Automated Information Extraction Pipeline for Constructing ED Knowledge Graphs from Korean Clinical Problem Lists
Studies in Health Technology and Informatics · 21.05.2026
DOI: 10.3233/shti260360 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 21.05.2026. Verfasst von Hyeyoon Moon und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Digital Health, SAIHST, Sungkyunkwan University, Seoul, Korea. Hauptthemen laut MEDLINE: Data Mining, Natural Language Processing, Electronic Health Records, Information Storage and Retrieval. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Emergency department problem lists remain unstructured despite documenting major medical problems. We developed an information extraction pipeline for constructing ED knowledge graphs, comparing three normalization strategies and five LLMs on 250 annotated Samsung Medical Center ED problem lists. Llama 3.1 70B with Named Entity Disambiguation achieved optimal performance (Exact F1: 0.65, Partial F1: 0.70), improving F1 by 6.56% over raw text. The resulting knowledge graph from 2,000 problem lists contains 1,983 entities and 3,208 relations, establishing a practical framework for large-scale ED knowledge graph construction.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Digital Health, SAIHST, Sungkyunkwan University, Seoul, Korea.
- Department of Emergency Medicine, Samsung Medical Center, Seoul, Korea.
Zitieren
APA
Moon, H., Jang, E., & Cha, W. C. (2026). Automated Information Extraction Pipeline for Constructing ED Knowledge Graphs from Korean Clinical Problem Lists. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260360
Vancouver
Moon H, Jang E, Cha WC. Automated Information Extraction Pipeline for Constructing ED Knowledge Graphs from Korean Clinical Problem Lists. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260360
BibTeX
@article{Moon2026,
author = {Moon, Hyeyoon and Jang, Eunhye and Cha, Won Chul},
title = {Automated Information Extraction Pipeline for Constructing ED Knowledge Graphs from Korean Clinical Problem Lists},
journal = {Studies in Health Technology and Informatics},
year = {2026},
doi = {10.3233/shti260360}
}
EUVIMED