CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients
arXiv:2005.13249
Abstract
The healthcare industry generates troves of unlabelled physiological data. This data can be exploited via contrastive learning, a self-supervised pre-training method that encourages representations of instances to be similar to one another. We propose a family of contrastive learning methods, CLOCS, that encourages representations across space, time, \textit{and} patients to be similar to one another. We show that CLOCS consistently outperforms the state-of-the-art methods, BYOL and SimCLR, when performing a linear evaluation of, and fine-tuning on, downstream tasks. We also show that CLOCS achieves strong generalization performance with only 25\% of labelled training data. Furthermore, our training procedure naturally generates patient-specific representations that can be used to quantify patient-similarity.
Accepted to ICML 2021
References in corpus (8)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- A Simple Framework for Contrastive Learning of Visual Representations
- Bootstrap your own latent: A new approach to self-supervised Learning
- Learning Representations by Maximizing Mutual Information Across Views
- Self-supervised ECG Representation Learning for Emotion Recognition
- Subject-Aware Contrastive Learning for Biosignals
- Deep Bayesian Gaussian Processes for Uncertainty Estimation in Electronic Health Records
- Unsupervised Representation for EHR Signals and Codes as Patient Status Vector
Cited by in corpus (8)
- Self-supervised representation learning from 12-lead ECG data
- Patient Contrastive Learning: a Performant, Expressive, and Practical Approach to ECG Modeling
- MedAug: Contrastive learning leveraging patient metadata improves representations for chest X-ray interpretation
- Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data
- 3KG: Contrastive Learning of 12-Lead Electrocardiograms using Physiologically-Inspired Augmentations
- Contrastive Neural Processes for Self-Supervised Learning
- Leveraging Time Irreversibility with Order-Contrastive Pre-training
- PCPs: Patient Cardiac Prototypes