Why the study?
Traditional amplitude-based models often fail to capture disruptions in the underlying phase dynamics when detecting arrhythmic patterns in ECG signals.
Does a Bayesian framework based on circular SDEs improve the detection of phase anomalies in ECG signals compared to traditional AR and Fourier-based methods?
Population
MIT-BIH arrhythmia dataset and simulated ECG signals with phase anomalies
Comparison
Novel Bayesian circular SDE framework vs linear autoregressive model and Fourier-based spectral method
Key result
A Bayesian framework based on circular stochastic differential equations achieved superior accuracy in detecting subtle ECG phase anomalies compared to linear AR and Fourier-based spectral methods.
Authors
Loading...
May enhance subtle ECG anomaly detection; leaves open prospective clinical validation before practice change.
Does a Bayesian framework based on circular SDEs improve the detection of phase anomalies in ECG signals compared to traditional AR and Fourier-based methods?
A novel Bayesian framework using circular stochastic differential equations improves the detection of subtle phase anomalies in ECG signals, offering a new tool for arrhythmia detection.
Chatterjee et al. (2025) studied Arrhythmia. Bayesian framework based on circular stochastic differential equations vs. Linear autoregressive (AR) model and Fourier-based spectral method was evaluated on Detection of subtle phase anomalies. A Bayesian framework based on circular stochastic differential equations achieved superior accuracy in detecting subtle ECG phase anomalies compared to linear AR and Fourier-based spectral methods.