Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement

arXiv:2403.06659v1 Announce Type: cross
Abstract: Electrocardiograms (ECGs) are non-invasive diagnostic tools crucial for detecting cardiac arrhythmic diseases in clinical practice. While ECG Self-supervised Learning (eSSL) methods show promise in representation learning from unannotated ECG data, they often overlook the clinical knowledge that can be found in reports. This oversight and the requirement for annotated samples for downstream tasks limit eSSL's versatility. In this work, we address these issues with the Multimodal ECG Representation Learning (MERL}) framework. Through multimodal learning on …

abstract arxiv classification clinical cs.ai cs.lg data diagnostic diseases eess.sp found knowledge multimodal multimodal learning oversight practice reports representation representation learning self-supervised learning show supervised learning test tools type zero-shot