CuPID: Leveraging Masked Single-Lead ECG Modelling for Enhancing the Representations

2025-02-28

AI Summary

Irregular heartbeat rhythms in single-lead electrocardiogram (ECG) signals degrade the performance of masked data modeling (MDM). Method: This paper proposes CuPID, the first approach to inject STFT spectrograms as time-frequency contextual cues into the decoder to guide the encoder toward learning physiologically meaningful and fine-grained representations. CuPID integrates self-supervised contrastive optimization with a lightweight context injection mechanism, enhancing modeling robustness without additional annotations. Contribution/Results: Experiments demonstrate that CuPID significantly outperforms state-of-the-art methods on downstream tasks—including arrhythmia classification and anomaly detection—particularly under low-labeling-cost scenarios, where encoder representation quality improves markedly. These results validate the effectiveness and generalization advantage of time-frequency prompting for unsupervised representation learning from single-lead ECGs.

Technology Category

• Machine Learning: Unsupervised & Self-Supervised Learning
• Computer Vision: Multi-modal Vision
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Wearable sensing devices, such as Electrocardiogram (ECG) heart-rate monitors, will play a crucial role in the future of digital health. This continuous monitoring leads to massive unlabeled data, incentivizing the development of unsupervised learning frameworks. While Masked Data Modelling (MDM) techniques have enjoyed wide use, their direct application to single-lead ECG data is suboptimal due to the decoder's difficulty handling irregular heartbeat intervals when no contextual information is provided. In this paper, we present Cueing the Predictor Increments the Detailing (CuPID), a novel MDM method tailored to single-lead ECGs. CuPID enhances existing MDM techniques by cueing spectrogram-derived context to the decoder, thus incentivizing the encoder to produce more detailed representations. This has a significant impact on the encoder's performance across a wide range of different configurations, leading CuPID to outperform state-of-the-art methods in a variety of downstream tasks.

Problem

• Enhance unsupervised learning for single-lead ECG data.
• Address irregular heartbeat intervals in ECG decoding.
• Improve encoder performance using spectrogram-derived context.

Innovation

• CuPID enhances MDM with spectrogram-derived context.
• Tailored for single-lead ECG data processing.
• Improves encoder performance in downstream tasks.