PVC Detection Using a Convolutional Autoencoder and Random Forest Classifier

Abstract

The accurate detection of premature ventricular contractions (PVCs) in patients is an important task in cardiac care for some patients. In some cases, the usefulness to physicians in detecting PVCs stems from their long-term correlations with dangerous heart conditions. In other cases their potential as a precursor to serious cardiac events may make their detection a useful early warning mechanism. In many of these applications, the long-term nature of the monitoring required and the infrequency of PVCs make manual observation for PVCs impractical. Existing methods of automated PVC detection suffer from drawbacks such as the need to use difficult to extract morphological features, domain-specific features, or large numbers of estimated parameters. In particular, systems using large numbers of trained parameters have the potential to require large amounts of training data and computation and may have issues generalizing due to their potential to overfit. To address some of these drawbacks, we developed a novel PVC detection algorithm based around a convolutional autoencoder to address these weaknesses and validated our method using the MIT-BIH arrhythmia database.

Searching for Premature Ventricular Contraction from Electrocardiogram by Using One-Dimensional Convolutional Neural Network

“…The random forest classifier composed of 10 decision trees takes the latent space representation as input and annotate it. This algorithm achieved an overall accuracy above 97% on the MIT-BIH arrhythmia database [24]. [27].…”

“…The studies [22,23,26] performed wavelet transform on the ECG to obtain 2-D time-frequency images. Moreover, the research [24,25] used the features extracted by a trained autoencoder to recognize PVC. There is no doubt that the above methods are computationally intensive.…”

“…Therefore, achieving a real-time classifier with high accuracy and sensitivity is a challenging problem to address. the research [24,25] used the features extracted by a trained autoencoder to recognize PVC. There is no doubt that the above methods are computationally intensive.…”

Redundancy cancellation of compressed measurements by QRS complex alignment

“…If the peak amplitude is less than the mean value, the existence of a PVC is detected. There are several dedicated methods in the literature for frame classification [46][47][48][49]. Though these methods accurately classify ECG frames, their processes require intensive mathematical operations.…”

Deep-Learning Premature Contraction Localization in 12-lead ECG From Whole Signal Annotations

“…Malek et al in their study describe an improved template matching combined with QRS features analysis and assessment of several different correlation coefficients [2]. Gordon et al use a sofisticated deep learning technique -convolutional autoencoder -for automatic feature extraction and simple random forest for final detection of PVC beats [3]. Contrary to aforementioned approaches, no manually defined features nor selec-tion of the most appropriate features are needed.…”