MIA: Nathaniel Diamant, No such thing as unlabeled: Self-supervised learning on medical data (2021)

Models, Inference and Algorithms Broad Institute of MIT and Harvard October 13, 2021 Nathaniel Diamant Broad Institute No such thing as unlabeled: Self-supervised learning on medical data In medical datasets, the most important labels are often the rarest. For example, while responsible for more than 450,000 deaths a year in the United States alone, sudden cardiac death (SCD) will likely only show up in a few hundred health records in a hospital dataset of a hundred thousand patients. Furthermore, a binary label, like SCD, carries little information about the intricacies of the outcome. In contrast to the rarity and opacity of the labels, the relationships of data within a medical dataset are often plentiful and rich. Self-supervised learning (SSL) is an approach to training deep learning models that ideally matches the characteristics of medical datasets. We propose Patient Contrastive Learning, an SSL approach which exploits a fundamental relationship in medical datasets