Self-Supervised PPG Representation Learning Shows High Inter-Subject Variability

TL;DR

This paper explores self-supervised learning for PPG signals, showing it can outperform supervised methods with limited labels but suffers from high inter-subject variability, indicating room for improvement.

Contribution

It introduces a self-supervised framework for PPG representation learning and evaluates its effectiveness compared to supervised methods under scarce label conditions.

Findings

SSL outperforms supervised models with very limited labeled data

SSL representations are highly subject-specific, leading to high inter-subject variability

There is potential for improving SSL methods to reduce subject focus

Abstract

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.