BEACON-SP: Ontology-Grounded GraphRAG Framework for Clinical Suicide Risk Assessment

2026-10-06

AI Summary

This study addresses the challenges of integrating multi-source heterogeneous evidence and the lack of structured reasoning support in clinical suicide risk assessment. To this end, this work proposes an ontology-driven GraphRAG framework that pioneers the unification of three major suicide theory models into a single ontology. By leveraging patient-specific knowledge graphs to guide graph retrieval-augmented generation, the approach enables multi-hop reasoning and context-aware decision support across diagnoses, medications, and psychosocial factors. Benchmark evaluations demonstrate that the proposed method significantly outperforms vector-based RAG baselines, substantially improving both the completeness and relevance of assessments. Notably, it was preferred in 76.4% of cases, thereby validating the effectiveness of structured clinical reasoning for suicide risk evaluation.

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.

Problem

• Suicide Risk Assessment
• Clinical Decision Support
• GraphRAG
• Patient Knowledge Graphs
• Ontology

Innovation

• GraphRAG
• Ontology-Grounded
• Knowledge Graph
• Suicide Risk Assessment
• Multi-hop Reasoning