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
Kemal Davaslioglu · Nathan Conger · Sastry Kompella · Yalin E. Sagduyu · Nathaniel D. Bastian
中文摘要
BEACON-SP 是一个由本体引导的图检索增强生成（GraphRAG）框架，面向行为健康（如自杀预防）场景中面向临床医生的决策支持，有效评估需整合异构的临床、行为、社会与时间证据。BEACON-SP 将患者知识图谱与本体引导的检索相组合，可在诊断、风险与保护因素、生命事件及时间关系之间开展多跳推理。该框架以一个综合性自杀预防本体为基础，将三步理论（Three-Step Theory）、整合性动机-意志模型（Integrated Motivational-Volitional Model）以及自杀健康社会决定因素本体（Suicide Social Determinants of Health Ontology）统一为患者风险因素的整体表示。研究构建了本体驱动的患者知识图谱，并面向临床问答任务对 BEACON-SP 进行评估。在覆盖 15 个临床类别、100 名患者、包含 1500 条查询的基准测试中，使用修正后的对比评估协议，相较基于向量检索的 RAG 基线，BEACON-SP 在完整性、临床相关性及证据支撑度方面均有改善，事实准确性方面有小幅提升。在成对的细粒度准则比较中，GraphRAG 在 76.4% 的案例中被优选。结果表明，本体引导的 GraphRAG 有潜力为临床决策支持提供结构化、富含上下文的患者证据。
关键要点
- 01问题：自杀风险评估需要整合临床、行为、社会、时间等多源异构证据，向量 RAG 难以支撑多跳推理。
- 02方法：将三步理论、IMV 模型与自杀健康社会决定因素本体融合，构建统一自杀预防本体并驱动 GraphRAG 多跳检索。
- 03结果：在 1500 条查询、15 个临床类别、100 名患者的基准上，BEACON-SP 在完整性、临床相关性与证据支撑上优于向量 RAG 基线。
- 04偏好：在成对准则级比较中 GraphRAG 在 76.4% 的案例中被临床评估者偏好，事实准确性仅有小幅提升。
- 05局限：评估采用修正后的对比协议与问答场景，是否泛化到真实临床工作流与纵向预测仍待研究。
解读
尚无解读。
原始英文摘要
arXiv:2610.09026v1 Announce Type: cross 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.