KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908289536622592 |
|---|---|
| author | Zuo, Kaiwen Jiang, Yirui Mo, Fan Lio, Pietro |
| author_facet | Zuo, Kaiwen Jiang, Yirui Mo, Fan Lio, Pietro |
| contents | Integrating Large Language Models (LLMs) in healthcare diagnosis demands systematic frameworks that can handle complex medical scenarios while maintaining specialized expertise. We present KG4Diagnosis, a novel hierarchical multi-agent framework that combines LLMs with automated knowledge graph construction, encompassing 362 common diseases across medical specialties. Our framework mirrors real-world medical systems through a two-tier architecture: a general practitioner (GP) agent for initial assessment and triage, coordinating with specialized agents for in-depth diagnosis in specific domains. The core innovation lies in our end-to-end knowledge graph generation methodology, incorporating: (1) semantic-driven entity and relation extraction optimized for medical terminology, (2) multi-dimensional decision relationship reconstruction from unstructured medical texts, and (3) human-guided reasoning for knowledge expansion. KG4Diagnosis serves as an extensible foundation for specialized medical diagnosis systems, with capabilities to incorporate new diseases and medical knowledge. The framework's modular design enables seamless integration of domain-specific enhancements, making it valuable for developing targeted medical diagnosis systems. We provide architectural guidelines and protocols to facilitate adoption across medical contexts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_16833 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosis Zuo, Kaiwen Jiang, Yirui Mo, Fan Lio, Pietro Artificial Intelligence Machine Learning Integrating Large Language Models (LLMs) in healthcare diagnosis demands systematic frameworks that can handle complex medical scenarios while maintaining specialized expertise. We present KG4Diagnosis, a novel hierarchical multi-agent framework that combines LLMs with automated knowledge graph construction, encompassing 362 common diseases across medical specialties. Our framework mirrors real-world medical systems through a two-tier architecture: a general practitioner (GP) agent for initial assessment and triage, coordinating with specialized agents for in-depth diagnosis in specific domains. The core innovation lies in our end-to-end knowledge graph generation methodology, incorporating: (1) semantic-driven entity and relation extraction optimized for medical terminology, (2) multi-dimensional decision relationship reconstruction from unstructured medical texts, and (3) human-guided reasoning for knowledge expansion. KG4Diagnosis serves as an extensible foundation for specialized medical diagnosis systems, with capabilities to incorporate new diseases and medical knowledge. The framework's modular design enables seamless integration of domain-specific enhancements, making it valuable for developing targeted medical diagnosis systems. We provide architectural guidelines and protocols to facilitate adoption across medical contexts. |
| title | KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosis |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2412.16833 |