Journal of the Korean Data and Information Science Society

The Korean Data and Information Science Society (한국데이터정보과학회)
권호 표지
DOI QR코드

DOI QR Code

Identification of major risk factors association with respiratory diseases by data mining

데이터마이닝 모형을 활용한 호흡기질환의 주요인 선별

  • Received : 2014.02.12
  • Accepted : 2014.03.10
  • Published : 2014.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Data mining is to clarify pattern or correlation of mass data of complicated structure and to predict the diverse outcomes. This technique is used in the fields of finance, telecommunication, circulation, medicine and so on. In this paper, we selected risk factors of respiratory diseases in the field of medicine. The data we used was divided into respiratory diseases group and health group from the Gyeongsangbuk-do database of Community Health Survey conducted in 2012. In order to select major risk factors, we applied data mining techniques such as neural network, logistic regression, Bayesian network, C5.0 and CART. We divided total data into training and testing data, and applied model which was designed by training data to testing data. By the comparison of prediction accuracy, CART was identified as best model. Depression, smoking and stress were proved as the major risk factors of respiratory disease.

데이터 마이닝이란 대량의 데이터나 복잡한 구조의 데이터들을 정교한 통계분석과 모델링 테크닉을 이용하여 정확히 식별되지 않는 패턴이나 자료간의 상관관계를 밝혀내어 여러 가지 결과를 예측해 내는 통계적 기법이다. 이러한 데이터 마이닝 기법은 금융, 통신, 유통, 의학 등 다양한 분야에 활용되는데, 본 연구에서는 의학 분야에 적용하여 호흡기질환에 영향을 끼치는 요인을 선별하였다. 분석은 2012년도 경상북도 지역사회건강조사에 참여한 사람 중 의사에게서 폐결핵, 천식, 알레르기성 비염을 진단받은 경험이 있는 호흡기질환군과 건강군으로 정리한 자료를 대상으로 하였다. 호흡기질환이 영향을 끼치는 주요인을 선별하기 위해 인공신경망, 로지스틱 회귀모형, 베이지안 네트워크, C5.0, CART 기법을 이용하였다. 공정한 모형 평가를 위해 전체 데이터를 훈련용 데이터와 검증용 데이터로 나누었고, 훈련용 데이터에서 설정된 모형을 검증용 데이터에 적용하여 정확도를 비교하였다. 그 결과 CART가 최적 모형으로 선정되었으며 CART의 의사결정나무를 통하여 우울감 인지 여부, 현재 흡연여부, 스트레스 인지 여부 순으로 호흡기질환에 영향을 주는 것으로 나타났다. 그리고 호흡기질환의 주요인들에 대한 오즈비를 구하여 개별적인 영향력에 대해서도 밝혔다.

Keywords

References

  1. Berry, M. and Linoff, G. (1997). Data mining techniques: For marketing, sales and customer support, Wiley, New York.
  2. Berry, M. and Linoff, G. (2011). Data mining techniques: For marketing, sales and customer relationship management, Wiley, New York.
  3. Berson, A., Smith, S. and Thearling, K. (2000). Building data mining applications for CRM, McGraw-Hill, New York.
  4. Breiman, L., Friedman, J. H., Olshen, R. and Stone, C. J. (1984). Classification and regression tree, Chapman & Hall, New York.
  5. Freund, Y. and Mason, L. (1999). The alternating decision tree learning algorithm. Proceedings of the Sixteenth International Conference on Machine Learning, 99, 121-133.
  6. Han, S. H., Park, J. S., Seo, S. H., Yoon, J. E. and Jee, S. H. (2005). Factors affecting the morbidity related to respiratory diseases in urban Korea. Journal of the Korea Gerontology Society, 28, 205-217.
  7. Heo, M. H. and Lee, Y. G. (2008). Data mining modeling and example, Hannarae, Seoul.
  8. Kim, N. M., Lee, W. K. and Park, J. Y. (2013). The ecological analysis of asthmatic occurrence in patients: Using the national health insurance data. Journal of the Korean Data & Information Science Society, 24, 679-688. https://doi.org/10.7465/jkdi.2013.24.4.679
  9. Kim, T. H. and Kim, Y. H. (2013). A study on the analysis of customer loan for the credit finance company using classification model. Journal of the Korean Data & Information Science Society, 24, 411-425. https://doi.org/10.7465/jkdi.2013.24.3.411
  10. Kim, W. J., Bae, H. S., Choi, B. K., Hwang, J. M., Shin, K. H., Kim, M. H., Lee, K. H., Kim, K. U., Jeon, D. S., Park, H. K., Kim, Y. S., Lee, M. K. and Park, S. K. (2010). Depressive conditions in relation to asthma severity and control. Tuberculosis and Respiratory Diseases, 69, 265-270. https://doi.org/10.4046/trd.2010.69.4.265
  11. Lee, J. W., Park, M. R. and Yoo, H. N. (2005). Statistical methods for life science research, Free Academy, Seoul.
  12. Park, I. S., Han, J. T., Sohn, H. S. and Kang, S. B. (2011). Developing the administrative model using the data mining technique for injury in National Health Insurance. Journal of the Korean Data & Information Science Society, 23, 467-476.
  13. Oraka, E., King, M. E. and Callahan, D. B. (2010). Asthma and serious psychological distress: Prevalence and risk factors among US adults, 2001-2007. CHEST Journal, 137, 609-616. https://doi.org/10.1378/chest.09-1777
  14. Quinlan, J. R. (1993). C4.5: Programs for machine learning, Morgan-Kaufmann Publishers, San Mateo, CA.
  15. Ryu, Y. J., Chun, E. M., Sim, Y. S. and Lee, J. H. (2007). Depression and anxiety in outpatients with chronic obstructive pulmonary disease. Tuberculosis and Respiratory Diseases, 62, 11-8. https://doi.org/10.4046/trd.2007.62.1.11
  16. Ryu, Y. J., Chun, E. M., Lee, J. H. and Chang, J. H. (2010). Prevalence of depression and anxiety in outpatients with chronic airway lung disease. Korean Journal of Internal Medicine, 25, 51-57. https://doi.org/10.3904/kjim.2010.25.1.51
  17. Sarle, W. S. (1994). Neural networks and statistical models. Proceedings of the 19th Annual SAS Users Group International Conference, 1-13.
  18. Tan, P., Steinbach, M. and Kumar, V. (2006). Introduction to data mining, Addison Wesley Longman, California, USA.
  19. Yohannes, A. M., Baldwin, R. C. and Connolly, M. J. (2000). Depression and anxiety in elderly outpatients with chronic obstructive pulmonary disease : Prevalence, and validation of the BASDEC screening questionnaire. International Journal of Geriatric Psychiatry, 15, 1090-1096. https://doi.org/10.1002/1099-1166(200012)15:12<1090::AID-GPS249>3.0.CO;2-L

Cited by

  1. The statistical factors affecting the freezing of the road pavement vol.27, pp.1, 2016, https://doi.org/10.7465/jkdi.2016.27.1.67
  2. Prevalence of allergic diseases and its related factors in Korean adolescents-Using data from the 2013 Korea youth risk behavior web-based survey vol.27, pp.1, 2016, https://doi.org/10.7465/jkdi.2016.27.1.155
  3. The effect of road weather factors on traffic accident - Focused on Busan area - vol.26, pp.3, 2015, https://doi.org/10.7465/jkdi.2015.26.3.661
  4. Effect on ambulatory dental visitation frequency according to pack-years of smoking vol.27, pp.2, 2016, https://doi.org/10.7465/jkdi.2016.27.2.419
  5. Classification of the Diagnosis of Diabetes based on Mixture of Expert Model vol.19, pp.11, 2014, https://doi.org/10.9708/jksci.2014.19.11.149
  6. Study on prediction for a film success using text mining vol.26, pp.6, 2015, https://doi.org/10.7465/jkdi.2015.26.6.1259
  7. A study on the correlation between upper airway diseases and urinary heavy metals concentration in household residents vol.17, pp.1, 2018, https://doi.org/10.15250/joie.2018.17.1.78
  8. Nomogram plot for predicting chronic otitis media in Korean adults vol.28, pp.4, 2014, https://doi.org/10.7465/jkdi.2017.28.4.899