DOI QR코드

DOI QR Code

Developing the high-risk drinking predictive model in Korea using the data mining technique

데이터마이닝 기법을 활용한 한국인의 고위험 음주 예측모형 개발 연구

  • Park, Il-Su (Department of Health Management, Uiduk University) ;
  • Han, Jun-Tae (Department of Student Aid Policy Research, Korea Student Aid Foundation)
  • 박일수 (위덕대학교 보건관리학과) ;
  • 한준태 (한국장학재단 장학정책연구소)
  • Received : 2017.09.20
  • Accepted : 2017.11.02
  • Published : 2017.11.30

Abstract

In this paper, we develop the high-risk drinking predictive model in Korea using the cross-sectional data from Korea Community Health Survey (2014). We perform the logistic regression analysis, the decision tree analysis, and the neural network analysis using the data mining technique. The results of logistic regression analysis showed that men in their forties had a high risk and the risk of office workers and sales workers were high. Especially, current smokers had higher risk of high-risk drinking. Neural network analysis and logistic regression were the most significant in terms of AUROC (area under a receiver operation characteristic curve) among the three models. The high-risk drinking predictive model developed in this study and the selection method of the high-risk intensive drinking group can be the basis for providing more effective health care services such as hazardous drinking prevention education, and improvement of drinking program.

본 연구는 질병관리본부에서 실시한 전국 규모의 자료인 지역사회건강조사 2014년 자료를 이용하여 고위험 음주자들의 특성 및 요인을 파악하고 고위험 음주 예측모형을 개발했다. 예측모형 개발은 데이터마이닝 방법 중 로지스틱 회귀분석, 의사결정나무, 신경망 분석 3가지 방법을 적용했으며, 로지스틱 회귀분석의 주요 결과로는 40대 남자의 위험도가 높았고, 사무직과 판매서비스직의 위험도가 높았다. 특히 현재 흡연자인 경우 고위험 음주 위험도가 높았다. 3가지 방법 중 AUROC (area under a receiver operation characteristic curve) 측면에서 신경망 분석과 로지스틱 회귀분석이 가장 높게 나타났다. 또한 고위험 음주 예방을 위한 우선 관리 대상자를 선정함에 있어 신경망 분석과 로지스틱 회귀분석으로 개발된 예측모형의 사후확률을 기초로 두 가지 모형 모두 예측분포의 상위 10%인 집단에 해당되는 경우를 선정한 결과 신경망 분석이나 로지스틱 회귀모형 1가지 모형으로 적용하는 것보다 반응률 및 향상도가 다소 개선되는 것으로 나타났다. 본 연구에서 개발된 고위험 음주 예측모형과 우선 관리 대상자 선정 방법은 문제적 음주 예방 및 개선 교육, 절주 프로그램 개발 등에 보다 세분화되고 효과적인 건강관리 서비스를 제공을 위한 기초자료가 될 수 있을 것이다.

Keywords

References

  1. Byeon, H. (2015). Prediction modeling of high risk drinking in Korea using CRT method. Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology, 5, 99-108.
  2. Casswall, S. and Thamarangsi, T. (2009). Reducing the harm from alcohol: Call to action. Lancet, 373, 2247-2257. https://doi.org/10.1016/S0140-6736(09)60745-5
  3. Chavez, L. J., Williams, E. C., Lapham, G. and Bradley, K. A. (2012). Association between alcohol screening scores and alcohol related risk among female veterans affairs patients. Journal of Studies on Alcohol and Drugs, 73, 391-400. https://doi.org/10.15288/jsad.2012.73.391
  4. Chick, J. (1998). Alcohol health and the heart: implications for clinicians. Alcohol & Alcoholism, 33, 576-591. https://doi.org/10.1093/alcalc/33.6.576
  5. Chung, S. S. and Joung, K. H. (2012). Factors associated with the patterns of alcohol use in Korean adults. Korean Journal of Adult Nursing, 24, 441-453. https://doi.org/10.7475/kjan.2012.24.5.441
  6. Lee, J. K. (2014). Socio-demographic and geospatial factors influencing drinking. Mental Health and Social Work, 42, 143-173.
  7. Lee, E. K. and Park, J. H. (2016). The effects of drinking motives, refusal self-efficacy, and outcome expectancy on high risk drinking. Journal of the Korean Data and Information Science Society, 27, 1047-1057. https://doi.org/10.7465/jkdi.2016.27.4.1047
  8. Lee, H. K. and Roh, S. W. (2011). The relations of alcohol drinking behavior, depressive mood, and suicidal ideation among Korean adult. Journal of Korean Alcohol Science, 12, 155-168.
  9. Ryu, S. Y., Crespi, C. M. and Maxwell, A. E. (2013). Drinking patterns among Korean adults: Results of the 2009 Korean Community Health Survey. Journal of Preventive Mdicine and Public Health, 46, 183-191. https://doi.org/10.3961/jpmph.2013.46.4.183
  10. Kang, H. C., Han, S. T., Choi, J. H., Lee, S. G., Kim, E. S. and Um, I. H. (2014). Methodology of data mining for big data analysis: A case study on SAS Enterprise Miner, Free Academy, Seoul.
  11. Kim, M. K. (2012). A study on parents’ alcohol use, university students’ alcohol expectancy, and alcohol use disorder: Mediating effects on self-esteem and depression. Asian journal of Child Welfare and Development, 10, 61-80.
  12. Kim, M. K., Ko, M. J. and Han, J. T. (2010). Alcohol consumption and mortality from all-cause and cancers among 1.34 million Koreans: the results from the Korea national health insurance corporation's health examinee cohort in 2000. Cancer Causes Control, 21, 2295-2302. https://doi.org/10.1007/s10552-010-9656-9
  13. Kweon, G. Y. (2005). Factors influencing drinking of employees: focus on the white collar employees. Korean Journal of Social Welfare, 57, 93-118.
  14. Maskarinec, G., Meng, L. and Kolonel, L. N. (1998). Alcohol intake, body weight, and mortality in a multiethnic prospective cohort. Epidemiology, 9, 654-661.