Related Experiment Video
Updated: Dec 11, 2025
08:10
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
2.0K
[Detection algorithm of paroxysmal atrial fibrillation with sparse coding based on Riemannian manifold]
Xianhui Meng1, Ming Liu1, Peng Xiong1
1Key Laboratory of Digital Medical Engineering of Hebei Province, College of Electronic and Information Engineering, Hebei University, Baoding, Hebei 071002, P.R.China.
Summary
A novel algorithm detects paroxysmal atrial fibrillation using sparse coding on Riemannian manifolds, improving early detection of this heart rhythm disorder with high accuracy.
Area of Science:
- Cardiology
- Biomedical Engineering
- Signal Processing
Background:
- Early detection of paroxysmal atrial fibrillation (PAF) is challenging due to its short duration.
- Existing methods may require longer signals or complex parameter tuning.
- Accurate detection is crucial for timely intervention and stroke prevention.
Purpose of the Study:
- To develop a robust and efficient algorithm for early detection of paroxysmal atrial fibrillation.
- To leverage Riemannian manifold geometry and sparse coding for improved heart rate variability analysis.
- To achieve high sensitivity and specificity using shorter physiological signals.
Main Methods:
- Utilized sparse coding on Riemannian manifolds to analyze heart rate variability (RR interval variations).
- Characterized data using computational covariance matrices within the Riemannian manifold space.
- Learned a Riemann dictionary iteratively using an affine invariant Riemannian metric for sparse reconstruction loss.
Main Results:
- Achieved high classification accuracy on the MIT-BIH AF database: 99.34% sensitivity, 95.41% specificity, 97.45% accuracy.
- Demonstrated strong performance on the MIT-BIH NSR database with 95.18% specificity.
- The proposed method requires shorter heart rate variability signals and is parameter-independent.
Conclusions:
- The proposed sparse coding algorithm on Riemannian manifolds offers a precise and efficient method for detecting paroxysmal atrial fibrillation.
- Its ability to use shorter signals and its parameter independence make it suitable for real-time monitoring.
- Potential for long-term monitoring applications in wearable devices for cardiovascular health.
