CardioRAG: A Retrieval-Augmented Generation Framework for Multimodal Chagas Disease Detection

2025-10-01

AI Summary

In resource-limited settings where serological testing for Chagas disease is scarce, early screening suffers from low diagnostic accuracy, heavy reliance on large labeled datasets, and poor clinical interpretability. Method: We propose a retrieval-augmented generation (RAG) framework integrating clinical prior knowledge with large language models (LLMs), explicitly embedding evidence-based ECG features—such as right bundle branch block, left anterior fascicular block, and heart rate variability—into the AI reasoning pipeline. A variational autoencoder enables semantic case retrieval, supporting a multimodal, interpretable ECG diagnosis system. Contribution/Results: Evaluated in real-world clinical settings, our method achieves 89.80% recall and an F1 score of 0.68, significantly improving high-risk patient identification efficiency and providing accurate, prioritized support for serological testing.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Chagas disease affects nearly 6 million people worldwide, with Chagas cardiomyopathy representing its most severe complication. In regions where serological testing capacity is limited, AI-enhanced electrocardiogram (ECG) screening provides a critical diagnostic alternative. However, existing machine learning approaches face challenges such as limited accuracy, reliance on large labeled datasets, and more importantly, weak integration with evidence-based clinical diagnostic indicators. We propose a retrieval-augmented generation framework, CardioRAG, integrating large language models with interpretable ECG-based clinical features, including right bundle branch block, left anterior fascicular block, and heart rate variability metrics. The framework uses variational autoencoder-learned representations for semantic case retrieval, providing contextual cases to guide clinical reasoning. Evaluation demonstrated high recall performance of 89.80%, with a maximum F1 score of 0.68 for effective identification of positive cases requiring prioritized serological testing. CardioRAG provides an interpretable, clinical evidence-based approach particularly valuable for resource-limited settings, demonstrating a pathway for embedding clinical indicators into trustworthy medical AI systems.

Problem

• Detects Chagas cardiomyopathy using AI-enhanced ECG screening
• Integrates clinical ECG features with large language models
• Provides interpretable diagnosis for resource-limited healthcare settings

Innovation

• Retrieval-augmented generation framework integrating LLMs
• Uses variational autoencoder for semantic case retrieval
• Combines ECG clinical features with evidence-based indicators