Key result
An adaptive sampling methodology using deep reinforcement learning achieved 97.2% accuracy for SVEB and 97.6% for VEB classification while being 7.3× more energy-efficient than the baseline.
A novel deep reinforcement learning-based adaptive sampling method for ECG classification achieves high accuracy for arrhythmias while significantly reducing energy consumption, making it suitable for wearable devices.
May support energy-efficient ECG wearables; hypothesis-generating pending clinical validation trials.
This article presents a resource-efficient adaptive sampling methodology for classifying electrocardiogram (ECG) signals into different heart rhythms. We present our methodology in two folds: ( i ) the design of a novel real-time adaptive neural network architecture capable of classifying ECG signals with different sampling rates and ( ii ) a runtime implementation of sampling rate control using deep reinforcement learning (DRL). By using essential morphological details contained in the heartbeat waveform, the DRL agent can control the sampling rate and effectively reduce energy consumption at runtime. To evaluate our adaptive classifier, we use the MIT-BIH database and the recommendation of the AAMI to train the classifiers. The classifier is designed to recognize three major types of arrhythmias, which are supraventricular ectopic beats (SVEB), ventricular ectopic beats (VEB), and normal beats (N). The performance of the arrhythmia classification reaches an accuracy of 97.2% for SVEB and 97.6% for VEB beats. Moreover, the designed system is 7.3× more energy-efficient compared to the baseline architecture, where the adaptive sampling rate is not utilized. The proposed methodology can provide reliable and accurate real-time ECG signal analysis with performances comparable to state-of-the-art methods. Given its time-efficient, low-complexity, and low-memory-usage characteristics, the proposed methodology is also suitable for practical ECG applications, in our case for arrhythmia classification, using resource-constrained devices, especially wearable healthcare devices and implanted medical devices.
No takes yet. Share an insight, caveat, or question.
Demirel et al. (2023) studied Arrhythmia. Adaptive sampling methodology using deep reinforcement learning vs. Baseline architecture without adaptive sampling rate was evaluated on Arrhythmia classification accuracy and energy efficiency (7.3x more energy-efficient). An adaptive sampling methodology using deep reinforcement learning achieved 97.2% accuracy for SVEB and 97.6% for VEB classification while being 7.3× more energy-efficient than the baseline.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: