Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

Classification of the Diagnosis of Diabetes based on Mixture of Expert Model

Mixture of Expert 모형에 기반한 당뇨병 진단 분류

  • Lee, Hong-Ki (Department of Management, Jungwon University) ;
  • Myoung, Sung-Min (Department of Medical Information and Administration, Jungwon University)
  • 이홍기 (중원대학교 경영학과) ;
  • 명성민 (중원대학교 의료정보행정학과)
  • Received : 2014.10.13
  • Accepted : 2014.11.13
  • Published : 2014.11.29
Download PDF
⟨ Previous Next ⟩

Abstract

Diabetes is a chronic disease that requires continuous medical care and patient-self management education to prevent acute complications and reduce the risk of long-term complications. The worldwide prevalence and incidence of diabetes mellitus are reached epidemic proportions in most populations. Early detection of diabetes could help to prevent its onset by taking appropriate preventive measures and managing lifestyle. The major objective of this research is to develop an automated decision support system for detection of diabetes using mixture of experts model. The performance of the classification algorithms was compared on the Pima Indians diabetes dataset. The result of this study demonstrated that the mixture of expert model achieved diagnostic accuracies were higher than the other automated diagnostic systems.

당뇨병은 급성합병증을 예방하고 장기간의 합병증의 위험도를 감소하기 위하여 지속적인 치료와 환자 자가 관리 교육이 필요한 만성질환이다. 또한 전 세계적으로 당뇨병에 대한 유병률과 사망률이 대부분의 인구집단에서 역학적 비율에 도달하였다. 많은 연구에서 당뇨병에 대한 조기진단은 적절한 치료와 생활습관을 지키는 관리를 통하여 발병을 예방하는데 도움을 줄 수 있으며, 이를 통하여 당뇨병의 합병증을 감소시키고 생존률을 향상시킬 수 있다고 보고하고 있다. 본 연구는 PIMA Indians 당뇨 데이터에 대하여 mixture of expert 모형을 적용하여 당뇨유병환자의 여부를 분류하고, 이를 로지스틱 회귀분석, 신경망분석의 성능과 비교함으로서 그 유용성을 주장하고자 하였다. 연구결과 정확도 및 ROC 곡선, c-통계량에서 ME 모형이 다른 분류도구들에 비해서 높게 나타남을 확인할 수 있었다.

Keywords

References

  1. Georg, P., Ludvik, B., "Lipids and diabetes", Journal of Clinical and Basic Cardiology, Vol. 3, No. 3, pp. 159-162, 2000.
  2. Korean National Health and Nutrition Survey, http://knhanes.cdc.go.kr
  3. Statistics Korea, "Annual report on the cause of death statistics: 2012", Statistics Korea, 2013
  4. Kim, Y., Chang, D., Kim, S., Park, I., Kang, S., "A study on factors management of diabetes mellitus using data mining", Journal of academia-industrial technology, Vol. 10, No. 5, pp. 1100-1108, 2009.
  5. Diabetes Control and Complications Trial Research Group, "The effect of intensive treatment of diabetes on the development and progression of long-term complications in insulin-dependent diabetes mellitus", New England Journal of Medicine, Vol. 329, pp. 977-986, 1995.
  6. Holman, R., Paul, S., Bethel, M., Matthews, D., Neil, H., "10-year follow-up of intensive glucose control in type 2 diabetes", New England Journal of Medicine, Vol. 359, No. 15, pp.1577-1589, 2008. https://doi.org/10.1056/NEJMoa0806470
  7. Sokol, M., McGuigan, K., Verbrugge, R., Epstein, R., "Impact of medication adherence on hospitalization risk and healthcare cost", Medical Care, Vol. 43, No. 6, pp. 521-530, 2005. https://doi.org/10.1097/01.mlr.0000163641.86870.af
  8. Hwang, S., Kim, D., Kang, T., Park, G., "Medical diagnosis system of breast cancer using FCMbased parallel neural networks", In Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence, pp. 712-719, 2007.
  9. Shortliffe, E., Cimino J., "Biomedical Informatics: computer applications in health care and biomedicine", Springer-Verlag: New York, pp. 76-79, 2013.
  10. Kim, S., Kim, D., "Rhythm classification of ECG signal by rule and SVM based algorithm", Journal of the Korea Society of Computer and Information, Vol. 18, No. 9, 2013. https://doi.org/10.9708/jksci.2013.18.9.043
  11. Lee, J., Kim, H., "Identification of major risk factors association with respiratory diseases by data mining", Journal of the Korean data and information science society, Vol. 25, No. 2, pp. 373-384, 2014. https://doi.org/10.7465/jkdi.2014.25.2.373
  12. Lee, S., "Comparisons of predictive modeling techniques for breast cancer in Korean women", Journal of Korean Society of Medical Informatics, Vol. 14, No. 1, pp. 37-44, 2008.
  13. Ubeyli, E,. "A mixture of experts network structure for breast cancer diagnosis", Journal of medical systems, Vol. 29, pp. 5569-5579, 2005.
  14. Chen, H., Liu, D., Yang, B., Liu, J., Wang, G., "A new hybrid method based on local fisher discriminant analysis and support vector machines for hepatitis disease diagnosis", Expert systems with applications, Vol. 38, No. 9, pp. 11796-11803, 2011. https://doi.org/10.1016/j.eswa.2011.03.066
  15. Sakai, S., Kobayashi, K., Nakamura, J., Toyabe, S., Akazawa, K., "Accuracy in the diagnostic prediction of acute appendicitis based on the bayesian network model", Methods of information in medicine, Vol. 46, No. 6, pp. 723-726, 2007.
  16. Jacobs, R., Jordan, M., Nowlan, S., Hinton, G., "Adaptive mixture of local experts", Neural compuation, Vol. 3, pp. 179-87, 1991. https://doi.org/10.1162/neco.1991.3.2.179
  17. Gutta, S., Huang, J., Jonathon, P., Wechsler, H., "Mixture of experts for classification of gender, ethnic origin, and pose of human faces", Neural Networks, IEEE Transactions on, Vol. 11, No. 4, pp. 948-960, 2000. https://doi.org/10.1109/72.857774
  18. Le Cao, K., Meugnier, E., McLachlan, G., "Integrative mixture of experts to combine clinical factors and gene markers", Bioinformatics, Vol. 26, No. 9, pp. 1192-1198, 2010. https://doi.org/10.1093/bioinformatics/btq107
  19. Hu, Y., Palreddy, S., Tompkins, W., "A patient-adaptable ECG beat classifier using a mixture of experts approach", Biomedical Engineering, IEEE Transactions on, Vol. 44, No. 9, pp. 891-900, 1997. https://doi.org/10.1109/10.623058
  20. Smith, J., Everhart, J., Dickson, W., Knowler, W., Johannes, R., "Using the ADAP learning algorithm to forecast the onset of diabetes mellitus", Proc Annu Symp Comput Appl Med Care, Vol. 9, pp. 261-265, 1988.
  21. UCI Machine Learning Repository. University of California, Center for Machine Learning and Intelligent Systems, http://archive.ics.uci.edu/ml/datasets.html
  22. Hong, X., Harris, C., "A mixture of experts network structure construction algorithm for modelling and control", Applied Intelligence, Vol. 16, pp. 159-169, 2002. https://doi.org/10.1080/08839510252824553
  23. Jordan, M., Jacobs, R., "Hierarchical mixture of experts and the EM algorithm", Neural Computation, Vol. 6, pp. 2181-2214, 1994.
  24. Lee, J., "Data mining using R, SAS, MS-SQL", Free Academy, pp. 172-173, 2011.
  25. Bradley, A., "The use of the area under the ROC curve in the evaluation of machine learning algorithms", Pattern recognition, Vol. 30, No. 7, pp. 1145-1159, 1997. https://doi.org/10.1016/S0031-3203(96)00142-2
  26. Venables, W., Ripley, B., "Modern applied statistics with S", Springer: New York, pp. 245-250, 2002.
  27. Ubeyli, E., "Comparisons of different classification algorithms in clinical decision-making", Expert System, Vol. 24, pp. 117-131, 2007.
  28. Shankaracharya, Odedra, D., Samanta, S., Vidyarthi, A., "Computational Intelligencebased diagnosis tool for the detection of prediabetes and type 2 diabetes in India", The review of diabetic studies, Vol. 9, No. 1, pp. 55-62, 2012. https://doi.org/10.1900/RDS.2012.9.55
  29. Brause, R., "Medical analysis and diagnosis by neural networks", Lecture note in computer science, Vol. 99, pp. 1-13, 2001.
  30. Shanker, M,. "Using neural networks to predict the onset of diabetes mellitus", Journal of chemical information and computer sciences, Vol. 36, pp. 35-41, 1996. https://doi.org/10.1021/ci950063e
  31. Lim, C., Harrison, R., Kennedy, R., "Application of autonomous neural network system to medical pattern classification tasks", Artificial intelligence in medicine, Vol. 11, No.3, pp. 215-239, 1997. https://doi.org/10.1016/S0933-3657(97)00035-3
  32. Ubeyli, E., "Combining neural network models for automated diagnostic systems", Journal of medical systems, Vol. 30, pp. 6483-6488, 2006.
  33. Lee, H., Park J., "Probabilistic filtering for a biological knowledge discovery system with text mining and automatic inference", Journal of the Korean data and information science society, Vol. 17, No. 2, pp. 139-147, 2012. https://doi.org/10.9708/jksci.2012.17.2.139
  34. Min, D., "Comparison of neural network modeling and logistic regression based on pattern analysis of customer using SAS E-Miner", Journal of Korean Data Analysis Society, Vol. 9, No. 4, pp. 1861-1873, 2007.
  35. Lim, J., Sohn, J., Sohn, J., Lim, D., "Breast cancer classification using optimal support vector machine", Journal of the Korea Society of Health Informatics and Statistics, Vol. 38, No. 1, pp. 108-121, 2013.
  36. Subasi, A., "EEG signal classification using wavelet feature extraction and mixture of expert model", Expert system and applications, Vol. 32, pp. 1084-1093, 2007. https://doi.org/10.1016/j.eswa.2006.02.005
  37. Kurnik, R., Oliver, J., Waterhouse, S., Dunn, T., Jaylakshmi, Y., Lesho, M., Lopatin, M., Tamada, J., Wei, C., Potts, R., "Application of the mixtures of experts algorithm for signal processing in a noninvasive glucose monitoring system", Sensors and actuators B, Vol. 60, pp. 19-26, 1999. https://doi.org/10.1016/S0925-4005(99)00239-7
  38. Corchado, JM., Paz, J., Rodriguez, S., Bajo, J., "Model of experts for decision support in the diagnosis of leukemia patients", Artificial intelligence in medicine, Vol. 46, pp. 179-200, 2009. https://doi.org/10.1016/j.artmed.2008.12.001