Key result
Personalized zero-shot ensemble classifier outperforms prior methods for ECG arrhythmia detection with ~93% F1-score.
Why the study?
Personalized ECG monitoring algorithms in wearable devices lack abnormal heartbeat training data for healthy individuals without a cardiac disorder history.
Absolute Event Rate: 0.928% vs 0.886%
A novel zero-shot learning approach for personalized ECG monitoring achieves high accuracy in arrhythmia detection without requiring prior abnormal heartbeat data from the user.
May enable personalized zero-shot ECG monitoring; hypothesis-generating pending prospective clinical validation.
This paper proposes a low-cost and highly accurate ECG-monitoring system intended for personalized early arrhythmia detection for wearable mobile sensors. Earlier supervised approaches for personalized ECG monitoring require both abnormal and normal heartbeats for the training of the dedicated classifier. However, in a real-world scenario where the personalized algorithm is embedded in a wearable device, such training data is not available for healthy people with no cardiac disorder history. In this study, (i) we propose a null space analysis on the healthy signal space obtained via sparse dictionary learning, and investigate how a simple null space projection or alternatively regularized least squares-based classification methods can reduce the computational complexity, without sacrificing the detection accuracy, when compared to sparse representation-based classification. (ii) Then we introduce a sparse representation-based domain adaptation technique in order to project other existing users' abnormal and normal signals onto the new user's signal space, enabling us to train the dedicated classifier without having any abnormal heartbeat of the new user. Therefore, zero-shot learning can be achieved without the need for synthetic abnormal heartbeat generation. An extensive set of experiments performed on the benchmark MIT-BIH ECG dataset shows that when this domain adaptation-based training data generator is used with a simple 1-D CNN classifier, the method outperforms the prior work by a significant margin. (iii) Then, by combining (i) and (ii), we propose an ensemble classifier that further improves the performance. This approach for zero-shot arrhythmia detection achieves an average accuracy level of 98.2% and an F1-Score of 92.8%. Finally, a personalized energy-efficient ECG monitoring scheme is proposed using the above-mentioned innovations.
No takes yet. Share an insight, caveat, or question.
Yamaç et al. (2022) studied Cardiac arrhythmia (n=34). Personalized zero-shot ensemble classifier (Sparse Representation Based Domain Adaptation) vs. Prior zero-shot methods (e.g., Abnormal Beat Synthesis) was evaluated on F1-Score for abnormal beat detection. The proposed personalized zero-shot ensemble classifier for ECG arrhythmia detection achieved an average accuracy of 98.2% and an F1-Score of 92.8%, outperforming prior zero-shot methods.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: