Text Extraction and Standardization System Development for Pathological Records in the Korea Biobank Network

SooJeong Ko; Sunghyeon Park; SeolWhan Oh; YunSeon Im; Surin Jung; BoYeon Choi; Jaeyoon Kim; Wona Choi; InYoung Choi

doi:10.3233/SHTI231234

Text Extraction and Standardization System Development for Pathological Records in the Korea Biobank Network

Stud Health Technol Inform. 2024 Jan 25:310:1440-1441. doi: 10.3233/SHTI231234.

Authors

SooJeong Ko^{1

2}, Sunghyeon Park^{1

2}, SeolWhan Oh¹, YunSeon Im^{1

2}, Surin Jung¹, BoYeon Choi^{1

2}, Jaeyoon Kim^{1

2}, Wona Choi², InYoung Choi²

Affiliations

¹ Department of Medical Informatics, College of Medicine, The Catholic University of Korea.
² Department of Biomedicine and Health Sciences, The Catholic University of Korea.

PMID: 38269686
DOI: 10.3233/SHTI231234

Abstract

In Korea, the Korea Centers for Disease Control and Prevention operates the Korea BioBank Network (KBN). KBN has pathological records that collected in Korea and it is useful dataset for research. In this study, we established system that time efficient and reduced error by step-by-step data extraction process from KBN pathological records. We tested the extraction process by 769 lung cancer cohorts and 1292 breast cancer cohorts and accuracy is 91%. We expect this system can be used to efficiently process data from multiple institutions, including Korea BioBank Network.

Keywords: NLP; biobank system.

MeSH terms

Biological Specimen Banks*
Centers for Disease Control and Prevention, U.S.
Humans
Lung Neoplasms*
Republic of Korea
United States