🤖 AI Summary
Automatic ECG diagnosis faces challenges of low model reliability, poor interpretability, and heavy dependence on labeled data. Method: This paper proposes a zero-shot retrieval-augmented generation (RAG) framework that—uniquely—integrates an expert-curated, structured cardiology knowledge graph into the RAG pipeline, enabling evidence-driven ECG interpretation in synergy with large language models (LLMs). It combines PTB-XL fine-tuning with medical-knowledge-guided semantic retrieval, eliminating reliance on conventional supervised training. Results: The framework achieves high accuracy on multi-class diagnosis tasks using PTB-XL, demonstrating strong generalization and clinical interpretability: each diagnostic output is accompanied by explicit knowledge provenance and step-by-step reasoning justification. This work establishes a novel paradigm for trustworthy, zero-shot, knowledge-enhanced AI-assisted ECG analysis.
📝 Abstract
Leveraging Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) for analyzing medical data, particularly Electrocardiogram (ECG), offers high accuracy and convenience. However, generating reliable, evidence-based results in specialized fields like healthcare remains a challenge, as RAG alone may not suffice. We propose a Zero-shot ECG diagnosis framework based on RAG for ECG analysis that incorporates expert-curated knowledge to enhance diagnostic accuracy and explainability. Evaluation on the PTB-XL dataset demonstrates the framework's effectiveness, highlighting the value of structured domain expertise in automated ECG interpretation. Our framework is designed to support comprehensive ECG analysis, addressing diverse diagnostic needs with potential applications beyond the tested dataset.