Leveraging Graph-RAG for Enhanced Diagnostic and Treatment Strategies in Dentistry

This paper presents a method for extracting and interpreting information from diverse, unstructured dental literature using advanced AI techniques. By integrating information extraction, ontologies, and knowledge graphs, the approach enhances the efficiency and accuracy of dental data analysis. Named Entity Recognition (NER) and a Large Language Model (LLM) are employed to extract relevant entities and relationships, which are then structured into triples and integrated with a dental ontology to ensure contextual relevance. This enriched ontology supports Retrieval-Augmented Generation (RAG) applications, enabling advanced querying and analysis. The methodology improves the identification and categorization of dental conditions, treatments, and anatomical terms, providing a structured representation of dental knowledge. Knowledge graphs facilitate the representation and analysis of relationships between entities, fostering insightful interpretations and supporting hypothesis generation, thereby enhancing the accessibility and usability of dental knowledge. Experimental results demonstrate the effectiveness of this approach in managing complex dental information, showcasing the benefits of combining Knowledge Representation (KR) with Machine Learning (ML). This research contributes to dental studies by offering a robust framework for extracting and utilizing knowledge from diverse and extensive datasets.