Large language models for intelligent RDF knowledge graph construction: results from medical ontology mapping

The exponential growth of digital data, particularly in specialized domains like healthcare, necessitates advanced knowledge representation and integration techniques. RDF knowledge graphs offer a powerful solution, yet their creation and maintenance, especially for complex medical ontologies like S...

Full description

Saved in:
Bibliographic Details
Main Authors: Apostolos Mavridis, Stergios Tegos, Christos Anastasiou, Maria Papoutsoglou, Georgios Meditskos
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-04-01
Series:Frontiers in Artificial Intelligence
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/frai.2025.1546179/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850179505905205248
author Apostolos Mavridis
Stergios Tegos
Christos Anastasiou
Maria Papoutsoglou
Georgios Meditskos
author_facet Apostolos Mavridis
Stergios Tegos
Christos Anastasiou
Maria Papoutsoglou
Georgios Meditskos
author_sort Apostolos Mavridis
collection DOAJ
description The exponential growth of digital data, particularly in specialized domains like healthcare, necessitates advanced knowledge representation and integration techniques. RDF knowledge graphs offer a powerful solution, yet their creation and maintenance, especially for complex medical ontologies like Systematized Nomenclature of Medicine - Clinical Terms (SNOMED CT), remain challenging. Traditional methods often struggle with the scale, heterogeneity, and semantic complexity of medical data. This paper introduces a methodology leveraging the contextual understanding and reasoning capabilities of Large Language Models (LLMs) to automate and enhance medical ontology mapping for Resource Description Framework (RDF) knowledge graph construction. We conduct a comprehensive comparative analysis of six systems–GPT-4o, Claude 3.5 Sonnet v2, Gemini 1.5 Pro, Llama 3.3 70B, DeepSeek R1, and BERTMap—using a novel evaluation framework that combines quantitative metrics (precision, recall, and F1-score) with qualitative assessments of semantic accuracy. Our approach integrates a data preprocessing pipeline with an LLM-powered semantic mapping engine, utilizing BioBERT embeddings and ChromaDB vector database for efficient concept retrieval. Experimental results on a dataset of 108 medical terms demonstrate the superior performance of modern LLMs, particularly GPT-4o, achieving a precision of 93.75% and an F1-score of 96.26%. These findings highlight the potential of LLMs in bridging the gap between structured medical data and semantic knowledge representation, toward more accurate and interoperable medical knowledge graphs.
format Article
id doaj-art-e3d5125752b74cd8a3fcfba6fe620e1d
institution OA Journals
issn 2624-8212
language English
publishDate 2025-04-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Artificial Intelligence
spelling doaj-art-e3d5125752b74cd8a3fcfba6fe620e1d2025-08-20T02:18:28ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122025-04-01810.3389/frai.2025.15461791546179Large language models for intelligent RDF knowledge graph construction: results from medical ontology mappingApostolos MavridisStergios TegosChristos AnastasiouMaria PapoutsoglouGeorgios MeditskosThe exponential growth of digital data, particularly in specialized domains like healthcare, necessitates advanced knowledge representation and integration techniques. RDF knowledge graphs offer a powerful solution, yet their creation and maintenance, especially for complex medical ontologies like Systematized Nomenclature of Medicine - Clinical Terms (SNOMED CT), remain challenging. Traditional methods often struggle with the scale, heterogeneity, and semantic complexity of medical data. This paper introduces a methodology leveraging the contextual understanding and reasoning capabilities of Large Language Models (LLMs) to automate and enhance medical ontology mapping for Resource Description Framework (RDF) knowledge graph construction. We conduct a comprehensive comparative analysis of six systems–GPT-4o, Claude 3.5 Sonnet v2, Gemini 1.5 Pro, Llama 3.3 70B, DeepSeek R1, and BERTMap—using a novel evaluation framework that combines quantitative metrics (precision, recall, and F1-score) with qualitative assessments of semantic accuracy. Our approach integrates a data preprocessing pipeline with an LLM-powered semantic mapping engine, utilizing BioBERT embeddings and ChromaDB vector database for efficient concept retrieval. Experimental results on a dataset of 108 medical terms demonstrate the superior performance of modern LLMs, particularly GPT-4o, achieving a precision of 93.75% and an F1-score of 96.26%. These findings highlight the potential of LLMs in bridging the gap between structured medical data and semantic knowledge representation, toward more accurate and interoperable medical knowledge graphs.https://www.frontiersin.org/articles/10.3389/frai.2025.1546179/fullLLMontologyknowledge graphhealth dataRDFSNOMED CT
spellingShingle Apostolos Mavridis
Stergios Tegos
Christos Anastasiou
Maria Papoutsoglou
Georgios Meditskos
Large language models for intelligent RDF knowledge graph construction: results from medical ontology mapping
Frontiers in Artificial Intelligence
LLM
ontology
knowledge graph
health data
RDF
SNOMED CT
title Large language models for intelligent RDF knowledge graph construction: results from medical ontology mapping
title_full Large language models for intelligent RDF knowledge graph construction: results from medical ontology mapping
title_fullStr Large language models for intelligent RDF knowledge graph construction: results from medical ontology mapping
title_full_unstemmed Large language models for intelligent RDF knowledge graph construction: results from medical ontology mapping
title_short Large language models for intelligent RDF knowledge graph construction: results from medical ontology mapping
title_sort large language models for intelligent rdf knowledge graph construction results from medical ontology mapping
topic LLM
ontology
knowledge graph
health data
RDF
SNOMED CT
url https://www.frontiersin.org/articles/10.3389/frai.2025.1546179/full
work_keys_str_mv AT apostolosmavridis largelanguagemodelsforintelligentrdfknowledgegraphconstructionresultsfrommedicalontologymapping
AT stergiostegos largelanguagemodelsforintelligentrdfknowledgegraphconstructionresultsfrommedicalontologymapping
AT christosanastasiou largelanguagemodelsforintelligentrdfknowledgegraphconstructionresultsfrommedicalontologymapping
AT mariapapoutsoglou largelanguagemodelsforintelligentrdfknowledgegraphconstructionresultsfrommedicalontologymapping
AT georgiosmeditskos largelanguagemodelsforintelligentrdfknowledgegraphconstructionresultsfrommedicalontologymapping