A large-scale 12-lead electrocardiogram dataset for acute coronary syndrome prediction containing 19,955 ECGs
Xinyue Du1, Ying Liu2, Lingli Wang1
1Department of Cardiovascular Medicine, Cardiovascular Research Center, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China.
Insights
A new, large dataset of electrocardiograms (ECGs) for acute coronary syndrome (ACS) prediction is now available. This resource, along with a baseline AI model, aims to advance cardiovascular disease research and diagnosis.
Area of Science:
- Cardiology
- Artificial Intelligence
- Medical Informatics
Background:
- Acute coronary syndrome (ACS) is a critical manifestation of coronary heart disease, necessitating rapid diagnosis via electrocardiograms (ECGs).
- Existing artificial intelligence (AI) models show promise but are hindered by limited, accessible ECG datasets for ACS prediction.
- Prompt intervention is crucial for patients with occlusion myocardial infarction (OMI), a severe ACS subtype.
Purpose of the Study:
- To introduce a comprehensive 12-lead ECG dataset for acute coronary syndrome (ACS) prediction.
- To provide a baseline deep learning model for occlusion myocardial infarction (OMI) detection.
- To facilitate AI-driven research and development in cardiovascular diagnostics.
Main Methods:
- Compiled a dataset of 19,955 ten-second ECG recordings (500 Hz) from 18,909 patients who underwent digital subtraction angiography.
- Annotated the dataset with labels for ST-elevation myocardial infarction, non-ST-elevation myocardial infarction, unstable angina, OMI, and infarction locations.
- Developed and open-sourced a baseline deep learning model for OMI detection, validated by physician assessments.
Main Results:
- Established a large-scale, openly accessible 12-lead ECG dataset specifically for ACS and OMI research.
- Demonstrated the utility of the dataset by developing and releasing a functional baseline deep learning model for OMI detection.
- Provided clinical diagnostic benchmarks through expert physician assessments of ACS and OMI identification.
Conclusions:
- The newly released ECG dataset and baseline AI model represent significant resources for advancing AI applications in acute coronary syndrome diagnosis.
- This initiative addresses the scarcity of large, labeled ECG datasets, paving the way for more robust AI tools in emergency cardiology.
- The open-sourced nature of the data and model encourages further research and innovation in AI-powered cardiovascular diagnostics.
Abstract:
Acute coronary syndrome(ACS) is a common cardiovascular disease and a severe type of coronary heart disease. Electrocardiograms(ECGs) are the initial and indispensable examination for patients suspected of ACS in emergency treatment. Particularly in patients with occlusion myocardial infarction(OMI), prompt medical intervention is imperative. Although ECG-based artificial intelligence(AI) models have achieved high diagnostic accuracy in conditions such as atrial fibrillation and heart failure, their application to ACS prediction has been limited by the scarcity of large, openly available ECG datasets. In this study, we present a comprehensive 12-lead ECG dataset for ACS prediction, comprising 19,955 ten-second recordings sampled at 500 Hz from 18,909 patients-all of whom underwent digital subtraction angiography. The dataset includes labels for ST-elevation myocardial infarction, non-ST-elevation myocardial infarction, unstable angina, OMI, and infarction locations. Two physicians also assessed ACS and OMI identification, providing clinical diagnostic benchmarks. Furthermore, we developed and open-sourced a baseline deep learning model for OMI detection. This database and baseline model offer valuable resources for advancing AI research in ACS.
Related Concept Videos
01:30Acute Coronary Syndrome III: Diagnostic Studies
01:29Electrocardiogram
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and...
01:28Electrocardiogram Fundamentals
An electrocardiogram (ECG) is a diagnostic tool for identifying cardiac conditions such as arrhythmias, conduction abnormalities, and myocardial ischemia.
Definition
An electrocardiogram (ECG) visualizes the heart's electrical activity by tracing the electrical movement associated with each heartbeat on a graph or monitor. As the heart beats, an electrical wave passes through it, correlating with the cardiac cycle events.
Parts of an ECG
An ECG utilizes electrodes on the skin...
01:30Acute Coronary Syndrome I: Introduction
01:19Acute Coronary Syndrome II: Pathophysiology and Clinical Manifestations
01:26Acute Coronary Syndrome V: Nursing Management