PCPs: Patient Cardiac Prototypes

TL;DR

This paper introduces patient cardiac prototypes (PCPs), a method for creating patient-specific embeddings from cardiac signals to improve interpretability, personalization, and dataset efficiency in clinical deep learning.

Contribution

The paper proposes a novel supervised contrastive learning approach to generate patient-specific cardiac embeddings called PCPs, enabling personalized diagnosis and dataset distillation.

Findings

PCPs facilitate discovery of similar patients within and across datasets.

PCPs can be used with hypernetworks for patient-specific diagnosis.

PCPs serve as a compact dataset substitute for efficient data management.

Abstract

Many clinical deep learning algorithms are population-based and difficult to interpret. Such properties limit their clinical utility as population-based findings may not generalize to individual patients and physicians are reluctant to incorporate opaque models into their clinical workflow. To overcome these obstacles, we propose to learn patient-specific embeddings, entitled patient cardiac prototypes (PCPs), that efficiently summarize the cardiac state of the patient. To do so, we attract representations of multiple cardiac signals from the same patient to the corresponding PCP via supervised contrastive learning. We show that the utility of PCPs is multifold. First, they allow for the discovery of similar patients both within and across datasets. Second, such similarity can be leveraged in conjunction with a hypernetwork to generate patient-specific parameters, and in turn, patient-specific diagnoses. Third, we find that PCPs act as a compact substitute for the original dataset, allowing for dataset distillation.