Beacon-SP uses graph and ontology to improve suicide risk assessment
BEACON-SP: Ontology-Grounded GraphRAG Framework for Clinical Suicide Risk Assessment
Artificial IntelligenceComputation and LanguageInformation Retrieval
Summary
Suicide risk assessment is complex because it requires combining many different types of information about a patient. The authors created BEACON-SP, a tool that uses graphs and a structured knowledge framework called an ontology to better organize and understand clinical and social information. This helps doctors answer questions about a patient's suicide risk by showing them clearer and more complete evidence. Compared to previous methods, BEACON-SP gives more relevant and well-supported answers for clinical decisions.
What this means in practice
- •For mental health clinicians: Provide clinicians with clearer, evidence-grounded answers to patient suicide risk questions by integrating diverse clinical and social data.
- •For electronic health record developers: Enhance clinical decision support tools by embedding ontology-guided graph retrieval to improve risk assessment interfaces for behavioral health.
Authors
Kemal Davaslioglu, Nathan Conger, Sastry Kompella, Yalin E. Sagduyu, Nathaniel D. Bastian
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.