Atrial Fibrillation Detection Using Feature Based Algorithm and Deep Convolutional Neural Network

Aims: Electrocardiographic waveforms (ECG) are recognized as the most reliable method to detect abnormal heart rhythms such as atrial fibrillation. This task is challenging when the signals are distorted by noise. This paper presents an automatic classification algorithm to classify short lead ECGs in terms of abnormality of heart rhythm (AF or alternative rhythms) and quality (noisy recordings). Methods: To meet this end, at first baseline wander removal and Butterworth filter for each signal are applied as a preprocessing stage. Due to the existence of noise in recordings, high quality beats are selected for any further analysis using cycle quality assessment. Then, three sets of features defined as correlation coefficient, fractal dimension and variance of R peaks are extracted to predict noisy recordings. Two separate approaches are employed to classify other three classes. The first approach is the feature based methodology and the second one is the applying deep neural networks. In the first approach, features from different domains are extracted. The method for AF-detection utilizes and characterizes variability in RR-intervals which are extracted by applying classic Pan-Tompkins algorithm. To improve the accuracy of the AF-detection, atrial activity is analyzed by understanding whether the P-wave is present in signal. This is done by investigating the morphology of P-waves. Heart rate abnormality and the existence of premature beats in a signal are regarded as two characteristics to distinguish non-AF rhythms. The whole sets of features are fed into a neural network classifier. Another approach uses the segments with 600 samples as the input of a 1 dimensional convolutional neural network. The output obtained from both approaches are combined using a decision table and finally the recordings are classified into three classes. Results: The proposed method is evaluated using scoring function from 2017 PhysioNet/CinC Challenge and achieved an overall score of 80% and 71% on the training dataset and hidden test dataset, respectively.