Suscribirse

Prognostic Implications of Machine Learning Algorithm–Supported Diagnostic Classification of Myocardial Injury Using the Fourth Universal Definition of Myocardial Infarction - 07/05/25

Doi : 10.1016/j.hlc.2024.11.023 
Kristina Lambrakis, BSc a, b, c, , Ehsan Khan, MBBS, MMed a, d, Zhibin Liao, PhD e, Joey Gerlach, BN d, f, Adam J. Nelson, MBBS, PhD, MBA b, d, g, Shaun G. Goodman, MD, MSc h, Tom Briffa, PhD i, Louise Cullen, MBBS, PhD j, k, l, Johan Verjans, MD, PhD d, e, f, Derek P. Chew, MBBS, MPH, PhD a, b, c, f
a College of Medicine and Public Health, Flinders University of South Australia, Adelaide, SA, Australia 
b Victorian Heart Institute, Monash University, Melbourne, Vic, Australia 
c MonashHeart, Monash Health, Melbourne, Vic, Australia 
d South Australian Department of Health, Adelaide, SA, Australia 
e Australian Institute of Machine Learning, The University of Adelaide, Adelaide, SA, Australia 
f South Australian Health and Medical Research Institute, Adelaide, SA, Australia 
g Faculty of Health and Medical Sciences, The University of Adelaide, Adelaide, SA, Australia 
h Division of Cardiology, St. Michael’s Hospital, University of Toronto, Toronto, ON, and Canadian VIGOUR Centre, University of Alberta, Edmonton, AB, Canada 
i School of Population and Global Health, The University of Western Australia, Perth, WA, Australia 
j Emergency and Trauma Centre, Royal Brisbane and Women’s Hospital, Brisbane, Qld, Australia 
k School of Public Health, Queensland University of Technology, Brisbane, Qld, Australia 
l School of Medicine, The University of Queensland, Brisbane, Qld, Australia 

Corresponding author at: Victorian Heart Hospital, 631 Blackburn Road, Clayton, VIC 3168, AustraliaVictorian Heart Hospital631 Blackburn RoadClaytonVic3168Australia

Abstract

Background

With widespread adoption of high-sensitivity troponin assays, more individuals with myocardial injury are now identified, with type 1 myocardial infarction (T1MI) being less common despite having the most well-established evidence base to inform care. This study assesses the temporal time course of cardiovascular events among various forms of myocardial injury.

Method

Consecutive hospital encounters were identified. Using the first episode of care during the sampling period, myocardial injury classifications (i.e., T1MI, acute injury/type 2 myocardial infarction [T2MI], chronic injury, and no injury) were established via two machine learning algorithms. The temporal time course of increased hazard for mortality, recurrent myocardial infarction, heart failure, and arrhythmia over 3 years were explored.

Results

There were 176,787 index episodes; 6.9% were classified as T1MI, 6.0% as acute injury/T2MI, and 26.7% as chronic injury. Although each classification was associated with an early increased risk of all-cause mortality compared with no injury (incidence rate ratio [IRR]<30 days: T1MI: 19.97 [95% confidence interval 12.50–32.69]; acute injury/T2MI: 26.51 [16.80–42.97]; chronic injury: 15.37 [10.22–23.95]), the instantaneous relative hazard for recurrent myocardial infarction was highest in those with initial T1MI (IRR<30 days: T1MI: 28.81 [22.75–36.76]; acute injury/T2MI: 10.23 [7.60–13.77]; chronic injury:5.54 [4.34–7.41]). In contrast, the instantaneous hazard for heart failure in those with initial acute injury/T2MI and chronic injury remained increased over long-term follow up unlike in T1MI (IRR1 3 yrs: T1MI: 5.52 [4.99–6.09]; acute injury/T2MI: 10.36 [9.51–11.30]; chronic injury:7.40 [6.90–7.94]).

Conclusions

The substantial and persistent rate of late cardiac events highlights the need to establish an evidence base for the therapeutic management of “non-T1MI” diagnostic classifications and suggests opportunity to improve late outcomes using existing and emerging therapies.

El texto completo de este artículo está disponible en PDF.

Keywords : Troponin, Myocardial Infarction, Myocardial Injury, Diagnosis, Artificial Intelligence


Esquema


Crown Copyright © 2024  Publicado por Elsevier Masson SAS. Todos los derechos reservados.
Añadir a mi biblioteca Eliminar de mi biblioteca Imprimir
Exportación

    Exportación citas

  • Fichero

  • Contenido

Vol 34 - N° 5

P. 497-505 - mai 2025 Regresar al número
Artículo precedente Artículo precedente
  • Practice Change in Surgical Treatment Strategies for Ischaemic Mitral Regurgitation and Late Outcomes
  • Yaerhim Shin, John K. French, Mahnoor Mian, Dominic Y. Leung, Nguyen Giang Tien Tran, Hugh D. Wolfenden, Rebecca Dignan
| Artículo siguiente Artículo siguiente
  • Psychosocial Well-Being and Healthy Eating in Cardiac Rehabilitation: A National Survey of Cardiac Rehabilitation Practitioners Self-Reported Practices
  • Sarah Gauci, Georgia K. Chaseling, Susie Cartledge, Madeline L. West, Ling Zhang, Clara Zwack, Matthew Hollings, Tom Briffa, Robyn Gallagher, Julie Redfern, Adrienne O’Neil

Bienvenido a EM-consulte, la referencia de los profesionales de la salud.
El acceso al texto completo de este artículo requiere una suscripción.

¿Ya suscrito a @@106933@@ revista ?

@@150455@@ Voir plus

Mi cuenta


Declaración CNIL

EM-CONSULTE.COM se declara a la CNIL, la declaración N º 1286925.

En virtud de la Ley N º 78-17 del 6 de enero de 1978, relativa a las computadoras, archivos y libertades, usted tiene el derecho de oposición (art.26 de la ley), el acceso (art.34 a 38 Ley), y correcta (artículo 36 de la ley) los datos que le conciernen. Por lo tanto, usted puede pedir que se corrija, complementado, clarificado, actualizado o suprimido información sobre usted que son inexactos, incompletos, engañosos, obsoletos o cuya recogida o de conservación o uso está prohibido.
La información personal sobre los visitantes de nuestro sitio, incluyendo su identidad, son confidenciales.
El jefe del sitio en el honor se compromete a respetar la confidencialidad de los requisitos legales aplicables en Francia y no de revelar dicha información a terceros.


Todo el contenido en este sitio: Copyright © 2026 Elsevier, sus licenciantes y colaboradores. Se reservan todos los derechos, incluidos los de minería de texto y datos, entrenamiento de IA y tecnologías similares. Para todo el contenido de acceso abierto, se aplican los términos de licencia de Creative Commons.