Related Experiment Video
Updated: Aug 17, 2025
Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System
Published on: April 11, 2025
An artificial intelligence-enabled ECG algorithm for identifying ventricular premature contraction during sinus
Sheng-Nan Chang1, Yu-Heng Tseng2, Jien-Jiun Chen1
1Division of Cardiology, Department of Internal Medicine, National Taiwan University College of Medicine and Hospital Yun-Lin Branch, Dou-Liu City, Taiwan.
Insights
Artificial intelligence (AI) can detect ventricular premature complexes (VPCs) using normal sinus rhythm (NSR) electrocardiograms (ECGs). This AI-enabled ECG approach offers rapid, point-of-care identification of VPCs, improving upon traditional long-term monitoring methods.
Area of Science:
- Cardiology
- Artificial Intelligence in Medicine
- Medical Diagnostics
Background:
- Ventricular premature complexes (VPCs) are common arrhythmias with potential to trigger serious cardiac events.
- Current VPC screening methods are costly, time-consuming, and less effective for low-frequency VPCs.
- Twelve-lead electrocardiograms (ECGs) are a low-cost, widely accessible diagnostic tool.
Purpose of the Study:
- To develop and evaluate an AI-enabled ECG algorithm for identifying patients with VPCs during normal sinus rhythm (NSR).
- To leverage machine learning for improved detection of VPCs, overcoming limitations of traditional monitoring.
Main Methods:
- A convolutional neural network (CNN) algorithm was developed to detect VPC signatures in standard 12-lead ECGs during NSR.
- ECG records from 398 patients with VPCs were analyzed, including 1617 NSR ECGs without VPCs and 753 normal ECGs for comparison.
- Both image and time-series data formats were utilized for training and optimizing CNN models (InceptionV3, ResNet50V2).
Main Results:
- The AI-enabled ECG models demonstrated satisfactory performance in predicting VPCs.
- The single-input image model (InceptionV3) achieved an accuracy of 0.895 (95% CI 0.683-0.937).
- The multi-input time-series model (ResNet50V2) achieved an accuracy of 0.880 (95% CI 0.646-0.943), outperforming the single-input time-series model (0.840).
Conclusions:
- AI-enabled ECG analysis during NSR can rapidly identify individuals with VPCs at the point of care.
- This technology holds potential for automatic prediction of VPC episodes, reducing reliance on prolonged monitoring.
- AI offers a promising, efficient alternative for detecting and managing VPCs in clinical practice.
Background:
Ventricular premature complex (VPC) is a common arrhythmia in clinical practice. VPC could trigger ventricular tachycardia/fibrillation or VPC-induced cardiomyopathy in susceptible patients. Existing screening methods require prolonged monitoring and are limited by cost and low yield when the frequency of VPC is low. Twelve-lead electrocardiogram (ECG) is low cost and widely used. We aimed to identify patients with VPC during normal sinus rhythm (NSR) using artificial intelligence (AI) and machine learning-based ECG reading.
Methods:
We developed AI-enabled ECG algorithm using a convolutional neural network (CNN) to detect the ECG signature of VPC presented during NSR using standard 12-lead ECGs. A total of 2515 ECG records from 398 patients with VPC were collected. Among them, only ECG records of NSR without VPC (1617 ECG records) were parsed.
Results:
A total of 753 normal ECG records from 387 patients under NSR were used for comparison. Both image and time-series datasets were parsed for the training process by the CNN models. The computer architectures were optimized to select the best model for the training process. Both the single-input image model (InceptionV3, accuracy: 0.895, 95% confidence interval [CI] 0.683-0.937) and multi-input time-series model (ResNet50V2, accuracy: 0.880, 95% CI 0.646-0.943) yielded satisfactory results for VPC prediction, both of which were better than the single-input time-series model (ResNet50V2, accuracy: 0.840, 95% CI 0.629-0.952).
Conclusions:
AI-enabled ECG acquired during NSR permits rapid identification at point of care of individuals with VPC and has the potential to predict VPC episodes automatically rather than traditional long-time monitoring.
Related Concept Videos
01:29Electrocardiogram
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and...
01:25ECG Interpretation of Arrhythmias II: Atrial, Junctional and Ventricular Arrhythmias
01:16ECG Interpretation of Arrhythmias I: Sinus Arrhythmias
Types of Arrhythmias
Sinus Node Arrhythmias
Sinus Bradycardia: Originating from the sinoatrial (SA) node, sinus bradycardia involves slower impulses, resulting in a heart rate of less than 60 beats per minute (bpm). Causes include sleep, vagal stimulation, beta-blockers, hypothyroidism,...
01:25Correlation between ECG and Cardiac Cycle
A cardiac action potential originates in the SA node and spreads throughout the atria and the AV node in approximately 0.03 seconds. This results in the P wave in an ECG and triggers atrial contraction. The action potential is then briefly slowed at the AV node, allowing the atria to contract and fill the ventricles with blood before...
01:30Pulse rhythm
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
01:29Dysrhythmias III: Characteristics of Dysrhythmias