Automated prediction of spontaneous termination of atrial fibrillation from electrocardiograms

Hayn, Dieter; Edegger, Kurt; Scherr, Daniel; Lercher, Peter; Rotman, B.; Klein, W.; Schreier, Günter

doi:10.1109/cic.2004.1442885

Cited by 14 publications

(15 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These results demonstrate that AF of N type behaves more randomly and oscillates more dramatically. This matches the conclusion obtained by Hayn et al [21], who studied the relation between dominant peak frequency (DAF) and degree of organization of AF. Meanwhile, the correlation coefficient between IS and mIF using linear regression analysis is 0.56 (p 5 0.01).…”

Section: Resultssupporting

confidence: 87%

Time-frequency characterization of atrial fibrillation from surface ECG based on Hilbert-Huang transform

Huang

Chen

Pan

2007

Journal of Medical Engineering & Technology

View full text Add to dashboard Cite

In this paper, based on Hilbert-Huang transform (HHT), we develop a new non-invasive time-frequency analysis method to characterize the dynamic behaviour of atrial fibrillation (AF) from surface ECG. We first extract f waves from single-lead ECG records of AF patients using PCA analysis. To capture the non-stationary behaviours of AF signals at different time scales, we use HHT to find the Hilbert spectrum and instantaneous frequency (IF) distribution of residual signals from principal component analysis. Two important feature variables, namely mean IF (mIF) and index of frequency stability over time (IS), are derived from the IF distribution, and in combination will be able to effectively discriminate two different AF types: self-terminating and non-terminating termination. The proposed AF signal decomposition and analysis method will help us efficiently differentiate individual AF patients, advance our understanding of AF mechanisms, and provide useful guidelines for improving administration of AF patients, especially paroxysmal AF.

show abstract

Section: Resultssupporting

confidence: 87%

Time-frequency characterization of atrial fibrillation from surface ECG based on Hilbert-Huang transform

Huang

Chen

Pan

2007

Journal of Medical Engineering & Technology

View full text Add to dashboard Cite

show abstract

“…Additionally, t test revealed that the SampEn of f p1 has the highest predictive power among all the studied spectral parameters. In previous studies of the AF termination [9,16,29], f p1 has been also revealed as a good predictor of AF termination. The main difference between our work and those studies is that we consider the mathematical regularity of spectral parameters in opposition to direct mean values.…”

Section: Discussionmentioning

confidence: 92%

“…Several groups based their study on the atrial activity (AA) overall peak frequency plus additional spectral characteristics as the main peak power [29] or time-frequency pattern [26]. Other groups tried to predict the evolution of PAF episodes by means of linear classifiers based on the main peak frequency and the mean RR interval [9,16]. In [28], the fibrillation frequency, fibrillation amplitude and exponential decay are extracted from a frequency-shifted and amplitude-scaled version of a log-spectral profile.…”

Section: Introductionmentioning

confidence: 99%

Time and frequency series combination for non-invasive regularity analysis of atrial fibrillation

Vaya

Rieta

2009

Med Biol Eng Comput

View full text Add to dashboard Cite

In this work, we present a new method based on electrocardiogram signal processing to distinguish between the atrial fibrillation (AF) episodes that terminate immediately and those that sustain. The spectrogram of the atrial activity is computed and 12 numerical series of spectral parameters are constructed. The sample entropy (SampEn) of six series are relevant in the characterization of AF termination (p < 0.05). Furthermore, a combined discriminant analysis in both time and frequency domains is performed, which improves the univariant time-frequency analysis. The discriminant analysis achieves optimal combination of parameters so that the percentage of correctly classified recordings reaches 100% for the learning set and 93.33% for the test set. The main conclusion is that the combined analysis of time and frequency series regularity might be used to predict spontaneous termination of paroxysmal AF and could provide information about the organization of atrial activation in AF.

show abstract

“…The features analyzed were selected by the article who obtained the best results in the completion, and therefore the way they processed the ECG and the characteristics they used should, in theory, be representative of the recordings. In total 55 different characteristics were used, from the following articles : Cantini et al (2004), Lemay et al (2004), Hayn et al (2004), Raine and Langley (2004), Mora and Castells (2004), Scherr et al (2007), Petrutiu et al (2006), and Chiarugi et al (2007).…”

Section: Feature Extractionsmentioning

confidence: 99%

Intelligent System Based on Genetic Programming for Atrial Fibrillation Classification

Valenzuela

Rojas

et al. 2009

Applied Artificial Intelligence

View full text Add to dashboard Cite

This article focuses on the development of intelligent classifiers in the area of biomedicine, focusing on the problem of diagnosing cardiac diseases based on the electrocardiogram (ECG), or more precisely, on the differentiation of the types of atrial fibrillations. First of all, we will study the ECG, and the treatment of the ECG in order to work with it with this specific pathology. In order to achieve this we will study different ways of elimination, in the best possible way, of any activity that is not caused by the auriculars. We will study and imitate the ECG treatment methodologies and the characteristics extracted from the electrocardiograms that were used by the researchers who obtained the best results in the Physionet Challenge, where the classification of ECG recordings according to the type of atrial fibrillation (AF) that they showed, was realized. We will extract a great amount of characteristics, partly those used by these researchers and additional characteristics that we consider to be important for the distinction previously mentioned. A new method based on evolutionary algorithms will be used to realize a selection of the most relevant characteristics and to obtain a classifier that will be capable of distinguishing the different types of this pathology.Atrial fibrillation (AF) is the sustained arrhythmia that is most frequently found in clinical practice, present in 0.4% of the total population. Its frequency increases with age and with the presence of structural cardiopathology (Chou and Chen 2008; Khasnis and Thakur 2008). Atrial fibrillation is especially prevalent in the elderly, affecting 2-5% of the population older than 60 years and 10% of people older than 80 years. It is an important cause of ictus, which can be found in about 15% of the patients that suffer from this phenomenon and in 2-8% of the patients

show abstract

Automated prediction of spontaneous termination of atrial fibrillation from electrocardiograms

Cited by 14 publications

References 7 publications

Time-frequency characterization of atrial fibrillation from surface ECG based on Hilbert-Huang transform

Time-frequency characterization of atrial fibrillation from surface ECG based on Hilbert-Huang transform

Time and frequency series combination for non-invasive regularity analysis of atrial fibrillation

Intelligent System Based on Genetic Programming for Atrial Fibrillation Classification

Contact Info

Product

Resources

About