Identification and risk stratification of coronary disease by artificial intelligence-enabled ECG
Related Experiment Video
Updated: Jul 8, 2025
Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System
Published on: April 11, 2025
Samir Awasthi1,2, Nikhil Sachdeva1,2, Yash Gupta1,2
1Anumana, Inc, One Main Street, Cambridge, MA, USA.
Insights
An artificial intelligence tool (ECG-AI) enhances atherosclerotic cardiovascular disease (ASCVD) risk prediction beyond traditional methods. This AI tool improves risk stratification for coronary artery disease (CAD) and myocardial infarction (MI), offering more accurate assessments.
Area of Science:
- Cardiology
- Artificial Intelligence in Medicine
- Public Health
Background:
- Atherosclerotic cardiovascular disease (ASCVD) is a leading global cause of mortality, primarily driven by coronary artery disease (CAD).
- Current ASCVD risk estimators, like the Pooled Cohort Equations (PCE), have suboptimal accuracy for risk stratification and primary prevention.
- There is a critical need for improved methods to accurately assess ASCVD risk, especially in individuals where PCE may underestimate or overestimate risk.
Purpose of the Study:
- To develop and validate an artificial intelligence-based electrocardiogram analysis tool (ECG-AI) for detecting CAD.
- To evaluate the additive value of ECG-AI in ASCVD risk stratification compared to the PCE.
- To assess the utility of ECG-AI for identifying specific indicators of CAD, such as coronary artery calcium (CAC) and prior myocardial infarction (MI).
Main Methods:
- Utilized deep electronic health record data from over 7 million patients across 70+ healthcare facilities.
- Developed independent ECG-AI models using neural networks to identify CAC score ≥300, obstructive CAD, and regional left ventricular akinesis indicative of prior MI.
- Assessed ECG-AI's performance in a retrospective observational study of patients without prior ASCVD, comparing its risk stratification to PCE.
Main Results:
- ECG-AI demonstrated high accuracy in identifying CAC ≥300 (AUROC 0.88), obstructive CAD (AUROC 0.85), and regional akinesis (AUROC 0.94).
- An ensemble ECG-AI model independently and additively predicted 3, 5, and 10-year risks for acute coronary events and mortality.
- Patients positive on 1, 2, or 3 disease-specific ECG-AI models showed significantly increased 3-year acute coronary event risk (HRs 2.41, 4.23, 11.75, respectively) compared to those with zero positive models.
Conclusions:
- ECG-AI shows significant potential to enhance ASCVD risk stratification, addressing limitations of current methods.
- The tool offers accessible risk assessment for patients with suboptimal PCE estimates and for risk evaluation over shorter timeframes (<10 years).
- ECG-AI can provide valuable additive information to existing risk calculators, improving the identification of individuals at high risk for cardiovascular events.
Background:
Atherosclerotic cardiovascular disease (ASCVD) is the leading cause of death worldwide, driven primarily by coronary artery disease (CAD). ASCVD risk estimators such as the pooled cohort equations (PCE) facilitate risk stratification and primary prevention of ASCVD but their accuracy is still suboptimal.
Methods:
Using deep electronic health record data from 7,116,209 patients seen at 70+ hospitals and clinics across 5 states in the USA, we developed an artificial intelligence-based electrocardiogram analysis tool (ECG-AI) to detect CAD and assessed the additive value of ECG-AI-based ASCVD risk stratification to the PCE. We created independent ECG-AI models using separate neural networks including subjects without known history of ASCVD, to identify coronary artery calcium (CAC) score ≥300 Agatston units by computed tomography, obstructive CAD by angiography or procedural intervention, and regional left ventricular akinesis in ≥1 segment by echocardiogram, as a reflection of possible prior myocardial infarction (MI). These were used to assess the utility of ECG-AI-based ASCVD risk stratification in a retrospective observational study consisting of patients with PCE scores and no prior ASCVD. The study period covered all available digitized EHR data, with the first available ECG in 1987 and the last in February 2023.
Findings:
ECG-AI for identifying CAC ≥300, obstructive CAD, and regional akinesis achieved area under the receiver operating characteristic (AUROC) values of 0.88, 0.85, and 0.94, respectively. An ensembled ECG-AI identified 3, 5, and 10-year risk for acute coronary events and mortality independently and additively to PCE. Hazard ratios for acute coronary events over 3-years in patients without ASCVD that tested positive on 1, 2, or 3 versus 0 disease-specific ECG-AI models at cohort entry were 2.41 (2.14-2.71), 4.23 (3.74-4.78), and 11.75 (10.2-13.52), respectively. Similar stratification was observed in cohorts stratified by PCE or age.
Interpretation:
ECG-AI has potential to address unmet need for accessible risk stratification in patients in whom PCE under, over, or insufficiently estimates ASCVD risk, and in whom risk assessment over time periods shorter than 10 years is desired.
Funding:
Anumana.
More Related Videos
06:16Signal Acquisition, Score Interpretation, and Economics of a Non-Invasive Point-of-Care Test for Coronary Artery Disease
Published on: August 9, 2024
18:11A Research Method For Detecting Transient Myocardial Ischemia In Patients With Suspected Acute Coronary Syndrome Using Continuous ST-segment Analysis
Published on: December 28, 2012
Related Concept Videos
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...