Key result
FedECG framework outperforms state-of-the-art distributed methods, predicting ECG abnormalities with ~95% accuracy.
Why the study?
Machine learning ECG monitoring on smart devices faces challenges with non-i.i.d. data variations, costly professional labeling of mostly unlabeled data, and privacy risks from centralizing user data.
Does the FedECG framework improve the accuracy of ECG abnormalities prediction compared to state-of-the-art distributed methods while preserving privacy?
Does the FedECG framework improve the accuracy of ECG abnormalities prediction compared to state-of-the-art distributed methods while preserving privacy?
The FedECG framework enables accurate prediction of ECG abnormalities using semi-supervised federated learning, preserving data privacy while outperforming existing distributed methods.
The soaring popularity of smart devices equipped with electrocardiograms (ECG) is driving a nationwide craze for predicting heart abnormalities. Smart ECG monitoring system has achieved significant success by training machine learning models on massive amounts of user data. However, three issues arise accordingly: 1) ECG data collected from various devices may display personal characteristic variations, leading to non-independent and identically distributed (non-i.i.d.) data. These differences can impact the accuracy and reliability of data analysis and interpretation; 2) Most ECG data on smart devices is unlabeled, and data labeling is resource-consuming as it requires heavy-loaded labeling from professionals; 3) While centralizing data for machine learning can address above issues like non-i.i.d. data and labeling difficulties, it may compromise personal privacy. To tackle these three issues, we introduce a novel federated semi-supervised learning (FSSL) framework named FedECG for ECG abnormalities prediction. Specifically, we adopt a pre-processing module to better utilize the ECG data. Next, we devise a novel model based on ResNet-9 in FSSL to accurately predict abnormal signals from ECG recordings. In addition, we incorporate pseudo-labeling and data augmentation techniques to enhance our implemented semi-supervised learning. We also develop a model aggregation algorithm to improve the model convergence performance in federated learning. Finally, we conduct simulations on a real-world dataset. Experiments demonstrate that FedECG obtains 94.8% accuracy with only 50% of the data labeled. FedECG achieved slightly lower accuracy than traditional centralized methods in ECG monitoring, with a 2% reduction. In contrast, FedECG outperforms the state-of-the-art distributed methods by about 3%. Moreover, FedECG can also support unlabeled data and preserve data privacy as well.
No takes yet. Share an insight, caveat, or question.
Ying et al. (2023) studied ECG abnormalities. FedECG (federated semi-supervised learning framework) vs. Traditional centralized methods and state-of-the-art distributed methods was evaluated on Prediction accuracy. The FedECG framework achieved 94.8% accuracy for predicting ECG abnormalities using 50% labeled data, outperforming state-of-the-art distributed methods by 3%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: