DGADS: A graph-based agentic decision support system for precision dental question answering

Large language models (LLMs) have significant potential for dental applications, but their inherent tendency to hallucinate remains a major challenge. This study aims to develop and evaluate a graph-based agentic decision support system for dental question answering.

We developed a Dental Graph-based Agentic Decision Support System (DGADS) to support precision dental question answering. DGADS comprised three core modules: a knowledge graph builder, a graph-based RAG module, and an agentic RAG module. DGADS transformed a large volume of dental textual knowledge into a knowledge graph, termed DentalKG, and established a graph-based retrieval augmented generation system. DGADS was evaluated on three benchmarks against state-of-the-art LLMs and chunk-based RAG approaches, including internal multiple-choice questions, external multiple-choice questions, and open-ended questions.

DentalKG comprised 130,735 entities and 236,935 triples constructed and evaluated between 15 October 2025 and 1 May 2026. DGADS leveraged knowledge from DentalKG to outperform baseline models, achieving absolute accuracy improvements of 0.04 (95% CI: 0.03, 0.06) on 500 internal questions and 0.05 (95% CI: 0.04, 0.07) on 260 external questions. In addition, DGADS improved performance on open-ended questions, with mean scores increasing up to 0.78 points on a 5-point scale. DGADS was able to automatically assess the sufficiency of information retrieved from DentalKG and retrieve relevant data from external information sources.

DGADS has the potential to become a useful research-oriented tool for supporting dental question answering, with the promise of improving the precision and efficiency of broader clinical applications.

DGADS supports precise dental question answering by grounding LLMs' outputs in a dental knowledge graph and retrieving external evidence when needed. By reducing hallucinations and providing traceable rationale in benchmark-based evaluations, it may help clinicians access reliable information more efficiently in the future.