[논문]대사증후군의 인지와 신체활동 실천에 영향을 미치는 요인: 데이터 마이닝 접근

이수경; 문미경

doi:10.5762/kais.2017.18.12.581

대사증후군의 인지와 신체활동 실천에 영향을 미치는 요인: 데이터 마이닝 접근
Factors influencing metabolic syndrome perception and exercising behaviors in Korean adults: Data mining approach 원문보기

한국산학기술학회논문지 = Journal of the Korea Academia-Industrial cooperation Society, v.18 no.12, 2017년, pp.581 - 588

이수경 (계명대학교 간호대학, 간호과학연구소) , 문미경 (경북대학교 간호대학, 간호과학연구소)

초록
AI-Helper

본 연구는 기계 학습법 중 하나인 XGBoost를 이용하여 대사증후군을 인지하고 신체활동을 수행하는 집단을 예측하고자 2014년 7월부터 2015년 12월까지 시도되었다. 이에 2009-2013년 지역사회건강조사를 연구자료로 사용하였고 370,430명의 성인을 분석에 포함하였다. 본 연구의 종속변수는 대사증후군의 인지 및 신체활동 실천정도에 따른 단계로 3단계로 구분하였다:Stage 1(무인지, 무 신체활동), Stage 2(인지, 무 신체활동), and Stage 3(인지, 신체활동). 예측변수로는 5년간의 지역사회건강조사 중 공통으로 수집된 문항으로부터 161개의 특성을 선택하였다. 자료 분석을 위해 R program을 이용하여 XGBoost 알고리즘을 적용하였다. 분석 결과 정확도는 0.735 이었으며, 가장 영향을 미치는 10개의 특성은 나이, 교육수준, 체중조절시도 경험, EQ-5D 운동능력, 영양표시 확인, 개인 건강보험가입 유무, EQ-5D 일상활동, 금연광고경험 여부, 통증유무, 당뇨에 대한 보건기관의 교육 경험 순으로 확인되었다. 본 연구결과는 XGBoost가 보건의료빅데이터를 이용한 질병의 예방과 관리에 영향을 주는 요인을 확인하는데 유용한 도구임을 보여주었다. 또한, 본 연구를 통해 대사증후군에 취약한 계층을 확인하고 이를 위한 교육프로그램 개발에 도움을 줄 수 있을 것으로 보인다.

Abstract ▼ AI-Helper

This study was conducted to determine which factors would predict metabolic syndrome (MetS) perception and exercise by applying a machine learning classifier, or Extreme Gradient Boosting algorithm (XGBoost) from July 2014 to December 2015. Data were obtained from the Korean Community Health Survey (KCHS), representing different community-dwelling Korean adults 19 years and older, from 2009 to 2013. The dataset includes 370,430 adults. Outcomes were categorized as follows based on the perception of MetS and physical activity (PA): Stage 1 (no perception, no PA), Stage 2 (perception, no PA), and Stage 3 (perception, PA). Features common to all questionnaires for the last 5 years were selected for modeling. Overall, there were 161 features, categorical except for age and the visual analogue scale (EQ-VAS). We used the Extreme Boosting algorithm in R programming for a model to predict factors and achieved prediction accuracy in 0.735 submissions. The top 10 predictive factors in Stage 3 were: age, education level, attempt to control weight, EQ mobility, nutrition label checks, private health insurance, EQ-5D usual activities, anti-smoking advertising, EQ-VAS, education in health centers for diabetes, and dental care. In conclusion, the results showed that XGBoost can be used to identify factors influencing disease prevention and management using healthcare bigdata.

주제어

AI 본문요약
AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

문제 정의

This study was conducted to identify factors associated with the stages of MetS and PA using secondary data obtained from the 2009-2013 KCHS. A powerful machine learning tool, XGBoost, was used for data analysis.

제안 방법

Accuracy, recall and precision were used for performance evaluation. Accuracy is a value that indicates the ratio of correctly identified data with all testing data.
The KCHS questionnaire had little difference according to health concerns per year. For this study, a common questionnaire was used for 5 years along with modeling features. Among them, 15 features related to the outcome variables(PA and the perception of Mets) were excluded.
The questionnaires of the survey consist of 10 categories: housing characteristics, health behaviors, immunizations, and screening, chronic disease, hospital utilization, injuries and addiction, limitation of activities, and quality-of-life(QoL), healthcare utilization, the sociophysical environment, and one's education and economic status[12].
The study has some limitation, however, because it did not compare performance with other data mining classifiers – including measures such as the area under the receiver operating characteristic curve(ROC-AUC).
The KCHS, initiated by Korea Center for Disease Control and Prevention(KCDC), monitors the health status of the Korean population through the collection and analysis of data on a broad range of health topics[12]. The survey data include comprehensive information on pro-health behaviors including PA, sociodemographics, health status, and healthcare utilization[13]. Survey data is a good resource to identify group characteristics engaging in PA and being aware of MetS.
The KCHS was conducted to provide data for planning, implementing, monitoring, and evaluating community health promotion and disease prevention by the KCDC from 253 existing administrative districts in Korea[12]. The survey monitors the health status of the Korean population through collection and analysis of data, using a broad range of health topics. The questionnaires of the survey consist of 10 categories: housing characteristics, health behaviors, immunizations, and screening, chronic disease, hospital utilization, injuries and addiction, limitation of activities, and quality-of-life(QoL), healthcare utilization, the sociophysical environment, and one's education and economic status[12].
Therefore, the purpose of this study was to determine which factors would be most predictive of the group who engaged in PA with a clear perception of MetS, while applying a machine learning classifier, XGBoost.

대상 데이터

A total of 370,430 subjects were included for the final modeling. 42.
Data were obtained from the KCHS, which represents community-dwelling Korean adults 19 years and older, from 2009 to 2013. It includes 370,430 adults for the last 5 years[Table 1]. The KCHS was conducted to provide data for planning, implementing, monitoring, and evaluating community health promotion and disease prevention by the KCDC from 253 existing administrative districts in Korea[12].
A powerful machine learning tool, XGBoost, was used for data analysis. The large dataset in the study was representative of community-dwelling Korean adults and includes over one hundred seventy variables related to health status.

이론/모형

This study used an Extreme Gradient Boosting method to predict the group who took part in PA and correctly perceived MetS. The most weighted 15 factors were identified, and the relationship between these top factors and stages were able to shed a great deal of light on characteristics of the group.

성능/효과

Based on the machine learning results, age, educational level, weight control, EQ-5D mobility, private health insurance, and EQ-5D usual activity, Experience with anti-smoking advertisements, EQ-VAS, and education in health centers for diabetes mellitus were the top 10 factors for predicting Stage 3, especially for those who were aware of MetS and engaged in PA.
The results of this study show that people with experience in attempting to control body weight and checking the nutritional labeling tend to be much more perceptive about MetS and engaged in PA. The results were similar to the study of Lee and colleagues[6]’ regarding the elderly.

참고문헌 (25)

S. M. Grundy, J. I. Cleeman, S. R. Daniels, K. A. Donato, R. H. Eckel, B. A. Franklin, D. J. Gordon, R. M. Krauss, P. J. Savage, S. C. Smith, J. A. Spertus, "Diagnosis and management of the metabolic syndrome", Circulation, vol. 112, no. 17, pp. 2735-52, 2005. DOI: https://doi.org/10.1161/CIRCULATIONAHA.105.169404

상세보기
S. Mottillo, K. B. Filion, J. Genest, L. Joseph, L. Pilote, P. Poirier, S. Rinfret, E. L. Schiffrin, M. L. Eisenberg, "The metabolic syndrome and cardiovascular risk: a systematic review and meta-analysis", Journal of the American College of Cardiology, vol. 56, no. 14, pp. 1113-32, Sep 28, 2010. DOI: https://doi.org/10.1016/j.jacc.2010.05.034

상세보기
J. O. Hill, D. Bessesen, "What to do about the metabolic syndrome?", Archives of internal medicine, vol. 163, no. 4, pp. 395-7, 2003. DOI: https://doi.org/10.1001/archinte.163.4.395

상세보기
M. F. Jumean, Y. Korenfeld, V. K. Somers, K. S. Vickers, R. J. Thomas, F. Lopez-Jimenez, "Impact of diagnosing metabolic syndrome on risk perception", American journal of health behavior, vol. 36, no. 4, pp. 522-3, Jul 1, 2012. DOI: https://doi.org/10.5993/AJHB.36.4.9

상세보기
K. Glanz, B. Rimer, K. Viswanath, eds. Health behavior and health education: theory, research, and practice. John Wiley & Sons, 2008.
J. A. Lee, J. S. Lee, J. H. Park, "Metabolic syndrome perception and exercise behaviors in the elderly", Korean Journal of Health Education and Promotion, vol. 29, No. 5. pp. 61-75, 2012.
K. J. Stewart, A. C. Bacher, K. Turner, J. G. Lim, P. S. Hees, E. P. Shapiro, M. Tayback, P. Ouyang, "Exercise and risk factors associated with metabolic syndrome in older adults." American journal of preventive medicine, vol. 28, no. 1 pp. 9-18, Jan, 2005. DOI: https://doi.org/10.1016/j.amepre.2004.09.006

상세보기
J. R. Churilla, E. C. Fitzhugh, "Relationship between leisure-time physical activity and metabolic syndrome using varying definitions: 1999-2004 NHANES", Diabetes and Vascular Disease Research, vol. 6, no. 2 pp. 100-9, Apr, 2009. DOI: https://doi.org/10.1177/1479164109336040

상세보기
S. K. Park, J. L. Larson, "The relationship between physical activity and metabolic syndrome in people with chronic obstructive pulmonary disease", The Journal of cardiovascular nursing, vol. 29, no. 6, pp. 499, Nov, 2014. DOI: https://doi.org/10.1097/JCN.0000000000000096

상세보기
A. Bener, M. T. Yousafzai, S. Darwish, A. O. Al-Hamaq, E. A. Nasralla, M. Abdul-Ghani, "2013. Obesity index that better predict metabolic syndrome: body mass index, waist circumference, waist hip ratio, or waist height ratio", Journal of obesity, 2013. DOI: https://doi.org/10.1155/2013/269038
A. Scuteri, S. Laurent, F. Cucca, J. Cockcroft, P. G. Cunha, L. R. Manas, F. U. M. Raso, M. L. Muiesan, L. Ryliskyte, E. Rietzschel, J. Strait, "Metabolic syndrome across Europe: different clusters of risk factors", European journal of preventive cardiology, vol. 22, no. 4, pp. 486-491, 2015. DOI: https://doi.org/10.1177/2047487314525529

상세보기
Y. T. Kim, B. Y. Choi, K.O. Lee, H. Kim, J. H. Chun, S. Y. Kim, D. H. Lee, T. A. Ghim, D. S. Lim, Y. W. Kang, T. Y Lee, "Overview of Korean Community Health Survey", Journal of the Korean Medical Association/Taehan Uisa Hyophoe Chi, vol. 55, no. 1, pp. 74-83, 2012.
K. H. Choi, J. Heo, S. Kim, Y. J. Jeon, M. Oh, "Factors associated with breast and cervical cancer screening in Korea: data from a national community health survey", Asia Pacific Journal of Public Health, vol. 25, no. 6, pp. 476-86, 2013. DOI: https://doi.org/10.1177/1010539513506601

상세보기
W. Raghupathi, V. Raghupath, "Big data analytics in healthcare: promise and potential.", Health information science and systems, vol. 2, no. 1, pp. 3, 2014.

상세보기
R. Bellazzi, B. Zupan, "Predictive data mining in clinical medicine: current issues and guidelines", International journal of medical informatics, vol. 77, no. 2 pp. 81-97, Feb 29, 2008. DOI: https://doi.org/10.1016/j.ijmedinf.2006.11.006

상세보기
T. Chen, C. Guestrin, "Xgboost: A scalable tree boosting system.", In Proceedings of the 22nd ACM sigkdd international conference on knowledge discovery and data mining, pp. 785-794. ACM, 2016. DOI: https://doi.org/10.1145/2939672.2939785
I. Babajide Mustapha, F. Saeed, "Bioactive molecule prediction using extreme gradient boosting", Molecules, vol. 21, no. 8, pp. 983, Jul 28, 2016. DOI: https://doi.org/10.3390/molecules21080983

상세보기
L. Torlay, M. Perrone-Bertolotti, E. Thomas, M. Baciu, "Machine learning-XGBoost analysis of language networks to classify patients with epilepsy", Brain Informatics, vol. 22, no. 1, April, 2017.
A. M. Arymurthy, "Predicting the status of water pumps using data mining approach. InBig Data and Information Security (IWBIS)", International Workshop, IEEE, pp. 57-64, Oct, 2016. DOI: https://doi.org/10.1109/IWBIS.2016.7872890
P. Ajit, "Prediction of Employee Turnover in Organizations using Machine Learning Algorithms", algorithms, vol. 4, no. 5, pp. C5, 2016
M. Sokolova, G. Lapalme, "A systematic analysis of performance measures for classification tasks.", Information Processing & Management, vol. 31, no. 4, pp. 427-37, July, 2009. DOI: https://doi.org/10.1016/j.ipm.2009.03.002
B. T. Tran, B. Y. Jeong, J. K. Oh, "The prevalence trend of metabolic syndrome and its components and risk factors in Korean adults: results from the Korean National Health and Nutrition Examination Survey 2008-2013", BMC Public Health, vol. 1, no. 17, pp. 1-8, 2017. DOI: https://doi.org/10.1186/s12889-016-3936-6
R. Brooks, E. Group, "EuroQol: the current state of play", Health policy, vol. 37, no. 1, pp53-72, July, 1996. DOI: https://doi.org/10.1016/0168-8510(96)00822-6

상세보기
S. S. Park, Y. S. Yoon, S. W. Oh, "Health-related quality of life in metabolic syndrome: The Korea National Health and Nutrition Examination Survey 2005", diabetes research and clinical practice, vol. 91, no. 3, pp. 381-8, Mar 31, 2011.

상세보기
E. S. Ford, C. Li, "Metabolic syndrome and health-related quality of life among US adults", Annals of epidemiology, vol. 18, no. 3 pp. 165-71, Mar 31, 2008. DOI: https://doi.org/10.1016/j.annepidem.2007.10.009

상세보기

저자의 다른 논문 :

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증