텍스트마이닝 기법을 이용한 『상한론』 내의 증상-본초 조합의 탐색적 분석
Analysis of Symptoms-Herbs Relationships in Shanghanlun Using Text Mining Approach
2
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Shanghanlun (Treatise on Cold Damage Diseases) is the oldest document in the literature on clinical records of Traditional Asian medicine (TAM), on which TAM theories about symptoms-herbs relationships are based. In this study, we aim to quantitatively explore the relationships between symptoms and herbs in Shanghanlun. The text in Shanghanlun was converted into structured data. Using the structured data, Term Frequency - Inverse Document Frequency (TF-IDF) scores of symptoms and herbs were calculated from each chapter to derive the major symptoms and herbs in each chapter. To understand the structure of the entire document, principal component analysis (PCA) was performed for the 6-dimensional chapter space. Bipartite network analysis was conducted focusing on Jaccard scores between symptoms and herbs and eigenvector centralities of nodes. TF-IDF scores showed the characteristics of each chapter through major symptoms and herbs. Principal components drawn by PCA suggested the entire structure of Shanghanlun. The network analysis revealed a ‘multi herbs – multi symptoms’ relationship. Common symptoms and herbs were drawn from high eigenvector centralities of their nodes, while specific symptoms and herbs were drawn from low centralities. Symptoms expected to be treated by herbs were derived, respectively. Using measurable metrics, we conducted a computational study on patterns of Shanghanlun. Quantitative researches on TAM theories will contribute to improving the clarity of TAM theories.
Abstract
Shanghanlun (Treatise on Cold Damage Diseases) is the oldest document in the literature on clinical records of Traditional Asian medicine (TAM), on which TAM theories about symptoms-herbs relationships are based. In this study, we aim to quantitatively explore the relationships between symptoms and herbs in Shanghanlun. The text in Shanghanlun was converted into structured data. Using the structured data, Term Frequency - Inverse Document Frequency (TF-IDF) scores of symptoms and herbs were calculated from each chapter to derive the major symptoms and herbs in each chapter. To understand the structure of the entire document, principal component analysis (PCA) was performed for the 6-dimensional chapter space. Bipartite network analysis was conducted focusing on Jaccard scores between symptoms and herbs and eigenvector centralities of nodes. TF-IDF scores showed the characteristics of each chapter through major symptoms and herbs. Principal components drawn by PCA suggested the entire structure of Shanghanlun. The network analysis revealed a ‘multi herbs – multi symptoms’ relationship. Common symptoms and herbs were drawn from high eigenvector centralities of their nodes, while specific symptoms and herbs were drawn from low centralities. Symptoms expected to be treated by herbs were derived, respectively. Using measurable metrics, we conducted a computational study on patterns of Shanghanlun. Quantitative researches on TAM theories will contribute to improving the clarity of TAM theories.
참고문헌 (23)
- Shin SW, "Diagnosis system in Sanghanlun", Journal of Pathology in Korean Medicine, 12(1), pp.1~18 (1998)
- Shin HM, "A Study on the Dose of Prescription in Shanghanlun", Journal of Korean Medicine, 20(3), pp.3~8 (1999)
- 홍성민, "상한론 처방을 이용한 아토피성 피부염 환자 1례 보고", 한방안이비인후피부과학회지, 20(2), pp.230~239 (2007), 대한한방안이비인후피부과학회
- 전태동, "교통사고 환자에 대한 상한론 처방의 유의성 연구", 한방재활의학과학회지, 20(1), pp.153~166 (2010), 한방재활의학과학회
- Hearst MA, "Untangling text data mining", Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics, pp.3~10 (1999)
- 배정환, "텍스트 마이닝을 이용한2012년 한국대선 관련 트위터 분석", 지능정보연구, 19(3), pp.141~156 (2013), 한국지능정보시스템학회[DOI]
- Chou CH, "A text mining approach to Internet abuse detection", Information Systems and e-Business Management, 6(4), pp.419~439 (2008)
- Spasic I, "Text mining and ontologies in biomedicine : making sense of raw text", Briefings in bioinformatics, 6(3), pp.239~251 (2005)
- 이충열, "현대 한의학의 이해 - 한의학의 정체성 문제 고찰을 위한 예비 연구", 동의생리병리학회지, 24(5), pp.758~769 (2010), 한의병리학회
- 이충열, "한의학 기초이론의 현대화와 한의학 이론용어", 동의생리병리학회지, 27(5), pp.540~552 (2013), 한의병리학회
- 이정현, "한의학 용어 개념의 정량화 연구 - 방약합편의 병증 용어를 대상으로 -", 대한한의학원전학회지, 27(1), pp.99~109 (2014), 대한한의학원전학회[DOI]
- 송영섭, "데이터 마이닝을 이용한 대변과 약물간의 연관성 분석 -방약합편을 중심으로-", 대한한의진단학회지, 16(2), pp.33~46 (2012), 대한한의진단학회
- 배효진, "텍스트마이닝(Text mining)을 활용한 한의학 원전 연구의 가능성 모색 -『黃帝內經』에 대한 적용례를 중심으로 -", 대한한의학원전학회지, 31(4), pp.27~46 (2018), 대한한의학원전학회[DOI]
- Jung WM, "Spatial patterns of the indications of acupoints using data mining in classic medical text: a possible visualization of the meridian system", Evidence-Based Complementary and Alternative Medicine, 2015 (2015)
- 오준호, "의학 사상의 유사성은 계량 분석 될 수 있는가", 대한한의학원전학회지, 31(2), pp.71~82 (2018), 대한한의학원전학회[DOI]
- 김성원, "데이터베이스(DB)를 이용한 傷寒論 組方의 分析 - 桂枝湯, 麻黃湯, 大靑龍湯을 중심으로 -", 대한한의학원전학회지, 32(1), pp.171~189 (2019), 대한한의학원전학회[DOI]
- 김상운, "상한론 증상에 근거한 진료기록부 작성에 대한 제언", 대한한의진단학회지, 18(2), pp.85~110 (2014), 대한한의진단학회
- Shen CW, "Analyzing the trend of O2O commerce by bilingual text mining on social media", Computers in Human Behavior, 101, pp.474~483 (2019)
- Wang H, "A system for real-time twitter sentiment analysis of 2012 us presidential election cycle", Proceedings of the ACL 2012 system demonstrations, pp.115~120 (2012)
- Oh J, "Construction And Analysis Of The Time-Evolving Pain-Related Brain Network Using Literature Mining", Journal of Pain Research, 12, pp.2891~ (2019)
- Kwon Y, "New approach to generating insights for aging research based on literature mining and knowledge integration", PloS one, 12(8) (2017)
- 이정환, "<약징(藥徵)>을 통해 본 길익동동(吉益東洞)의 의학사상 연구 Ⅲ", 대한한의학원전학회지, 19(2), pp.66~73 (2006), 대한한의학원전학회
- Yeo IS, "Korean medicine, see it as science?", Research Institute for Healthcare Policy Korean Medical Association, 9(3), pp.70~75 (2011)