Journal of Physiology & Pathology in Korean Medicine (동의생리병리학회지)

The Physiological Society of Korean Medicine and The Society of Pathology in Korean Medicine (대한동의생리학회·한의병리학회)
권호 표지

Data mining Algorithms for the Development of Sasang Type Diagnosis

사상체질 진단검사를 위한 데이터마이닝 알고리즘 연구

  • Hong, Jin-Woo (Division of Clinical Medicine, School of Korean Medicine, Pusan National University) ;
  • Kim, Young-In (Department of Biomedical Engineering, College of Natural Resource and Life Science, Pusan National University) ;
  • Park, So-Jung (Division of Longevity and Biofunctional Medicine, School of Korean Medicine, Pusan National University) ;
  • Kim, Byoung-Chul (Department of Biomedical Engineering, College of Natural Resource and Life Science, Pusan National University) ;
  • Eom, Il-Kyu (School of Electrical Engineering, Pusan National University) ;
  • Hwang, Min-Woo (Division of Clinical Medicine, School of Korean Medicine, Pusan National University) ;
  • Shin, Sang-Woo (Division of Applied Medicine, School of Korean Medicine, Pusan National University) ;
  • Kim, Byung-Joo (Division of Longevity and Biofunctional Medicine, School of Korean Medicine, Pusan National University) ;
  • Kwon, Young-Kyu (Division of Longevity and Biofunctional Medicine, School of Korean Medicine, Pusan National University) ;
  • Chae, Han (Division of Longevity and Biofunctional Medicine, School of Korean Medicine, Pusan National University)
  • 홍진우 (부산대학교 한의학전문대학원 임상의학부) ;
  • 김영인 (부산대학교 생명자원과학대학 바이오메디컬공학과) ;
  • 박소정 (부산대학교 한의학전문대학원 양생기능의학부) ;
  • 김병철 (부산대학교 생명자원과학대학 바이오메디컬공학과) ;
  • 엄일규 (부산대학교 전자전기공학부) ;
  • 황민우 (부산대학교 한의학전문대학원 임상의학부) ;
  • 신상우 (부산대학교 한의학전문대학원 응용의학부) ;
  • 김병주 (부산대학교 한의학전문대학원 양생기능의학부) ;
  • 권영규 (부산대학교 한의학전문대학원 양생기능의학부) ;
  • 채한 (부산대학교 한의학전문대학원 양생기능의학부)
  • Published : 2009.12.25
Download PDF
⟨ Previous Next ⟩

Abstract

This study was to compare the effectiveness and validity of various data-mining algorithm for Sasang type diagnostic test. We compared the sensitivity and specificity index of nine attribute selection and eleven class classification algorithms with 31 data-set characterizing Sasang typology and 10-fold validation methods installed in Waikato Environment Knowledge Analysis (WEKA). The highest classification validity score can be acquired as follows; 69.9 as Percentage Correctly Predicted index with Naive Bayes Classifier, 80 as sensitivity index with LWL/Tae-Eum type, 93.5 as specificity index with Naive Bayes Classifier/So-Eum type. The classification algorithm with highest PCP index of 69.62 after attribute selection was Naive Bayes Classifier. In this study we can find that the best-fit algorithm for traditional medicine is case sensitive and that characteristics of clinical circumstances, and data-mining algorithms and study purpose should be considered to get the highest validity even with the well defined data sets. It is also confirmed that we can't find one-fits-all algorithm and there should be many studies with trials and errors. This study will serve as a pivotal foundation for the development of medical instruments for Pattern Identification and Sasang type diagnosis on the basis of traditional Korean Medicine.

Keywords

References

  1. 허 준, 최병주. (클레멘타인을 이용한)데이터마이닝 : 입문편. SPSS 아카데미, 서울, 2001
  2. 이창희. Feature selection을 이용한 중요변수 선택방법에 관한 연구. 석사학위논문, 중앙대학교, 2007
  3. Michael, J.A. Berry and Gordon Linoff, Data Mining Techniques: For Marketing, Sales, and Customer Support, John Wiley & Sons, Inc., 1997
  4. Frank, E., Hall, M., Trigg, L., Holmes, G., Witten, I.H. Data mining in bioinformatics using Weka. Bioinformatics. 20(15):2479-2481, 2004 https://doi.org/10.1093/bioinformatics/bth261
  5. 이덕기. 데이터마이닝 소프트웨어의 효율성에 관한 비교 연구. 석사학위논문. 호서대학교, 2001
  6. 이수진, 김명근, 채 한. 사상체질 진단검사 타당성분석에 대한 연구. 대한한의학회지 29(1):7-14, 2008
  7. 황상문, 박소정, 강기림, 권영규, 채 한. 사상체질 진단검사 타당성 분석지표의 일반화 연구. 동의생리병리학회지 23(5):950-957, 2009
  8. Chae, H., Lyoo, I.K., Lee, S.J., Cho, S., Bae, H., Hong, M., Shin, M. An alternative way to individualized medicine: psychological and physical traits of Sasang typology. Journal of Alternative and Complementary Medicine. 9(4):519-528, 2003 https://doi.org/10.1089/107555303322284811
  9. 채 한, 황상문, 엄일규, 김병철, 김영인, 김병주, 권영규. 신경망을 사용한 사상체질 진단검사 개발 연구. 동의생리병리학회지 23(4):765-771, 2009
  10. 박은경, 이영섭, 박성식. 의사결정나무법을 이용한 체질진단에 관한 연구. 사상체질의학회지 13(2):144-155, 2001
  11. 진희정, 문진석, 고성호, 구임회, 이시우, 이도현, 송미영, 김종열. 사상체질 의사결정시스템 구축을 위한 체질 진단 자료를 이용한 예비연구. 한국한의학연구원논문집, 13(2):75-81, 2007
  12. 박성식, 최재영. 의사결정나무법을 이용한 설문지의 응답특성에 대한 임상적 검토. 사상체질의학회지 15(3):177-186, 2003
  13. Zhang, Q., Lee, K.J., Whangbo, T.K. K-mean and double cross-validation algorithm for LS-SVM in Sasang typology classification. Proceedings of the IEEE International Conference on Automation and Logistics. August pp 18-21, 2007, Jinan, China, pp 426-430, 2007 https://doi.org/10.1109/ICAL.2007.4338600
  14. Witten, I.H., Frank, E. Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations. Morgan Kaufmann, San Francisco, C.A, 2000
  15. 김선호, 고병희, 송일병. 사상체질분류검사지(QSCCⅡ)의 표준화 연구. 사상의학회지 7(1):187-246, 1995
  16. 이수진, 박수현, 고유선, 박수진, 엄일규, 김병철, 김영인, 백진웅, 김명근, 권영규, 채한. 임피던스 분석을 활용한 사상인의 신체계측 연구. 동의생리병리학회지 23(2):433-437, 2009
  17. Savova, G.K., Ogren, P.V., Duffy, P.H., Buntrock, D.J., Chute, C.G. Mayo clinic NLP system for patient smoking status identification. Journal of the American Medical Informatics Association. 15(1):25-28, 2008 https://doi.org/10.1197/jamia.M2437
  18. Park, S.H., Kim, M.G., Lee, S.J., Kim, J.Y., Chae, H. Temperament and Character Profiles of Sasang Typology in an Adult Clinical Sample. Evid Based Complement Alternat Med. doi:10.1093/ecam/nep034, Advance Access published April 20, 2009
  19. Chae, H., Park, S.H., Lee, S.J., Kim, M.g., Wedding, D., Kwon, Y.K. Psychological profile of Sasang typology: A systematic Review. eCAM, 6: 21-29, 2009 https://doi.org/10.1093/ecam/nep079
  20. 채 한, 박수잔, 이수진, 고광찬. 사상 유형학의 성격심리학적 고찰. 대한한의학회지 25(2):151-164, 2004
  21. Lukman, S., He, Y., Hui, S.C. Computational medthos for Traditional Chinese Medicine: A survey. Computer methods and programs in biomedicine. 88: 283-294, 2007 https://doi.org/10.1016/j.cmpb.2007.09.008