Enhanced Early Risk Stratification in Cardiogenic Shock Using Machine Learning: A Hierarchical Clustering Analysis.
5 affiliations
- 1North Shore University Hospital, Manhasset, New York, USA; Northwell Cardiovascular Institute, New Hyde Park, New York, USA.
- 2Lenox Hill Hospital, New York, New York, USA.
- 3Feinstein Institutes for Medical Research, Manhasset, New York, USA.
- 4Lenox Hill Hospital, New York, New York, USA; Feinstein Institutes for Medical Research, Manhasset, New York, USA.
- 5Northwell Cardiovascular Institute, New Hyde Park, New York, USA; Lenox Hill Hospital, New York, New York, USA. Electronic address: [email protected].
Abstract
Background
Cardiogenic shock (CS) exhibits marked clinical heterogeneity, limiting the performance of conventional risk stratification tools like the Society for Cardiovascular Angiography and Interventions (SCAI) staging system. Machine learning (ML) has identified reproducible CS phenotypes that improve risk prediction, but their temporal consistency across the progression of shock remains incompletely described.Objectives
The purpose of this study was to evaluate the temporal evolution of ML-derived CS phenotypes across the first 3 intensive care unit (ICU) days and determine whether phenotype trajectories enhance mortality stratification beyond SCAI staging.Methods
In a multicenter retrospective registry of 2,906 adults with CS admitted to ICUs between 2016 and 2022, hierarchical agglomerative clustering was applied independently to clinical variables on ICU days 1, 2, and 3.Results
On day 1, 3 phenotypes emerged: Cardiac (younger, acute myocardial infarction-predominant, preserved renal function; 15% mortality), Cardio-Renal (older, non-acute myocardial infarction-predominant, isolated renal extracardiac impairment, predominantly SCAI A and B on admission; 27% mortality), and Cardio-Metabolic (severe renal and tissue malperfusion, predominantly SCAI D and E on admission; 55% mortality). Similar phenotypes persisted on day 2 and day 3. These ML-derived phenotypes enhanced mortality stratification within each SCAI stage across days 1 to 3.Conclusions
Hierarchical clustering reproduced previously identified CS phenotypes that were consistent across the first 3 days of ICU stay, providing an enhanced framework for early risk stratification. Prospective validation is required for clinical implementation.
Related
- Mortality risk stratification in contemporary myocardial infarction-related cardiogenic shock: development of AMICS-ADMIT prediction model and benchmarking of established scores.
- Norepinephrine Equivalent Dose for Mortality Risk Stratification in VA-ECMO Cardiogenic Shock
- An interpretable machine learning model for predicting intensive care unit mortality risk in elderly patients with concomitant cardiogenic shock and sepsis: Development and external validation using two large critical care databases
- Machine learning clustering of multidimensional clinical features identifies four prognostically distinct sepsis subtypes
- Letter to the Editor: Integrating Machine Learning Into Stroke Risk Stratification in AF—Authors' Reply
BibTeX
@article{li2026enhanced,
title = {{Enhanced Early Risk Stratification in Cardiogenic Shock Using Machine Learning: A Hierarchical Clustering Analysis.}},
author = {Shuojohn Li and Abduljabar Adi and Alejandro Quintero Villegas and Theodoros Zanos and Sami Dalati and Snehal R Patel and Matthew Griffin and Matthew Pierce and Miguel Alvarez Villela},
journal = {JACC. Advances},
year = {2026},
month = oct,
doi = {10.1016/j.jacadv.2026.103339},
url = {https://europepmc.org/article/MED/42868968},
note = {CC BY},
}
RIS
TY - JOUR
TI - Enhanced Early Risk Stratification in Cardiogenic Shock Using Machine Learning: A Hierarchical Clustering Analysis.
AU - Shuojohn Li
AU - Abduljabar Adi
AU - Alejandro Quintero Villegas
AU - Theodoros Zanos
AU - Sami Dalati
AU - Snehal R Patel
AU - Matthew Griffin
AU - Matthew Pierce
AU - Miguel Alvarez Villela
PY - 2026
DA - 2026/10/13
JO - JACC. Advances
DO - 10.1016/j.jacadv.2026.103339
UR - https://europepmc.org/article/MED/42868968
AB - Background Cardiogenic shock (CS) exhibits marked clinical heterogeneity, limiting the performance of conventional risk stratification tools like the Society for Cardiovascular Angiography and Interventions (SCAI) staging system. Machine learning (ML) has identified reproducible CS phenotypes that improve risk prediction, but their temporal consistency across the progression of shock remains incompletely described.Objectives The purpose of this study was to evaluate the temporal evolution of ML-derived CS phenotypes across the first 3 intensive care unit (ICU) days and determine whether phenotype trajectories enhance mortality stratification beyond SCAI staging.Methods In a multicenter retrospective registry of 2,906 adults with CS admitted to ICUs between 2016 and 2022, hierarchical agglomerative clustering was applied independently to clinical variables on ICU days 1, 2, and 3.Results On day 1, 3 phenotypes emerged: Cardiac (younger, acute myocardial infarction-predominant, preserved renal function; 15% mortality), Cardio-Renal (older, non-acute myocardial infarction-predominant, isolated renal extracardiac impairment, predominantly SCAI A and B on admission; 27% mortality), and Cardio-Metabolic (severe renal and tissue malperfusion, predominantly SCAI D and E on admission; 55% mortality). Similar phenotypes persisted on day 2 and day 3. These ML-derived phenotypes enhanced mortality stratification within each SCAI stage across days 1 to 3.Conclusions Hierarchical clustering reproduced previously identified CS phenotypes that were consistent across the first 3 days of ICU stay, providing an enhanced framework for early risk stratification. Prospective validation is required for clinical implementation.
SN - 2772-963X
ER -