EUVIMEDEUVIMED entdecken
BeobachtungsstudieMultizentrische StudieOpen Access · CC BY 4.0

Prehospital Risk Stratification Using Unsupervised Machine Learning in STEMI

Ana Ramos-Rodríguez, Raúl López-Izquierdo, Carlos Del Pozo Vegas, María Plaza-Martín, Cristina Tapia-Ballesteros, Juan F Delgado Benito, Ancor Sanz-García iD, Francisco Martín-Rodríguez

European Journal of Clinical Investigation · 2026-05 · 56 (5)

DOI: 10.1111/eci.70214 ↗

Kurz gefasst

Beobachtungsstudie in der Zeitschrift European Journal of Clinical Investigation, online erschienen am 24.04.2026. Verfasst von Ana Ramos-Rodríguez und 7 weiteren Autor:innen. Beteiligte Einrichtung: Emergency Department, Hospital Universitario Rio Hortega, Valladolid, Spain. Hauptthemen laut MEDLINE: ST Elevation Myocardial Infarction, Unsupervised Machine Learning, Emergency Medical Services. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Health Carlos III, MCIN/AEI/10.13039/501100011033, Instituto de Salud Carlos III.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

ST‐elevation myocardial infarction (STEMI) exhibits substantial clinical heterogeneity complicating prehospital risk stratification. Traditional risk assessment tools often fail to capture the complexity of this condition. Machine learning offers opportunities to identify complex clinical patterns not readily apparent during prehospital care.

Aim

To identify distinct phenotypes in STEMI patients using unsupervised machine learning algorithms based on prehospital parameters, and to determine their association with short‐term mortality and cardiovascular outcomes.

Methods

Prospective multicenter observational cohort study including adult patients with prehospital STEMI code activation transported by emergency medical services from January 2022 to August 2025. Only EMS‐transported patients were included; those who self‐presented to the emergency department were excluded. Prehospital variables, including demographic, clinical, and procedural data, were used for clustering. Factor Analysis of Mixed Data and a two‐step clustering: hierarchical clustering (exploring structure and number of clusters) and k‐means (clustering assigning patients to phenotypes). A Random Forest classifier with SHapley Additive exPlanations values was used to identify variables contributing to cluster assignment. The primary outcome was 30‐day all‐cause mortality, assessed through follow‐up records.

Results

Among 744 patients (median age, 65 years; 76.3% male) unsupervised clustering identified three distinct phenotypes: Phenotype‐1 (70.3%) characterized by hemodynamic stability, vessel locations, Killip class I presentation (70.6%), and favourable laboratory parameters; Phenotype‐2 (24.3%) presented higher comorbidity burden and metabolic derangements; and Phenotype‐3 (5.4%) exhibiting profound hemodynamic instability, severe respiratory failure, out‐of‐hospital cardiac arrest with return of spontaneous circulation (87.5%), Killip class IV presentation (67.5%), and marked metabolic derangements. The 30‐day mortality rates were: 3.4% in Phenotype‐1, 22.1% in Phenotype‐2, and 75.0% in Phenotype‐3.

Conclusions

Three clinically distinct STEMI phenotypes were identified with markedly different mortality risks and treatment requirements during prehospital care. Phenotypes derived from readily available prehospital parameters may facilitate early risk stratification, optimize triage decisions, and guide individualized therapeutic strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ST Elevation Myocardial InfarctionUnsupervised Machine LearningEmergency Medical ServicesHumansFemaleRisk AssessmentAgedClustering AlgorithmsMiddle AgedProspective StudiesMalePhenotypeRandom ForestCluster Analysis

Stichwörter der Autor:innen

STEMIclinical decision makingmachine learningphenotypeprehospital care

Autor:innen und Institutionen

  • Emergency Department, Hospital Universitario Rio Hortega, Valladolid, Spain.
  • Faculty of Medicine, Universidad de Valladolid, Valladolid, Spain.
  • CIBER of Respiratory Diseases (CIBERES), Institute of Health Carlos III, Madrid, Spain.
  • Valladolid Health Research Institute (IBioVALL), Valladolid, Spain.
  • Emergency Department, Hospital Clínico Universitario, Valladolid, Spain.
  • Cardiology Department, Hospital Clínico Universitario de Valladolid, Valladolid, Spain.

ORCID-Profile: Ancor Sanz-García

Förderung

  • Institute of Health Carlos III
  • MCIN/AEI/10.13039/501100011033
  • Instituto de Salud Carlos III

Zitieren

APA

Ramos-Rodríguez, A., López-Izquierdo, R., Del Pozo Vegas, C., Plaza-Martín, M., Tapia-Ballesteros, C., Delgado Benito, J. F., Sanz-García, A., & Martín-Rodríguez, F. (2026). Prehospital Risk Stratification Using Unsupervised Machine Learning in STEMI. European Journal of Clinical Investigation, 56(5). https://doi.org/10.1111/eci.70214

Vancouver

Ramos-Rodríguez A, López-Izquierdo R, Del Pozo Vegas C, Plaza-Martín M, Tapia-Ballesteros C, Delgado Benito JF, et al. Prehospital Risk Stratification Using Unsupervised Machine Learning in STEMI. European Journal of Clinical Investigation. 2026;56(5). doi:10.1111/eci.70214

BibTeX
@article{RamosRodrguez2026,
  author = {Ramos-Rodríguez, Ana and López-Izquierdo, Raúl and Del Pozo Vegas, Carlos and Plaza-Martín, María and Tapia-Ballesteros, Cristina and Delgado Benito, Juan F and Sanz-García, Ancor and Martín-Rodríguez, Francisco},
  title = {Prehospital Risk Stratification Using Unsupervised Machine Learning in STEMI},
  journal = {European Journal of Clinical Investigation},
  year = {2026},
  volume = {56},
  number = {5},
  doi = {10.1111/eci.70214}
}
Kostenlos starten →