Korean Journal of Acupuncture

Society for Meridian and Acupoint (경락경혈학회)
권호 표지
DOI QR코드

DOI QR Code

Machine Learning Approach to Blood Stasis Pattern Identification Based on Self-reported Symptoms

기계학습을 적용한 자기보고 증상 기반의 어혈 변증 모델 구축

  • Kim, Hyunho (Department of Biofunctional Medicine & Diagnostics, College of Korean Medicine, Kyung Hee University) ;
  • Yang, Seung-Bum (Department of Medical Non-commissioned Officer, Wonkwang Health Science) ;
  • Kang, Yeonseok (Department of Medical History, College of Korean Medicine, Wonkwang University) ;
  • Park, Young-Bae (Department of Biofunctional Medicine & Diagnostics, College of Korean Medicine, Kyung Hee University) ;
  • Kim, Jae-Hyo (Department of Meridian & Acupoint, College of Korean Medicine, Wonkwang University)
  • 김현호 (경희대학교 한의과대학 진단생기능의학과학교실) ;
  • 양승범 (원광보건대학교 의무부사관과) ;
  • 강연석 (원광대학교 한의과대학 의사학교실) ;
  • 박영배 (경희대학교 한의과대학 진단생기능의학과학교실) ;
  • 김재효 (원광대학교 한의과대학 경혈학교실)
  • Received : 2016.06.07
  • Accepted : 2016.06.25
  • Published : 2016.09.27
Download PDF
⟨ Previous Next ⟩

Abstract

Objectives : This study is aimed at developing and discussing the prediction model of blood stasis pattern of traditional Korean medicine(TKM) using machine learning algorithms: multiple logistic regression and decision tree model. Methods : First, we reviewed the blood stasis(BS) questionnaires of Korean, Chinese, and Japanese version to make a integrated BS questionnaire of patient-reported outcomes. Through a human subject research, patients-reported BS symptoms data were acquired. Next, experts decisions of 5 Korean medicine doctor were also acquired, and supervised learning models were developed using multiple logistic regression and decision tree. Results : Integrated BS questionnaire with 24 items was developed. Multiple logistic regression models with accuracy of 0.92(male) and 0.95(female) validated by 10-folds cross-validation were constructed. By decision tree modeling methods, male model with 8 decision node and female model with 6 decision node were made. In the both models, symptoms of 'recent physical trauma', 'chest pain', 'numbness', and 'menstrual disorder(female only)' were considered as important factors. Conclusions : Because machine learning, especially supervised learning, can reveal and suggest important or essential factors among the very various symptoms making up a pattern identification, it can be a very useful tool in researching diagnostics of TKM. With a proper patient-reported outcomes or well-structured database, it can also be applied to a pre-screening solutions of healthcare system in Mibyoung stage.

Keywords

References

  1. Yim HJ, Kim SH, Lee SR, Jung IN. Study to develop the instrument of pattern identification for Hwa-byung. Korean J Oriental Physiology & Pathology. 2008 ; 22(5) : 1071-7.
  2. Park YJ, Park JS, Kim MY, Park YB. Development of a valid and reliable phlegm pattern questionnaire. J Altern Complement Med. 2011 ; 17(9) : 851-8. https://doi.org/10.1089/acm.2010.0504
  3. Park YJ, Lim JS, Park YB. Development of a valid and reliable food retention questionnaire. European Journal of Integrative Medicine. 2013 ; 5(5) : 432-7. https://doi.org/10.1016/j.eujim.2013.06.002
  4. Yoon KJ, Park YB, Park YJ, Kim MY. Development and validation of a Lao Juan questionnaire. Chin J Intergr Med. 2015 ; 21(7) : 500-6. https://doi.org/10.1007/s11655-015-2079-4
  5. Ryu HH, Lee H, Kim H, Kim JY. Reliability and validity of a cold-heat pattern questionnaire for traditional Chinese medicine. J Altern Complement Med. 2010 ; 16(6) : 663-7. https://doi.org/10.1089/acm.2009.0331
  6. Park YJ, Yang DH, Lee JM, Park YB. Development of a valid and reliable blood stasis questionnaire and its relationship to heart rate variability. Complement Ther Med. 2013 ; 21(6) : 633-40. https://doi.org/10.1016/j.ctim.2013.08.019
  7. Kim SH, Ko BH, Song IB. A study on the standardization of QSCC II. J of Sasang Constitutional Medicine. 1996 ; 8(1) : 187-246.
  8. Lee JH, Ko BH, Song IB. A study on the validation of QSCC II. J of Sasang Constitutional Medicine. 1996 ; 8(1) : 247-94.
  9. Park DM, Lee SR, Kang WC, Jung IC. Preliminary Study to Develop the Instrument of Pattern Identification for Jing Ji and Zheng Chong. Journal of Oriental Neuropsychiatry. 2010 ; 21(2) : 1-15.
  10. Lee IS, Bae GM. A Clinical Study on Differentiation of Syndromes of Amenorrhea or Oligomenorrhea with DSOM. The Journal of Oriental Obstetrics and Gynecology. 2009 ; 22(2) : 189-208.
  11. Shin JH, Jung WY, Moon YK, Nam HJ, Kim YB, Lee JH, et al. An Expert Survey for Developing the Pattern Diagnosis Instrument of Acne. 2015 ; 28(2) : 23-32.
  12. Kim SK, Jang HC, Kim JH, Kim C, Yea SJ, Song MY. Computational methods for traditional Korean medicine : A survey. Korean J Oriental Physiology & Pathology. 2011 ; 25(5) : 894-9.
  13. Kim KK, Kim JW, Lee EJ, Kim JY, Choi SM. Study on classification function into Sasang constitution using data mining techniques. Korean J Oriental Physiology & Pathology. 2004 ; 18(6) : 1938-44.
  14. Hong JW, Kim YI, Park SJ, Kim BC, Eom IK, Hwang MW, et al. Data mining algorithms for the development of Sasang type diagnosis. Korean J Oriental Physiology & Pathology. 2009 ; 23(6) : 1234-40.
  15. Chae H, Hwang SM, Eom IK, Kim BC, Kim YI, Kim BJ, et al. Development of Sasang type diagnostic test with neural network. Korean J Oriental Physiology & Pathology. 2009 ; 23(4) : 765-71.
  16. Shin YS, Park YB, Park YJ, Kim MY, Lee SC, Oh HS. A fundamental study for 8 constitution medicine diagnosis expert system development. J Korean Institude of Oriental Medical Diagnostics. 2007 ; 11(1) : 25-47.
  17. Shin YS, Park YB, Park YJ, Kim MY, Lee SC, Oh HS. A study for 8 constitution medicine diagnosis expert system development. J Korean Institude of Oriental Medical Diagnostics. 2008 ; 12(1) : 142-84.
  18. Hand D, Mannila H, Smyth P. Principles of Data Mining. Cambridge, MA : MIT Press. 2001.
  19. Yang DH, Park YJ, Park YB, Lee SC. Development of questionnaires for blood stasis pattern. J Korean Institude of Oriental Medical Diagnostics. 2006 ; 10(1) : 141-52.
  20. Kim JB, Choi SH, Ahn KS. Study on the effects of Taorenchengqitang and its components on blood stasis model. Korean J Oriental Medical Pathology. 1997 ; 11(1) : 65-76.
  21. Gorsuch. Factor Analysis, 2nd edition. NJ : Lawrence Erlbaum. 1983.
  22. Breiman L, Friedman JH, Olshen RA, Stone CJ. Classification and regression trees. Monterey, CA : Wadsworth & Brooks/Cole Advanced Books & Software. 1984.
  23. Landis JR, Koch GG. The measurement of observer agreement for categorical data. Biometrics. 1977 ; 33 : 159-74. https://doi.org/10.2307/2529310
  24. Mary LM. Interrater reliability: the kappa statistic. Biochem Med. 2012 ; 22(3) : 276-82.

Cited by

  1. 머신러닝을 이용한 급성심근경색증 환자의 퇴원 시 사망 중증도 보정 방법 개발에 대한 융복합 연구 vol.17, pp.2, 2016, https://doi.org/10.14400/jdc.2019.17.2.217
  2. 한의 체중 조절 프로그램에 참여한 과체중, 비만 환자에서의 머신러닝 기법을 적용한 체중 감량 예측 연구 vol.41, pp.2, 2020, https://doi.org/10.13048/jkm.20015
  3. 머신러닝 기반 음성분석을 통한 체질량지수 분류 예측 - 한국 성인을 중심으로 vol.33, pp.4, 2021, https://doi.org/10.7730/jscm.2021.33.4.1