:29Cardiomyopathy III: Hypertrophic Cardiomyopathy
01:30Heart Failure IV: Classification and Diagnostic Evaluation
01:25Cardiomyopathy I: Introduction and Classification
01:30Acute Coronary Syndrome III: Diagnostic Studies