A random forest classifier using a novel CNN-derived segment label achieved an overall accuracy of 0.96 and an F1-score of 0.74 for supra-ventricular ectopic beats on the MIT-BIH Arrhythmia dataset.
Does a random forest classifier with a novel segment label feature improve heartbeat classification accuracy on ECGs?
A novel segment label feature improves the performance of a random forest classifier for identifying specific heartbeat types, particularly SVEB, on ECGs.
OBJECTIVE: Physicians use electrocardiograms (ECG) to diagnose cardiac abnormalities. Sometimes they need to take a deeper look at abnormal heartbeats to diagnose the patients more precisely. The objective of this research is to design a more accurate heartbeat classification algorithm to assist physicians in identifying specific types of the heartbeat. METHODS AND PROCEDURES: In this paper, we propose a novel feature called a segment label, to improve the performance of a heartbeat classifier. This feature, provided by a Convolutional Neural Network, encodes the information surrounding the particular heartbeat. The random forest classifier is trained based on this new feature and other traditional features to classify the heartbeats. RESULTS: We validate our method on the MIT-BIH Arrhythmia dataset following the inter-patient evaluation paradigm. The proposed method is competitive with other similar works. It achieves an accuracy of 0.96, and F1-scores for normal beats, ventricular ectopic beats, and Supra-Ventricular Ectopic Beats (SVEB) of 0.98, 0.93, and 0.74, respectively. The precision and sensitivity for SVEB are 0.76 and 0.78, which outperforms the state-of-the-art methods. CONCLUSION: Using a medical devices embedding our algorithm could ease the physicians' processes of diagnosing cardiovascular diseases, especially for SVEB, in clinical implementation.
Zou et al. (Sat,) conducted a other in Cardiac abnormalities / Arrhythmia. Random forest classifier with a CNN-derived segment label feature vs. State-of-the-art methods was evaluated on Classification accuracy and F1-scores. A random forest classifier using a novel CNN-derived segment label achieved an overall accuracy of 0.96 and an F1-score of 0.74 for supra-ventricular ectopic beats on the MIT-BIH Arrhythmia dataset.