Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2507.02773 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908436497694720 |
|---|---|
| author | Xie, Yuzhang Cui, Hejie Zhang, Ziyang Lu, Jiaying Shu, Kai Nahab, Fadi Hu, Xiao Yang, Carl |
| author_facet | Xie, Yuzhang Cui, Hejie Zhang, Ziyang Lu, Jiaying Shu, Kai Nahab, Fadi Hu, Xiao Yang, Carl |
| contents | Medical diagnosis prediction plays a critical role in disease detection and personalized healthcare. While machine learning (ML) models have been widely adopted for this task, their reliance on supervised training limits their ability to generalize to unseen cases, particularly given the high cost of acquiring large, labeled datasets. Large language models (LLMs) have shown promise in leveraging language abilities and biomedical knowledge for diagnosis prediction. However, they often suffer from hallucinations, lack structured medical reasoning, and produce useless outputs. To address these challenges, we propose KERAP, a knowledge graph (KG)-enhanced reasoning approach that improves LLM-based diagnosis prediction through a multi-agent architecture. Our framework consists of a linkage agent for attribute mapping, a retrieval agent for structured knowledge extraction, and a prediction agent that iteratively refines diagnosis predictions. Experimental results demonstrate that KERAP enhances diagnostic reliability efficiently, offering a scalable and interpretable solution for zero-shot medical diagnosis prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_02773 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs Xie, Yuzhang Cui, Hejie Zhang, Ziyang Lu, Jiaying Shu, Kai Nahab, Fadi Hu, Xiao Yang, Carl Artificial Intelligence Machine Learning Multiagent Systems Medical diagnosis prediction plays a critical role in disease detection and personalized healthcare. While machine learning (ML) models have been widely adopted for this task, their reliance on supervised training limits their ability to generalize to unseen cases, particularly given the high cost of acquiring large, labeled datasets. Large language models (LLMs) have shown promise in leveraging language abilities and biomedical knowledge for diagnosis prediction. However, they often suffer from hallucinations, lack structured medical reasoning, and produce useless outputs. To address these challenges, we propose KERAP, a knowledge graph (KG)-enhanced reasoning approach that improves LLM-based diagnosis prediction through a multi-agent architecture. Our framework consists of a linkage agent for attribute mapping, a retrieval agent for structured knowledge extraction, and a prediction agent that iteratively refines diagnosis predictions. Experimental results demonstrate that KERAP enhances diagnostic reliability efficiently, offering a scalable and interpretable solution for zero-shot medical diagnosis prediction. |
| title | KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs |
| topic | Artificial Intelligence Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2507.02773 |