Journal of Korean Medicine for Obesity Research (한방비만학회지)

The Society of Korean Medicine for obesity Research (한방비만학회)
권호 표지
DOI QR코드

DOI QR Code

Re-evaluation of Obesity Syndrome Differentiation Questionnaire Based on Real-world Survey Data Using Data Mining

데이터 마이닝을 이용한 한의비만변증 설문지 재평가: 실제 임상에서 수집한 설문응답 기반으로

  • Oh, Jihong (Department of Korean Medicine Rehabilitation, College of Korean Medicine, Dongguk University) ;
  • Wang, Jing-Hua (Institute of Bioscience & Integrative Medicine, Daejeon University) ;
  • Choi, Sun-Mi (KM Data Division, Korea Institute of Oriental Medicine) ;
  • Kim, Hojun (Department of Korean Medicine Rehabilitation, College of Korean Medicine, Dongguk University)
  • 오지홍 (동국대학교 한의과대학 한방재활의학교실) ;
  • 왕징화 (대전대학교 동서생명과학연구원) ;
  • 최선미 (한국한의학연구원 한의약데이터부) ;
  • 김호준 (동국대학교 한의과대학 한방재활의학교실)
  • Received : 2021.11.05
  • Accepted : 2021.12.13
  • Published : 2021.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

Objectives: The purpose of this study is to re-evaluate the importance of questions of obesity syndrome differentiation (OSD) questionnaire based on real-world survey and to explore the possibility of simplifying OSD types. Methods: The OSD frequency was identified, and variance threshold feature selection was performed to filter the questions. Filtered questions were clustered by K-means clustering and hierarchical clustering. After principal component analysis (PCA), the distribution patterns of the subjects were identified and the differences in the syndrome distribution were compared. Results: The frequency of OSD in spleen deficiency, phlegm (PH), and blood stasis (BS) was lower than in food retention (FR), liver qi stagnation (LS), and yang deficiency. We excluded 13 questions with low variance, 7 of which were related to BS. Filtered questions were clustered into 3 groups by K-means clustering; Cluster 1 (17 questions) mainly related to PH, BS syndromes; Cluster 2 (11 questions) related to swelling, and indigestion; Cluster 3 (11 questions) related to overeating or emotional symptoms. After PCA, significant different patterns of subjects were observed in the FR, LS, and other obesity syndromes. The questions that mainly affect the FR distribution were digestive symptoms. And emotional symptoms mainly affect the distribution of LS subjects. And other obesity syndrome was partially affected by both digestive and emotional symptoms, and also affected by symptoms related to poor circulation. Conclusions: In-depth data mining analysis identified relatively low importance questions and the potential to simplify OSD types.

Keywords

Acknowledgement

본 연구는 한국연구재단의 중견연구자지원사업(NRF-2021R1A2C1011087)과 보건산업진흥원의 한의약혁신기술개발사업(HF20C0020)의 연구비 지원으로 이루어졌음.

References

  1. Korea Disease Control and Prevention Agency. Korean national health and nutrition examination survey: 2019 national health statistics. Cheongju : Korea Disease Control and Prevention Agency. 2020 : 153-5.
  2. Moon JS, Kang BG, Choi SM. A study of syndrome index differentiation in obesity. Journal of Korean Medicine for Obesity Research. 2007 ; 7(1) : 55-69.
  3. Kang BG, Moon JS, Choi SM. A reliability analysis of syndrome differentiation questionnaire for obesity. Korean Journal of Oriental Medicine. 2007 ; 13(1) : 109-14.
  4. Moon JS, Kang BG, Kang KW, Choi SM. Weighting method based on experts opinions for obesity syndrome differentiation questionnaire. Journal of Society of Korean Medicine for Obesity Research. 2008 ; 8(1) : 53-61.
  5. Chung WS, Hwang MJ, Lee AR, Moon JS, Choi SM, Song MY. The difference of syndrome differentiation patterns between premenopausal and climacteric obese Korean women. Journal of Society of Korean Medicine for Obesity Research. 2008 ; 8(2) : 37-47.
  6. Cho YJ, Lee AR, Hwang MJ, Song MY. Relationship between oriental obesity pattern, life habitual factors and psychological factors in Korean obese and overweight women. Journal of Society of Korean Medicine for Obesity Research. 2011 ; 11(2) : 15-24.
  7. Kim EJ, Lee AR, Hwang MJ, Cho JH, Choi SM, Chung SH, et al. Relationship between visceral adipose tissue and oriental obesity pattern identification in obese Korean women. Journal of Korean Medicine Rehabilitation. 2011 ; 21(2) : 279-88.
  8. Kang KW, Moon JS, Kang BG, Kim BY, Choi SM. The comparison of pattern identification diagnosis according to symptom scale based on obesity pattern identification questionnaire. Journal of Society of Korean Medicine for Obesity Research. 2009 ; 9(1) : 37-44.
  9. Agarwal S. Data mining: data mining concepts and techniques. 2013 International Conference on Machine Intelligence and Research Advancement. 2013 : 203-7.
  10. Van Rossum G, Drake FL. Python 3 reference manual. Scotts Valley, CA : CreateSpace. 2009.
  11. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: machine learning in Python. Journal of Machine Learning Research. 2011 ; 12 : 2825-30.
  12. Kang KW, Moon JS, Kang BG, Kim BY, Kim NS, Yoo JH, et al. The discrimination model for the pattern identification diagnosis of overweight patients. Korea Journal of Oriental Medicine. 2008 ; 14(2) : 41-6.
  13. Park J, Lee M, Kim H, Hong S, Lee D, Yoo J, et al. Efficacy and adverse events of Bangpungtongseong-san (Bofutsusho-san) and Bangkihwangki-tang (Boiogiot-tang) by oriental obesity pattern identification on obese subjects: randomized, double blind, placebo-controlled trial. J Korean Med Obes Res. 2011 ; 12(2) : 265-78.