RareAgents: Advancing Rare Disease Care through LLM-Empowered Multi-disciplinary Team

2024-12-17

AI Summary

Rare disease diagnosis faces significant clinical challenges—including diagnostic uncertainty, scarcity of domain experts, and multisystem involvement—necessitating integrated, multidisciplinary decision support. Method: We propose the first large language model (LLM)-driven multidisciplinary team (MDT) framework tailored to rare diseases. It features a novel multi-agent collaborative architecture incorporating dynamic MDT coordination, traceable structured medical memory retrieval, and API-enabled integration of laboratory tests, clinical guidelines, and drug databases. The framework is built upon Llama-3.1-8B/70B and accompanied by MIMIC-IV-Ext-Rare—the first open-source, rare-disease–enhanced clinical dataset derived from MIMIC-IV. Contribution/Results: Extensive evaluation demonstrates statistically significant improvements over GPT-4o, state-of-the-art domain-specific models, and existing medical agents: +12.6%–23.4% absolute accuracy gains in differential diagnosis and pharmacotherapy recommendation tasks—establishing a new paradigm for LLM-augmented, complex rare disease clinical reasoning.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Multiagent Systems: Teamwork

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Rare diseases, despite their low individual incidence, collectively impact around 300 million people worldwide due to the vast number of diseases. The involvement of multiple organs and systems, and the shortage of specialized doctors with relevant experience make diagnosing and treating rare diseases more challenging than common diseases. Recently, agents powered by large language models (LLMs) have demonstrated notable applications across various domains. In the medical field, some agent methods have outperformed direct prompts in question-answering tasks from medical examinations. However, current agent frameworks are not well-adapted to real-world clinical scenarios, especially those involving the complex demands of rare diseases. To bridge this gap, we introduce RareAgents, the first LLM-driven multi-disciplinary team framework designed specifically for the complex clinical context of rare diseases. RareAgents integrates advanced Multidisciplinary Team (MDT) coordination, memory mechanisms, and medical tools utilization, leveraging Llama-3.1-8B/70B as the base model. Experimental results show that RareAgents outperforms state-of-the-art domain-specific models, GPT-4o, and current agent frameworks in differential diagnosis and medication recommendation for rare diseases. Furthermore, we contribute a novel rare disease dataset, MIMIC-IV-Ext-Rare, to support further advancements in this field.

Problem

• Improves rare disease diagnosis and treatment.
• Integrates multidisciplinary team coordination and tools.
• Outperforms existing models in clinical scenarios.

Innovation

• LLM-driven multidisciplinary team framework
• Integrated memory and medical tools
• Novel rare disease dataset contribution