Dynamic ECG features for atrial fibrillation recognition.

BACKGROUND: Atrial fibrillation (AF) can cause the formation of blood clots in the heart. The clots may move to the brain and cause a stroke. Therefore, this study analyzed the ECG features of AF and normal sinus rhythm signals for AF recognition which were extracted by using a second-order dynamic system (SODS) concept. OBJECTIVE: To find the appropriate windowing length for feature extraction based on SODS and to determine a machine learning method that could provide higher accuracy in recognizing AF. METHOD: ECG features were extracted based on a dynamic system (DS) that uses a second-order differential equation to describe the short-term behavior of ECG signals according to the natural frequency (ω), damping coefficient, (ξ), and forcing input (u). The extracted features were windowed into 2, 3, 4, 6, 8, and 10 second episodes to find the appropriate windowing size for AF signal processing. ANOVA and t-tests were used to determine the significant features. In addition, pattern recognition machine learning methods (an artificial neural network (ANN) and a support vector machine (SVM)) with k-fold cross validation (k-CV) were used to develop the ECG recognition system. RESULTS: Significant differences (p < 0.0001) were observed among all ECG groups (NSR, N, AF) using 2, 3, 4 and 6 second episodes for the features ω and u/ω; 4, 6 and 8 second episodes for features ω and u; 4 and 6 second episodes for features ω, u and u/ω, and; 10 second episodes for the feature ξ. The highest accuracy for AF recognition (AF, NSR) using ANN with k-CV was 95.3% using combination of features (ω and u; ω, u and u/ω) and SVM with k-CV was 95.0% using a combination of features ω, u and u/ω. CONCLUSION: This study found that 4 s is the most appropriate windowing length, using two features (ω and u) for AF detection with an accuracy of 95.3%. Moreover, the pattern recognition learning machine uses an ANN with 10-fold cross validation based on DS.

Atrial fibrillation classification and association between the natural frequency and the autonomic nervous system.

BACKGROUND: The feasibility study of the natural frequency (ω) obtained from a second-order dynamic system applied to an ECG signal was discovered recently. The heart rate for different ECG signals generates different ω values. The heart rate variability (HRV) and autonomic nervous system (ANS) have an association to represent cardiovascular variations for each individual. This study further analyzed the ω for different ECG signals with HRV for atrial fibrillation classification. METHODS: This study used the MIT-BIH Normal Sinus Rhythm (nsrdb) and MIT-BIH Atrial Fibrillation (afdb) databases for healthy human (NSR) and atrial fibrillation patient (N and AF) ECG signals, respectively. The extraction of features was based on the dynamic system concept to determine the ω of the ECG signals. There were 35,031 samples used for classification. RESULTS: There were significant differences between the N & NSR, N & AF, and NSR & AF groups as determined by the statistical t-test (p<0.0001). There was a linear separation at 0.4s(-1) for ω of both databases upon using the thresholding method. The feature ω for afdb and nsrdb falls within the high frequency (HF) and above the HF band, respectively. The feature classification between the nsrdb and afdb ECG signals was 96.53% accurate. CONCLUSIONS: This study found that features of the ω of atrial fibrillation patients and healthy humans were associated with the frequency analysis of the ANS during parasympathetic activity. The feature ω is significant for different databases, and the classification between afdb and nsrdb was determined.