arXiv：cs.CL· Kemal Davaslioglu, Nathan Conger, Sastry Kompella, Yalin E. Sagduyu, Nathaniel D. Bastian·· 3 小时前AI 评分35
BEACON-SP：面向临床自杀风险评估的本体驱动 GraphRAG 框架
BEACON-SP: Ontology-Grounded GraphRAG Framework for Clinical Suicide Risk Assessment
AI 导读
BEACON-SP 是一个本体驱动的 GraphRAG 框架，用于自杀预防等行为健康场景下面向临床医生的决策支持，通过患者知识图谱结合本体引导检索实现跨诊断、药物、风险与保护因素及时间关系的多跳推理。
正文
Abstract:We present BEACON-SP, an ontology-grounded Graph Retrieval-Augmented Generation (GraphRAG) framework for clinician-facing decision support in behavioral health settings such as suicide prevention, where effective assessment requires integrating heterogeneous clinical, behavioral, social, and temporal evidence. BEACON-SP combines patient knowledge graphs with ontology-guided retrieval to support multi-hop reasoning across diagnoses, medications, risk and protective factors, life events, and temporal relationships. The framework is enabled by a comprehensive suicide prevention ontology that integrates the Three-Step Theory, the Integrated Motivational-Volitional Model, and the Suicide Social Determinants of Health Ontology into a unified representation of patient risk factors. We construct ontology-grounded patient knowledge graphs and evaluate BEACON-SP for clinician-facing question answering. Compared with a vector-based retrieval-augmented generation (RAG) baseline on a 1,500-query benchmark spanning 15 clinical categories and 100 patients, BEACON-SP improves completeness, clinical relevance, and evidence grounding under a corrected comparative evaluation protocol, with a small gain on factual accuracy. In paired criterion-level comparisons, GraphRAG is preferred in 76.4% of cases. These results demonstrate the potential of ontology-guided GraphRAG to provide structured, contextualized patient evidence for clinical decision support.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2610.09026 [cs.AI] |
| (or arXiv:2610.09026v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09026 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kemal Davaslioglu [view email]
[v1]
Tue, 6 Oct 2026 19:23:51 UTC (343 KB)
来源：arXiv：cs.CL · arxiv.org