Phenotypic clustering of patients hospitalized in intensive cardiac care units: Insights from the ADDICT-ICCU study.

Acute cardiac event Cardiac intensive care unit Clustering analysis Heart failure Unsupervised machine learning

Journal

Archives of cardiovascular diseases
ISSN: 1875-2128
Titre abrégé: Arch Cardiovasc Dis
Pays: Netherlands
ID NLM: 101465655

Informations de publication

Date de publication:
23 May 2024
Historique:
received: 07 11 2023
revised: 16 03 2024
accepted: 25 03 2024
medline: 5 6 2024
pubmed: 5 6 2024
entrez: 4 6 2024
Statut: aheadofprint

Résumé

Intensive cardiac care units (ICCUs) were created to manage ventricular arrhythmias after acute coronary syndromes, but have diversified to include a more heterogeneous population, the characteristics of which are not well depicted by conventional methods. To identify ICCU patient subgroups by phenotypic unsupervised clustering integrating clinical, biological, and echocardiographic data to reveal pathophysiological differences. During 7-22 April 2021, we recruited all consecutive patients admitted to ICCUs in 39 centers. The primary outcome was in-hospital major adverse events (MAEs; death, resuscitated cardiac arrest or cardiogenic shock). A cluster analysis was performed using a Kamila algorithm. Of 1499 patients admitted to the ICCU (69.6% male, mean age 63.3±14.9 years), 67 (4.5%) experienced MAEs. Four phenogroups were identified: PG1 (n=535), typically patients with non-ST-segment elevation myocardial infarction; PG2 (n=444), younger smokers with ST-segment elevation myocardial infarction; PG3 (n=273), elderly patients with heart failure with preserved ejection fraction and conduction disturbances; PG4 (n=247), patients with acute heart failure with reduced ejection fraction. Compared to PG1, multivariable analysis revealed a higher risk of MAEs in PG2 (odds ratio [OR] 3.13, 95% confidence interval [CI] 1.16-10.0) and PG3 (OR 3.16, 95% CI 1.02-10.8), with the highest risk in PG4 (OR 20.5, 95% CI 8.7-60.8) (all P<0.05). Cluster analysis of clinical, biological, and echocardiographic variables identified four phenogroups of patients admitted to the ICCU that were associated with distinct prognostic profiles. ClinicalTrials.gov identifier: NCT05063097.

Sections du résumé

BACKGROUND BACKGROUND
Intensive cardiac care units (ICCUs) were created to manage ventricular arrhythmias after acute coronary syndromes, but have diversified to include a more heterogeneous population, the characteristics of which are not well depicted by conventional methods.
AIMS OBJECTIVE
To identify ICCU patient subgroups by phenotypic unsupervised clustering integrating clinical, biological, and echocardiographic data to reveal pathophysiological differences.
METHODS METHODS
During 7-22 April 2021, we recruited all consecutive patients admitted to ICCUs in 39 centers. The primary outcome was in-hospital major adverse events (MAEs; death, resuscitated cardiac arrest or cardiogenic shock). A cluster analysis was performed using a Kamila algorithm.
RESULTS RESULTS
Of 1499 patients admitted to the ICCU (69.6% male, mean age 63.3±14.9 years), 67 (4.5%) experienced MAEs. Four phenogroups were identified: PG1 (n=535), typically patients with non-ST-segment elevation myocardial infarction; PG2 (n=444), younger smokers with ST-segment elevation myocardial infarction; PG3 (n=273), elderly patients with heart failure with preserved ejection fraction and conduction disturbances; PG4 (n=247), patients with acute heart failure with reduced ejection fraction. Compared to PG1, multivariable analysis revealed a higher risk of MAEs in PG2 (odds ratio [OR] 3.13, 95% confidence interval [CI] 1.16-10.0) and PG3 (OR 3.16, 95% CI 1.02-10.8), with the highest risk in PG4 (OR 20.5, 95% CI 8.7-60.8) (all P<0.05).
CONCLUSIONS CONCLUSIONS
Cluster analysis of clinical, biological, and echocardiographic variables identified four phenogroups of patients admitted to the ICCU that were associated with distinct prognostic profiles.
TRIAL REGISTRATION BACKGROUND
ClinicalTrials.gov identifier: NCT05063097.

Identifiants

DOI: 10.1016/j.acvd.2024.03.004 PMID: 38834393
pubmed: 38834393
pii: S1875-2136(24)00211-0
doi: 10.1016/j.acvd.2024.03.004
pii:
doi:

Banques de données

ClinicalTrials.gov
['NCT05063097']

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Informations de copyright

Copyright © 2024 Elsevier Masson SAS. All rights reserved.

Auteurs

Kenza Hamzi (K)

Inserm MASCOT - UMRS 942, Department of Cardiology, University Hospital of Lariboisière, Université Paris-Cité, Assistance publique-Hôpitaux de Paris (AP-HP), 75010 Paris, France; Department of Data Science, Machine Learning and Artificial Intelligence in Health, DATA-TEMPLE Laboratory, University Hospital of Lariboisière (AP-HP), 75010 Paris, France.

Emmanuel Gall (E)

Inserm MASCOT - UMRS 942, Department of Cardiology, University Hospital of Lariboisière, Université Paris-Cité, Assistance publique-Hôpitaux de Paris (AP-HP), 75010 Paris, France; Department of Data Science, Machine Learning and Artificial Intelligence in Health, DATA-TEMPLE Laboratory, University Hospital of Lariboisière (AP-HP), 75010 Paris, France.

François Roubille (F)

Inserm, CNRS, PhyMedExp, Cardiology Department, INI-CRT, Université de Montpellier, CHU de Montpellier, 34295 Montpellier, France.

Antonin Trimaille (A)

Department of Cardiovascular Medicine, Nouvel Hôpital Civil, Strasbourg University Hospital, 67000 Strasbourg, France.

Meyer Elbaz (M)

Intensive Cardiac Care Unit, Rangueil University Hospital, Toulouse, France.

Amine El Ouahidi (A)

Department of Cardiology, University Hospital of Brest, 29609 Brest cedex, France.

Nathalie Noirclerc (N)

Service de Cardiologie, Centre Hospitalier Annecy-Genevois, 74370 Épagny-Metz-Tessy, France.

Damien Fard (D)

Intensive Cardiac Care Unit, University Hospital Henri-Mondor, Créteil, France.

Benoit Lattuca (B)

Department of Cardiology, Nîmes University Hospital, Montpellier University, Nîmes, France.

Charles Fauvel (C)

Inserm U1096, Department of Cardiology, Université de Rouen-Normandie, CHU de Rouen, 76000 Rouen, France.

Marc Goralski (M)

Service de Cardiologie, Centre Hospitalier d'Orleans, Orléans, France.

Sean Alvain (S)

Service de Cardiologie, Centre Hospitalier de Saintes, Saintes, France.

Aures Chaib (A)

Service de Cardiologie, Centre Hospitalier de Montreuil, Montreuil, France.

Nicolas Piliero (N)

Service de Cardiologie, CHU de Grenoble-Alpes, Grenoble, France.

Guillaume Schurtz (G)

Department of Cardiology, University Hospital of Lille, Lille, France.

Thibaut Pommier (T)

Department of Cardiology, University Hospital, Dijon, France.

Claire Bouleti (C)

Department of Cardiology, University Hospital of Poitiers, 86000 Poitiers, France.

Christophe Tron (C)

Inserm U1096, Department of Cardiology, Université de Rouen-Normandie, CHU de Rouen, 76000 Rouen, France.

Guillaume Bonnet (G)

Inserm, Inrae, C2VN, Service de Cardiologie Interventionnelle, Aix-Marseille Université, CHU de Timone, AP-HM, Marseille, France.

Pascal Nhan (P)

Inserm UMR_S 938, Centre de Recherche Saint-Antoine, Institut Hospitalo-Universitaire de Cardiométabolisme et Nutrition (ICAN), Sorbonne Université, Paris, France; Service de Cardiologie, Hôpital Saint-Antoine, Assistance publique-Hôpitaux de Paris, Paris, France.

Simon Auvray (S)

Department of Cardiology, Felix-Guyon University Hospital, Saint-Denis, Reunion.

Antoine Léquipar (A)

Inserm MASCOT - UMRS 942, Department of Cardiology, University Hospital of Lariboisière, Université Paris-Cité, Assistance publique-Hôpitaux de Paris (AP-HP), 75010 Paris, France; Department of Data Science, Machine Learning and Artificial Intelligence in Health, DATA-TEMPLE Laboratory, University Hospital of Lariboisière (AP-HP), 75010 Paris, France.

Jean-Guillaume Dillinger (JG)

Inserm MASCOT - UMRS 942, Department of Cardiology, University Hospital of Lariboisière, Université Paris-Cité, Assistance publique-Hôpitaux de Paris (AP-HP), 75010 Paris, France; Department of Data Science, Machine Learning and Artificial Intelligence in Health, DATA-TEMPLE Laboratory, University Hospital of Lariboisière (AP-HP), 75010 Paris, France.

Eric Vicaut (E)

Department of Data Science, Machine Learning and Artificial Intelligence in Health, DATA-TEMPLE Laboratory, University Hospital of Lariboisière (AP-HP), 75010 Paris, France; Unité de Recherche Clinique, Hôpital Fernand-Widal, AP-HP, 75010 Paris, France.

Patrick Henry (P)

Inserm MASCOT - UMRS 942, Department of Cardiology, University Hospital of Lariboisière, Université Paris-Cité, Assistance publique-Hôpitaux de Paris (AP-HP), 75010 Paris, France; Department of Data Science, Machine Learning and Artificial Intelligence in Health, DATA-TEMPLE Laboratory, University Hospital of Lariboisière (AP-HP), 75010 Paris, France.

Solenn Toupin (S)

Inserm MASCOT - UMRS 942, Department of Cardiology, University Hospital of Lariboisière, Université Paris-Cité, Assistance publique-Hôpitaux de Paris (AP-HP), 75010 Paris, France; Department of Data Science, Machine Learning and Artificial Intelligence in Health, DATA-TEMPLE Laboratory, University Hospital of Lariboisière (AP-HP), 75010 Paris, France.

Théo Pezel (T)

Inserm MASCOT - UMRS 942, Department of Cardiology, University Hospital of Lariboisière, Université Paris-Cité, Assistance publique-Hôpitaux de Paris (AP-HP), 75010 Paris, France; Department of Data Science, Machine Learning and Artificial Intelligence in Health, DATA-TEMPLE Laboratory, University Hospital of Lariboisière (AP-HP), 75010 Paris, France. Electronic address: theo.pezel@aphp.fr.

Classifications MeSH