CROCS: Clustering and Retrieval of Cardiac Signals Based on Patient Disease Class, Sex, and Age

TL;DR

CROCS is a supervised contrastive learning framework that clusters and retrieves cardiac signals based on patient attributes, improving accuracy and interpretability in large clinical databases.

Contribution

The paper introduces CROCS, a novel contrastive learning approach that uses clinical prototypes for effective clustering and retrieval of cardiac signals by patient-specific features.

Findings

CROCS outperforms the state-of-the-art DTC in clustering accuracy.

CROCS effectively retrieves relevant cardiac signals from large databases.

Clinical prototypes are semantically meaningful and interpretable.

Abstract

The process of manually searching for relevant instances in, and extracting information from, clinical databases underpin a multitude of clinical tasks. Such tasks include disease diagnosis, clinical trial recruitment, and continuing medical education. This manual search-and-extract process, however, has been hampered by the growth of large-scale clinical databases and the increased prevalence of unlabelled instances. To address this challenge, we propose a supervised contrastive learning framework, CROCS, where representations of cardiac signals associated with a set of patient-specific attributes (e.g., disease class, sex, age) are attracted to learnable embeddings entitled clinical prototypes. We exploit such prototypes for both the clustering and retrieval of unlabelled cardiac signals based on multiple patient attributes. We show that CROCS outperforms the state-of-the-art method, DTC, when clustering and also retrieves relevant cardiac signals from a large database. We also show that clinical prototypes adopt a semantically meaningful arrangement based on patient attributes and thus confer a high degree of interpretability.