Related Experiment Video
Updated: Jan 18, 2026
Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function
Published on: December 11, 2019
Efficient Deep Learning-Based Arrhythmia Detection Using Smartwatch ECG Electrocardiograms
Herwin Alayn Huillcen Baca1, Flor de Luz Palomino Valdivia1
1Faculty of Engineering, Academic Department of Engineering and Information Technology, Jose Maria Arguedas National University, Andahuaylas 03701, Peru.
Insights
This study introduces an efficient 1D CNN model for detecting cardiac arrhythmias from smartwatch ECGs. The model demonstrates high accuracy in multiclass detection, supporting early diagnosis and clinical application.
Area of Science:
- Biomedical Engineering
- Artificial Intelligence in Healthcare
- Cardiology
Background:
- Cardiovascular diseases, including cardiac arrhythmias, are a leading global cause of death.
- Early and accurate diagnosis of arrhythmias is critical but challenged by ECG interpretation subjectivity and noise.
- Current deep learning models for arrhythmia detection often neglect efficiency and clinical applicability, focusing solely on open datasets.
Purpose of the Study:
- To propose an efficient 1D Convolutional Neural Network (CNN) model for detecting cardiac arrhythmias using electrocardiograms (ECGs) from smartwatches.
- To develop a model suitable for practical clinical deployment for continuous monitoring and early arrhythmia detection.
- To evaluate the model's efficiency and effectiveness on both binary and multiclass arrhythmia detection tasks.
Main Methods:
- Developed an efficient 1D CNN architecture for smartwatch ECG-based arrhythmia detection.
- Trained and evaluated a binary arrhythmia detection model using the UMass Medical School Simband dataset.
- Validated a multiclass arrhythmia detection model using the MIT-BIH arrhythmia database and compared it with state-of-the-art methods.
Main Results:
- The binary model achieved 64.81% accuracy, 89.47% sensitivity, and 6.25% specificity, highlighting its reliability, particularly in specificity.
- The model demonstrated computational efficiency with 1.2 million parameters and 68.48 MFlops.
- The multiclass model achieved high performance with 99.57% accuracy, 99.57% sensitivity, and 99.47% specificity, positioning it among the best state-of-the-art proposals.
Conclusions:
- The proposed 1D CNN model is efficient and reliable for detecting cardiac arrhythmias from smartwatch ECGs.
- The model's performance, especially in multiclass detection, supports its potential for practical clinical application in early arrhythmia diagnosis and monitoring.
- This work addresses the gap in efficient deep learning models for real-world arrhythmia detection using wearable technology.
Abstract:
According to the World Health Organization, cardiovascular diseases, including cardiac arrhythmias, are the leading cause of death worldwide due to their silent, asymptomatic nature. To address this problem, early and accurate diagnosis is crucial. Although this task is typically performed by a cardiologist, diagnosing arrhythmias can be imprecise due to the subjectivity of reading and interpreting electrocardiograms (ECGs), and electrocardiograms are often subject to noise and interference. Deep learning-based approaches present methods for automatically detecting arrhythmias and are positioned as an alternative to support cardiologists' diagnoses. However, these methods are trained and tested only on open datasets of electrocardiograms from Holter devices, whose results aim to improve the accuracy of the state of the art, neglecting the efficiency of the model and its application in a practical clinical context. In this work, we propose an efficient model based on a 1D CNN architecture to detect arrhythmias from smartwatch ECGs, for subsequent deployment in a practical scenario for the monitoring and early detection of arrhythmias. Two datasets were used: UMass Medical School Simband for a binary arrhythmia detection model to evaluate its efficiency and effectiveness, and the MIT-BIH arrhythmia database to validate the multiclass model and compare it with state-of-the-art models. The results of the binary model achieved an accuracy of 64.81%, a sensitivity of 89.47%, and a specificity of 6.25%, demonstrating the model's reliability, especially in specificity. Furthermore, the computational complexity was 1.2 million parameters and 68.48 MFlops, demonstrating the efficiency of the model. Finally, the results of the multiclass model achieved an accuracy of 99.57%, a sensitivity of 99.57%, and a specificity of 99.47%, making it one of the best state-of-the-art proposals and also reconfirming the reliability of the model.
More Related Videos
Related Concept Videos
01:29Electrocardiogram
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and...
01:30Dysrhythmias V: Evaluating Dysrhythmias
01:23Holter Monitor: 24-Hour Monitoring
01:30Pulse rhythm
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
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...
01:29Disturbances in Heart Rhythm
Arrhythmias are categorized by their speed, rhythm, and origin. A slow heart...