Supervised machine learning applications in health care are often limited due to a scarcity of labeled training data. To mitigate this effect of small sample size, we introduce a pre-training approach, Patient Contrastive Learning of Representations (PCLR), which creates latent representations of ECGs from a large number of unlabeled examples. The resulting representations are expressive, performant, and practical across a wide spectrum of clinical tasks. We develop PCLR using a large health care system with over 3.2 million 12-lead ECGs, and demonstrate substantial improvements across multiple new tasks when there are fewer than 5,000 labels. We release our model to extract ECG representations at https://github.com/broadinstitute/ml4h/tree/master/model_zoo/PCLR.
@article{arxiv.2104.04569,
title = {Patient Contrastive Learning: a Performant, Expressive, and Practical Approach to ECG Modeling},
author = {Nathaniel Diamant and Erik Reinertsen and Steven Song and Aaron Aguirre and Collin Stultz and Puneet Batra},
journal= {arXiv preprint arXiv:2104.04569},
year = {2022}
}
Comments
17 pages, 7 figures. Submitted to Machine Learning for Healthcare 2021