Key result
The CAB framework, utilizing a Generative Adversarial Network and Bi-LSTM, achieved an overall classification accuracy of 99.71% for detecting heart arrhythmias from imbalanced ECG sensor data.
Why the study?
Automatic ECG classification is hindered by difficulty in extracting ECG features and limited labeled data, which degrades classification performance.
Answers are grounded in this paper and cite their sources.
A GAN-based data augmentation and Bi-LSTM classification framework (CAB) achieved 99.71% accuracy in classifying imbalanced ECG arrhythmia data, significantly improving the detection of rare heartbeat types.
Intelligently detecting anomalies in health sensor data streams (e.g., Electrocardiogram, ECG) can improve the development of E-health industry. The physiological signals of patients are collected through sensors. Timely diagnosis and treatment save medical resources, promote physical health, and reduce complications. However, it is difficult to automatically classify the ECG data, as the features of ECGs are difficult to extract. And the volume of labeled ECG data is limited, which affects the classification performance. In this paper, we propose a Generative Adversarial Network (GAN)-based deep learning framework (called CAB) for heart arrhythmia classification. CAB focuses on improving the detection accuracy based on a small number of labeled samples. It is trained based on the class-imbalance ECG data. Augmenting ECG data by a GAN model eliminates the impact of data scarcity. After data augmentation, CAB classifies the ECG data by using a Bidirectional Long Short Term Memory Recurrent Neural Network (Bi-LSTM). Experiment results show a better performance of CAB compared with state-of-the-art methods. The overall classification accuracy of CAB is 99.71%. The F1-scores of classifying Normal beats (N), Supraventricular ectopic beats (S), Ventricular ectopic beats (V), Fusion beats (F) and Unclassifiable beats (Q) heartbeats are 99.86%, 97.66%, 99.05%, 98.57% and 99.88%, respectively. Unclassifiable beats (Q) heartbeats are 99.86%, 97.66%, 99.05%, 98.57% and 99.88%, respectively.
No takes yet. Share an insight, caveat, or question.
Yilin Wang (2021) studied Heart arrhythmia (n=47). CAB (GAN-based deep learning framework with Bi-LSTM) vs. No-GAN and other state-of-the-art classification methods was evaluated on Overall classification accuracy. The CAB framework, utilizing a Generative Adversarial Network and Bi-LSTM, achieved an overall classification accuracy of 99.71% for detecting heart arrhythmias from imbalanced ECG sensor data.
Synapse has enriched 10 related papers. Consider them for comparative context: