Journal of dental education · 2025
Integrating Clinical and Systemic Knowledge in Periodontal and Peri-Implant Disease Education Through a Knowledge Graph.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Sun Yi-Jia, Zhao Yi-Feng, Zhang Lei, Luo Li-Jun, Zhou Yue, Zhang Yan, Han Xue, Zhou Min
Аннотация
AIM: This study aims to construct a knowledge graph in the field of periodontology and develop a knowledge-graph-based intelligent question-answering (QA) system, with the goal of enhancing the structured management and intelligent application of periodontal disease knowledge.
MATERIALS AND METHODS: Consensus documents and evidence-based guidelines from the EFP and AAP served as primary data sources. Entities and relationships related to periodontal diseases were extracted using a large language model-assisted semantic approach to generate structured quintuple data. A knowledge graph was constructed in Neo4j, upon which a graph-enhanced intelligent PerioMind system was developed.
RESULTS: A total of 26 authoritative documents were included, from which 1894 knowledge quintuples were extracted, resulting in a knowledge graph comprising 1872 nodes and 1894 edges. The PerioMind system, developed on top of the graph, demonstrated efficient parsing of natural language queries and the generation of professional responses. The system achieved the following evaluation scores (out of 5): accuracy 4.8, interpretability 4.4, domain relevance 4.8, and completeness 4.5.
CONCLUSION: This study developed a structured knowledge graph and the PerioMind system for periodontology, supporting intelligent diagnosis, education, and research. Future work will expand knowledge coverage and enhance semantic reasoning to advance an intelligent knowledge service platform.
MATERIALS AND METHODS: Consensus documents and evidence-based guidelines from the EFP and AAP served as primary data sources. Entities and relationships related to periodontal diseases were extracted using a large language model-assisted semantic approach to generate structured quintuple data. A knowledge graph was constructed in Neo4j, upon which a graph-enhanced intelligent PerioMind system was developed.
RESULTS: A total of 26 authoritative documents were included, from which 1894 knowledge quintuples were extracted, resulting in a knowledge graph comprising 1872 nodes and 1894 edges. The PerioMind system, developed on top of the graph, demonstrated efficient parsing of natural language queries and the generation of professional responses. The system achieved the following evaluation scores (out of 5): accuracy 4.8, interpretability 4.4, domain relevance 4.8, and completeness 4.5.
CONCLUSION: This study developed a structured knowledge graph and the PerioMind system for periodontology, supporting intelligent diagnosis, education, and research. Future work will expand knowledge coverage and enhance semantic reasoning to advance an intelligent knowledge service platform.