MTS-LOF: Medical Time-Series Representation Learning via Occlusion-Invariant Features

TL;DR

MTS-LOF is a self-supervised learning framework that combines contrastive learning and Masked Autoencoders with multi-masking strategies to learn occlusion-invariant, context-rich representations of medical time series data, improving healthcare applications.

Contribution

This paper introduces MTS-LOF, a novel SSL framework that integrates contrastive learning and MAE with multi-masking for enhanced medical time series representation learning.

Findings

MTS-LOF outperforms existing methods on diverse datasets.

The multi-masking strategy improves occlusion-invariant feature learning.

Joint-embedding SSL and MAE effectively capture temporal and structural dependencies.

Abstract

Medical time series data are indispensable in healthcare, providing critical insights for disease diagnosis, treatment planning, and patient management. The exponential growth in data complexity, driven by advanced sensor technologies, has presented challenges related to data labeling. Self-supervised learning (SSL) has emerged as a transformative approach to address these challenges, eliminating the need for extensive human annotation. In this study, we introduce a novel framework for Medical Time Series Representation Learning, known as MTS-LOF. MTS-LOF leverages the strengths of contrastive learning and Masked Autoencoder (MAE) methods, offering a unique approach to representation learning for medical time series data. By combining these techniques, MTS-LOF enhances the potential of healthcare applications by providing more sophisticated, context-rich representations. Additionally, MTS-LOF employs a multi-masking strategy to facilitate occlusion-invariant feature learning. This approach allows the model to create multiple views of the data by masking portions of it. By minimizing the discrepancy between the representations of these masked patches and the fully visible patches, MTS-LOF learns to capture rich contextual information within medical time series datasets. The results of experiments conducted on diverse medical time series datasets demonstrate the superiority of MTS-LOF over other methods. These findings hold promise for significantly enhancing healthcare applications by improving representation learning. Furthermore, our work delves into the integration of joint-embedding SSL and MAE techniques, shedding light on the intricate interplay between temporal and structural dependencies in healthcare data. This understanding is crucial, as it allows us to grasp the complexities of healthcare data analysis.