Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models?

TL;DR

This paper explores transferring knowledge from large language models to electrocardiography for cardiovascular disease detection and report generation, demonstrating promising results in zero-shot classification and report quality.

Contribution

It introduces a novel method using LLM embeddings and an Optimal Transport loss to transfer knowledge to ECG analysis, enabling diagnosis report generation and disease detection.

Findings

High-quality ECG diagnosis reports generated

Competitive zero-shot disease detection performance

Feasibility of LLM knowledge transfer to cardiology

Abstract

Recent advancements in Large Language Models (LLMs) have drawn increasing attention since the learned embeddings pretrained on large-scale datasets have shown powerful ability in various downstream applications. However, whether the learned knowledge by LLMs can be transferred to clinical cardiology remains unknown. In this work, we aim to bridge this gap by transferring the knowledge of LLMs to clinical Electrocardiography (ECG). We propose an approach for cardiovascular disease diagnosis and automatic ECG diagnosis report generation. We also introduce an additional loss function by Optimal Transport (OT) to align the distribution between ECG and language embedding. The learned embeddings are evaluated on two downstream tasks: (1) automatic ECG diagnosis report generation, and (2) zero-shot cardiovascular disease detection. Our approach is able to generate high-quality cardiac diagnosis reports and also achieves competitive zero-shot classification performance even compared with supervised baselines, which proves the feasibility of transferring knowledge from LLMs to the cardiac domain.