Self-Supervised PPG Representation Learning Shows High Inter-Subject Variability
This addresses the challenge of applying machine learning to PPG data in label-scarce regimes, though it is incremental due to the identified variability issues.
The paper tackled the problem of limited labeled data for PPG signal analysis by proposing a self-supervised learning method with a signal reconstruction pretext task, finding that it outperforms supervised baselines in very low-label settings (e.g., 10 samples per class) but suffers from high inter-subject variability in learned representations.
With the progress of sensor technology in wearables, the collection and analysis of PPG signals are gaining more interest. Using Machine Learning, the cardiac rhythm corresponding to PPG signals can be used to predict different tasks such as activity recognition, sleep stage detection, or more general health status. However, supervised learning is often limited by the amount of available labeled data, which is typically expensive to obtain. To address this problem, we propose a Self-Supervised Learning (SSL) method with a pretext task of signal reconstruction to learn an informative generalized PPG representation. The performance of the proposed SSL framework is compared with two fully supervised baselines. The results show that in a very limited label data setting (10 samples per class or less), using SSL is beneficial, and a simple classifier trained on SSL-learned representations outperforms fully supervised deep neural networks. However, the results reveal that the SSL-learned representations are too focused on encoding the subjects. Unfortunately, there is high inter-subject variability in the SSL-learned representations, which makes working with this data more challenging when labeled data is scarce. The high inter-subject variability suggests that there is still room for improvements in learning representations. In general, the results suggest that SSL may pave the way for the broader use of machine learning models on PPG data in label-scarce regimes.