Machine learning integration of echocardiographic and clinical data to improve prediction of survival following myocardial infarction

Sandhir B Prasad; Liam Scanlon; Anish Krishnan; Nicole Ivy Chan; Michael Mallouhi; William Vollbon; William Parsonage; Sankalp Khanna; Andrew Lin; John J Atherton

doi:10.1093/ehjopen/oeaf064

Machine learning integration of echocardiographic and clinical data to improve prediction of survival following myocardial infarction

Eur Heart J Open. 2025 Jun 3;5(3):oeaf064. doi: 10.1093/ehjopen/oeaf064. eCollection 2025 May.

Authors

Sandhir B Prasad^{1

2

3}, Liam Scanlon⁴, Anish Krishnan¹, Nicole Ivy Chan¹, Michael Mallouhi⁵, William Vollbon⁵, William Parsonage^{1

6}, Sankalp Khanna⁷, Andrew Lin⁴, John J Atherton^{1

2}

Affiliations

¹ Department of Cardiology, Royal Brisbane and Women's Hospital, Herston Road, Brisbane, Queensland 4029, Australia.
² Faculty of Medicine, University of Queensland, St Lucia, Queensland 4072, Australia.
³ Faculty of Medicine and Dentistry, Griffith University, 1 Parklands Drive, Southport, Queensland 4215, Australia.
⁴ Monash Victorian Heart Institute and Monash Health Heart, Victorian Heart Hospital, Monash University, 631 Blackburn Road, Clayton, Victoria 3168, Australia.
⁵ Queensland Statewide Cardiac Network, Ministry of Health, 1 Butterfield Street, Queensland 4029, Australia.
⁶ Faculty of Health, Queensland University of Technology, 2 George Street, Brisbane, Queensland 4000, Australia.
⁷ The Australian e-Health Research Centre, CSIRO Health & Biosecurity, 296 Herston Road, Herston, Queensland 4029, Australia.

Abstract

Aims: Machine learning (ML) could improve risk stratification following myocardial infarction (MI). However, previous ML studies for risk prediction following MI did not incorporate comprehensive echocardiographic data. This study sought to use machine learning (ML) to integrate comprehensive echocardiographic and clinical data for the predicting all-cause mortality following MI.

Methods and results: Retrospective study of consecutive patients admitted with MI to a tertiary referral hospital, with echocardiography performed within 24 h of admission. The cohort was randomly split into training (70%) and test (30%) sets. Two ML models (XGBoost and a neural network) were developed using echocardiographic and clinical data, and then compared with conventional logistic regression. The Shapley Additive exPlanations method was used for ML model interpretation. In the final study population of 3202 patients (mean age, 63.2 ± 12.5 years; 29.2% females), ST-elevation MI was present in 28.8%, and the mean cohort LVEF was 52.5 ± 11.2%. At a median follow-up of 4.5 years, there were 465 deaths. In the test set, XGBoost achieved the highest performance (AUC, 0.854), compared with logistic regression (AUC, 0.824; P = 0.006) and the neural network (AUC, 0.808; P = <0.001) for the prediction of death. In the XGBoost model, the highest-ranked predictors included age, renal function, echocardiographic left ventricular outflow velocity time integral, and diastolic parameters. Further, in nested ML models, the addition of echocardiographic parameters provided incremental value beyond clinical variables alone (AUC, 0.854 vs. 0.820; P = 0.002).

Conclusion: ML integration of comprehensive echocardiographic data with clinical data could lead to improved prediction of survival following MI. Clinical implementation should be considered.

Keywords: Echocardiography; Machine Learning; Mortality; Myocardial Infarction; Risk Stratification; XGBoost.