System Maintenance Notice

Please note that maintenance work is scheduled between 4 AM and 5 AM - CET. During this time, you may experience reduced performance. Thanks for your patience.

Publications

Journal Article Epublish

PubMed: 42689178 DOI: 10.3389/frai.2026.1886402

Unsupervised clustering identifies distinct phenotypes in acute myocardial infarction: insights from the FAST-MI 2015 registry.

Front Artif Intell 9:1886402

Authors: Vincent Bataille, Loïc Panh, Etienne Puymirat, Guillaume Cayla, Pascal Motreff, Gilles Lemesle, François Schiele, Tabassome Simon, Nicolas Danchin, Jean Ferrières

Affiliations

  • INSERM UMR 1295, CERPOP, Toulouse Rangueil University Hospital, Toulouse University School of Medicine, Toulouse, France.
  • ADIMEP (Association pour la Diffusion de la Médecine de Prévention), Toulouse, France.
  • Department of Cardiology, Clinique Pasteur, Toulouse, France.
  • Department of Cardiology, Assistance Publique-Hôpitaux de Paris (AP-HP), Hôpital Européen Georges Pompidou, Paris, France.
  • Department of Cardiology, University Hospital of Nîmes, University of Montpellier, Nîmes, France.
  • Department of Cardiology, University Hospital of Clermont-Ferrand, Clermont-Ferrand, France.
  • Department of Cardiology, Heart and Lung Institute, University Hospital of Lille, Lille, France.
  • French Alliance for Cardiovascular Trials (FACT), Paris, France.
  • Department of Cardiology, University Hospital of Besançon, University of Franche Comte, SINERGIES, Besançon, France.
  • Department of Clinical Pharmacology, Hôpital Saint-Antoine, Assistance Publique-Hôpitaux de Paris (AP-HP), Paris, France.
  • Department of Cardiology, Hôpital Saint Joseph, Paris, France.
  • Department of Cardiology, Toulouse Rangueil University Hospital, Toulouse, France.

Abstract

BACKGROUND

Current classification of Acute Myocardial Infarction (AMI) into ST-elevation (STEMI) and non-ST-elevation (NSTEMI) myocardial infarction does not fully reflect the clinical heterogeneity of patients.

OBJECTIVES

To identify clinically meaningful phenotypes of AMI patients using an unsupervised clustering approach and assess their associations with management strategies and long-term outcomes.

METHODS

Hierarchical agglomerative clustering using Ward's method was performed in 4,947 patients from the French FAST-MI 2015 nationwide registry. Clustering was based on baseline clinical, demographic, and laboratory features. Between-cluster differences in baseline characteristics, management, in-hospital complications, and 1-year mortality were analyzed.

RESULTS

Four phenotypic clusters were identified. Cluster 1 (n = 1,488) gathered older patients, predominantly men, with typical coronary risk factors, intermediate risk profile, and balanced STEMI/NSTEMI presentations. Cluster 2 (n = 1,305) gathered older polymorbid patients, 45% were women, 60% with NSTEMI presentation, with limited use of invasive strategies (71%), and a high 1-year mortality. Cluster 3 (n = 815) gathered young (mean age 44 years), predominantly male patients, with a high prevalence of smoking (73%) and few comorbidities, 62% STEMI, high rates of revascularization, and excellent prognosis. Cluster 4 (n = 1,339) was close to Cluster 3 with a more metabolic profile with higher rates of obesity, diabetes, and dyslipidemia, also with favorable outcomes. In-hospital complications were more frequent in Clusters 1 and 2. One-year mortality was lowest in Clusters 3 and 4 (1.5 and 2.3%), intermediate in Cluster 1 (6.0%), and highest in Cluster 2 (15.7%).

CONCLUSION

Unsupervised clustering identified four clinically relevant AMI phenotypes with distinct characteristics, management patterns, and prognoses. This data-driven classification highlights the diversity of AMI presentations and may offer complementary insights for patient profiling and risk stratification.

MeSH

Registries, Mortality, Myocardial Infarction, Phenotype, Classification, Acute Coronary Syndrome, Cluster Analysis, Precision Medicine, Prognosis