A Multi-granularity Concept Sparse Activation and Hierarchical Knowledge Graph Fusion Framework for Rare Disease Diagnosis
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914014207934464 |
|---|---|
| author | Zhang, Mingda Zhao, Na Qin, Jianglong Ye, Guoyu Tang, Ruixiang |
| author_facet | Zhang, Mingda Zhao, Na Qin, Jianglong Ye, Guoyu Tang, Ruixiang |
| contents | Despite advances from medical large language models in healthcare, rare-disease diagnosis remains hampered by insufficient knowledge-representation depth, limited concept understanding, and constrained clinical reasoning. We propose a framework that couples multi-granularity sparse activation of medical concepts with a hierarchical knowledge graph. Four complementary matching algorithms, diversity control, and a five-level fallback strategy enable precise concept activation, while a three-layer knowledge graph (taxonomy, clinical features, instances) provides structured, up-to-date context. Experiments on the BioASQ rare-disease QA set show BLEU gains of 0.09, ROUGE gains of 0.05, and accuracy gains of 0.12, with peak accuracy of 0.89 approaching the 0.90 clinical threshold. Expert evaluation confirms improvements in information quality, reasoning, and professional expression, suggesting our approach shortens the "diagnostic odyssey" for rare-disease patients. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_08529 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Multi-granularity Concept Sparse Activation and Hierarchical Knowledge Graph Fusion Framework for Rare Disease Diagnosis Zhang, Mingda Zhao, Na Qin, Jianglong Ye, Guoyu Tang, Ruixiang Artificial Intelligence Computation and Language 68T50, 92C50, 68T05 J.3; I.2.7; H.3.3; I.2.1 Despite advances from medical large language models in healthcare, rare-disease diagnosis remains hampered by insufficient knowledge-representation depth, limited concept understanding, and constrained clinical reasoning. We propose a framework that couples multi-granularity sparse activation of medical concepts with a hierarchical knowledge graph. Four complementary matching algorithms, diversity control, and a five-level fallback strategy enable precise concept activation, while a three-layer knowledge graph (taxonomy, clinical features, instances) provides structured, up-to-date context. Experiments on the BioASQ rare-disease QA set show BLEU gains of 0.09, ROUGE gains of 0.05, and accuracy gains of 0.12, with peak accuracy of 0.89 approaching the 0.90 clinical threshold. Expert evaluation confirms improvements in information quality, reasoning, and professional expression, suggesting our approach shortens the "diagnostic odyssey" for rare-disease patients. |
| title | A Multi-granularity Concept Sparse Activation and Hierarchical Knowledge Graph Fusion Framework for Rare Disease Diagnosis |
| topic | Artificial Intelligence Computation and Language 68T50, 92C50, 68T05 J.3; I.2.7; H.3.3; I.2.1 |
| url | https://arxiv.org/abs/2507.08529 |