디지털융복합연구 (Journal of Digital Convergence)

  • 제14권2호
  • /
  • Pages.325-332
  • /
  • 2016
  • /
  • 2713-6434(pISSN)
  • /
  • 2713-6442(eISSN)
한국디지털정책학회 (The Society of Digital Policy and Management)
권호 표지
DOI QR코드

DOI QR Code

국민건강영양조사를 활용한 대사증후군 유병 예측모형 개발을 위한 융복합 연구: 데이터마이닝을 활용하여

Development of Prediction Model for Prevalence of Metabolic Syndrome Using Data Mining: Korea National Health and Nutrition Examination Study

  • 김한결 (고려대학교 대학원 보건과학과 BK21 플러스 인간생명-상호작용 융복합 사업단) ;
  • 최근호 (근로복지공단 근로복지연구원 조사연구부 통계분석2팀) ;
  • 임성원 (고려대학교 일반대학원 보건과학과) ;
  • 이현실 (고려대학교 대학원 보건과학과 BK21 플러스 인간생명-상호작용 융복합 사업단)
  • Kim, Han-Kyoul (Department of Public Health Science, Graduate School BK21 Plus Program in Public Health Science, Korea University) ;
  • Choi, Keun-Ho (Korea Worker's Compensation & Welfare Service, Labor Welfare Research Institute, Research Department) ;
  • Lim, Sung-Won (School of Health Policy and Management, College of Health Science, Korea University) ;
  • Rhee, Hyun-Sill (Department of Public Health Science, Graduate School BK21 Plus Program in Public Health Science, Korea University)
  • 투고 : 2016.01.01
  • 심사 : 2016.02.20
  • 발행 : 2016.02.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

이 연구의 목적은 국민건강영양조사 2012년 자료 중 40세 이상 성인의 대사증후군 유병 여부를 예측에 영향을 미치는 변수를 확인하고 이를 예측하는 모형 개발하는데 있다. 선행연구를 통해 모델 생성에 필요한 투입변수를 선정하였다. 연구결과 투입변수 중 사회경제적 요인이 상위 순위에 해당하였으며, 건강행위 요인의 경우 하위 순위로 나타났다. 또한, 최종 예측모형은 의사결정나무 (Decision Tree)일 경우 90. 32%의 가장 높은 예측력을 나타내고 있었다. 이 연구의 결과는 다음과 같은 시사점을 나타낸다. 먼저, 대사증후군에 대한 예방 및 관리에 있어 건강행위에 대한 접근과 함께 사회경제적 요인에 대한 접근도 병행을 고려해야 한다. 또한, 의사결정나무 알고리즘의 경우 결과해석의 용이성이 있어 보건의료분야에서 많이 사용되며, 선행연구의 결과와 마찬가지로 높은 예측정확도를 나타내고 있다.

The purpose of this study is to investigate the attributes influencing the prevalence of metabolic syndrome and develop the prediction model for metabolic syndrome over 40-aged people from Korea Health and Nutrition Examination Study 2012. The researcher chose the attributes for prediction model through literature review. Also, we used the decision tree, logistic regression, artificial neural network of data mining algorithm through Weka 3.6. As results, social economic status factors of input attributes were ranked higher than health-related factors. Additionally, prediction model using decision tree algorithm showed finally the highest accuracy. This study suggests that, first of all, prevention and management of metabolic syndrome will be approached by aspect of social economic status and health-related factors. Also, decision tree algorithms known from other research are useful in the field of public health due to their usefulness of interpretation.

키워드

참고문헌

  1. E. S. Chung, An analysis of the Relationship between Depression and Menopausal Syndromes in Women at Mid life. Korean J Women Health Nurs, Vol. 3, No. 2. pp.230-240, 1997.
  2. F. Firouzi, M. Rashidi, S. Hashemi, M. Kangavari, A. Bahari, N. E. Daryani, M. M. Emam, N. Naderi, H. M. Shalmani, A. Farnood, M. Zali, A decision tree-based approach for determining low bone mineral density in inflammatory bowel disease using PWEKA software. European journal of gastroenterology &hepatology, Vol. 19, No. 12, pp. 1075-1081, 2007. https://doi.org/10.1097/MEG.0b013e3282202bb8
  3. F. S. de Edelenyi, L. Goumidi, S. Bertrais, C. Phillips, R. MacManus, H. Roche, R. Planells, D. Lairon, Prediction of the metabolic syndrome status based on dietary and genetic parameters, using Random Forest. Genes&nutrition, Vol. 3, No. 3-4, pp. 173-176, 2008. https://doi.org/10.1007/s12263-008-0097-y
  4. G. F. Marquezine, C. M. Oliveira, A. C. Pereira, J. E. Krieger, J. G. Mill, Metabolic syndrome determinants in an urban population from Brazil: social class andgender-specific interaction. International journal of cardiology, Vol. 129, NO. 2, pp.259-265, 2008. https://doi.org/10.1016/j.ijcard.2007.07.097
  5. G. J. Kim, J. S. Han, Chronic Disease Management using Smart Mobile Device, JOURNAL OF DIGITAL CONVERGENCE, Vol. 12, No. 4, pp. 335-342, 2014.
  6. H. M. Haught, J. P. Rose, J. A. Brown, Social-class indicators differentially predict engagement inprevention vs. detection behaviours. Psychology&Health, Vol. 31, No. 1, pp. 21-39, 2016. https://doi.org/10.1080/08870446.2015.1068313
  7. H. S. Chang, A Study on Weight Control Behaviour, Eating Habits and Health-related Life Habits According to Obesity Degree of Teacher in Jeonbuk Province, Korea. Journal of The Korean Society of Dietary Culture, Vol. 30, No.1 , pp.105-117. 2015. https://doi.org/10.7318/KJFC/2015.30.1.105
  8. J. Quentin-Trautvetter, P. Devos, A. Duhamel, R. Beuscart, Assessing association rules and decision trees on analysis of diabetes data from the DiabCare program in France. Studies in health technology and informatics, Vol. 90, pp.557-561. 2001.
  9. J. W. Chang, S. C. Sung, The effect of applying u-health system on metabolic syndrome management of elderly, JOURNAL OF DIGITAL CONVERGENCE, Vol. 11, No. 11, pp. 553-560, 2013. https://doi.org/10.14400/JDPM.2013.11.11.553
  10. K. D. Ko, B. Cho, W. C. Lee, H. W. Lee, H. K. Lee, & B. J. Oh, Obesity Explains Gender Differences in the Association Between Education Level and Metabolic Syndrome in South Korea The Results From the Korean National Health and Nutrition Examination Survey 2010. Asia-Pacific Journal of Public Health, Vol. 27, No, 2, pp.630-639, 2015. https://doi.org/10.1177/1010539513488624
  11. M. Dash, H. Liu, Feature selection for classification. Intelligent data analysis, Vol. 1, No. 3, pp. 131-156, 1997. https://doi.org/10.1016/S1088-467X(97)00008-5
  12. M. J. Gage, R. Schwarzkopf, M. Abrouk, J. D. Slover, Impact of metabolic syndrome on perioperative complication rates after total joint arthroplasty surgery. The Journal of arthroplasty, Vol. 29, No. 9, pp.1842-1845, 2014. https://doi.org/10.1016/j.arth.2014.04.009
  13. S. E. Ramsay, P. H. Whincup, R. Morris, L. Lennon, S. Wannamethee, Is socioeconomic position related to the prevalence of metabolic syndrome? Influence of social class across the life course in a population-based study of older men. Diabetes care, Vol. 31, No. 12, pp.2380-2382, 2008. https://doi.org/10.2337/dc08-1158
  14. S. H. Chung, Y. M. Suh, Development of a Medial Care Cost Prediction Model for Cancer Patients Using Case-Based Reasoning, Asia Pacific Journal of Information Systems, Vol. 16, No. 2, pp. 69-84, 2006.
  15. Y. S. Seo, S. H. Kang, A Convergence Study in the Severity-adjusted Mortality Ratio on inpatients with multiple chronic conditions, JOURNAL OF DIGITAL CONVERGENCE, Vol. 13, No. 12, pp. 245-257, 2015. https://doi.org/10.14400/JDC.2015.13.12.245
  16. American Heart Association, About Metabolic Syndrome, American Heart Association Home page, 2014,http://www.heart.org/HEARTORG/Conditions/More/MetabolicSyndrome/About-Metabolic-Syndrome_UCM_301920_Article.jsp, May 14.
  17. Donghyun Kim, Seoksoo Kim, "Design of Key Tree-based Management Scheme for Healthcare Information Exchange in Convergent u-Healthcare Service ", Journal of the Korea Convergence Society, Vol. 6, No. 6, pp. 81-86, 2015. https://doi.org/10.15207/JKCS.2015.6.6.081
  18. Young-Sook Kwon, "Necessity of the Development of a Web-based Obesity Management Program to Prevent Metabolic Syndrome of the Workers", Journal of the Korea Convergence Society, Vol. 5, No. 4, pp. 121-127, 2014. https://doi.org/10.15207/JKCS.2014.5.4.121