ETP: Learning Transferable ECG Representations via ECG-Text Pre-training

TL;DR

This paper introduces ECG-Text Pre-training (ETP), a novel framework that learns cross-modal ECG and text representations, enabling zero-shot classification and improving generalization in ECG analysis.

Contribution

The paper presents the first framework to leverage ECG-text pre-training for zero-shot classification, enhancing ECG representation learning beyond existing self-supervised methods.

Findings

ETP achieves superior performance on PTB-XL and CPSC2018 datasets.

ETP enables effective zero-shot ECG classification.

ETP improves robustness and generalization in ECG analysis.

Abstract

In the domain of cardiovascular healthcare, the Electrocardiogram (ECG) serves as a critical, non-invasive diagnostic tool. Although recent strides in self-supervised learning (SSL) have been promising for ECG representation learning, these techniques often require annotated samples and struggle with classes not present in the fine-tuning stages. To address these limitations, we introduce ECG-Text Pre-training (ETP), an innovative framework designed to learn cross-modal representations that link ECG signals with textual reports. For the first time, this framework leverages the zero-shot classification task in the ECG domain. ETP employs an ECG encoder along with a pre-trained language model to align ECG signals with their corresponding textual reports. The proposed framework excels in both linear evaluation and zero-shot classification tasks, as demonstrated on the PTB-XL and CPSC2018 datasets, showcasing its ability for robust and generalizable cross-modal ECG feature learning.