What is the clinical evidence from this study?

Study design: Observational. Population: Acute myocardial infarction (n=15104). Intervention: Deep neural network (DNN) models vs. Traditional machine learning models. Primary outcome: Accuracy of major adverse cardiac events (MACE) prediction at 1-month follow-up.

What does this research mean for the field?

Deep neural network models can predict major adverse cardiac events in patients following discharge for acute myocardial infarction with up to 92.2% accuracy, outperforming traditional machine learning methods. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

July 24, 2025Osong Public Health and Research Perspectives1 citationsOpen Access

Deep learning-based prognosis of major adverse cardiac events in patients with acute myocardial infarction: a retrospective observational study in the Republic of Korea

VKVungsovanreach Kong KKKyung-Ah Kim HSHo Sun Shon

Key Result

Deep neural network models predicted major adverse cardiac events in patients following discharge for acute myocardial infarction with an accuracy of 92.2% at 1 month, outperforming traditional machine learning.

Study Design

Type

Observational (n=15,104)

Multicenter

Yes

Structured PICO

Does a deep neural network model improve the prediction of major adverse cardiac events in patients with acute myocardial infarction compared to traditional machine learning models?

Population

15,104 patients diagnosed with acute myocardial infarction (AMI) admitted to the hospital, from the Korea Acute Myocardial Infarction Registry (KAMIR). Mean age 65.91 years, 72.1% female.

Intervention

Deep neural network (DNN) models for multiclass classification of major adverse cardiac events (MACE)

Comparator

Traditional machine learning models (multinomial logistic regression, random forest, decision trees, support vector machines, k-nearest neighbors, and extreme gradient boosting)

Outcome

Major adverse cardiac events (MACE) categorized into coronary artery bypass grafting (CABG), cardiac death (CD), myocardial infarction (MI), and repeat percutaneous coronary intervention (Re-PCI) at 1, 6, and 12 monthscomposite

Deep neural network models demonstrated high accuracy in predicting post-discharge major adverse cardiac events in patients with acute myocardial infarction, outperforming traditional machine learning algorithms.

Main Result

Absolute Event Rate: 92.2% vs 84.2%

Limitations

Processes only clinical data and does not incorporate image data, which may further enhance prediction accuracy.
Trained exclusively on the KAMIR dataset predominantly sourced from South Korean hospitals, limiting generalizability.

Abstract

BACKGROUND: This study developed deep neural network (DNN) models capable of accurately classifying major adverse cardiac events (MACE) in patients with acute myocardial infarction (AMI) after hospital discharge, across 3 follow-up intervals: 1, 6, and 12 months. METHODS: DNN models were constructed to predict post-discharge MACE across 4 categories. Multiple traditional machine learning models were implemented as controls to benchmark the performance of our DNN approach. All models were evaluated based on their ability to predict MACE occurrence during the specified follow-up periods. RESULTS: The DNN models demonstrated superior predictive performance over conventional machine learning methods, achieving high accuracies of 0.922, 0.884, and 0.913 for the 1-month, 6-month, and 12-month follow-up periods, respectively. CONCLUSION: The high accuracy of our DNN models highlights their practical advantages for AMI diagnosis and guidance of follow-up treatment. These models can serve as valuable decision support tools, enabling clinicians to optimize the overall management of AMI patients and potentially enhance their hospitalization experience.

问 AI

Bookmark

View Full Paper