Journal of Digital Convergence (디지털융복합연구)

The Society of Digital Policy and Management (한국디지털정책학회)
권호 표지
DOI QR코드

DOI QR Code

Development of T2DM Prediction Model Using RNN

RNN을 이용한 제2형 당뇨병 예측모델 개발

  • Jang, Jin-Su (BK21PLUS Program in Embodiment: Health-Society Interaction, Department of Health Science, Graduate School, Korea University) ;
  • Lee, Min-Jun (BK21PLUS Program in Embodiment: Health-Society Interaction, Department of Health Science, Graduate School, Korea University) ;
  • Lee, Tae-Ro (BK21PLUS Program in Embodiment: Health-Society Interaction, Department of Health Science, Graduate School, Korea University)
  • 장진수 (고려대학교 대학원 보건과학과 BK21플러스 인간생명-사회환경 상호작용융합사업단) ;
  • 이민준 (고려대학교 대학원 보건과학과 BK21플러스 인간생명-사회환경 상호작용융합사업단) ;
  • 이태노 (고려대학교 대학원 보건과학과 BK21플러스 인간생명-사회환경 상호작용융합사업단)
  • Received : 2019.05.15
  • Accepted : 2019.08.20
  • Published : 2019.08.28
Download PDF
⟨ Previous Next ⟩

Abstract

Type 2 diabetes mellitus(T2DM) is included in metabolic disorders characterized by hyperglycemia, which causes many complications, and requires long-term treatment resulting in massive medical expenses each year. There have been many studies to solve this problem, but the existing studies have not been accurate by learning and predicting the data at specific time point. Thus, this study proposed a model using RNN to increase the accuracy of prediction of T2DM. This work propose a T2DM prediction model based on Korean Genome and Epidemiology study(Ansan, Anseong Korea). We trained all of the data over time to create prediction model of diabetes. To verify the results of the prediction model, we compared the accuracy with the existing machine learning methods, LR, k-NN, and SVM. Proposed prediction model accuracy was 0.92 and the AUC was 0.92, which were higher than the other. Therefore predicting the onset of T2DM by using the proposed diabetes prediction model in this study, it could lead to healthier lifestyle and hyperglycemic control resulting in lower risk of diabetes by alerted diabetes occurrence.

제2형 당뇨병은 고혈당이 특징인 대사성 분비 장애로 여러 합병증을 야기하는 질병이며, 장기적인 치료가 필요하기 때문에 매년 많은 의료비를 지출한다. 이를 해결하기 위해 많은 연구들이 있어왔지만, 기존의 연구들은 한 시점에서의 데이터를 학습시켜 예측함으로써 정확도가 높지 않았다. 그래서 본 연구는 제2형 당뇨병 발생 예측에 대한 정확도를 높이기 위하여 RNN을 이용한 모델을 제안하였다. 본 모델을 개발하기 위해 한국인유전체역학조사 지역사회 코호트(안산 안성) 데이터를 이용하였으며, 시간의 흐름에 따른 데이터들을 모두 학습시켜 당뇨병 발생 예측모델을 만들었다. 예측 모델의 성능을 검증하기 위해 기존의 기계 학습 방법인 LR, k-NN, SVM과 정확도를 비교하였다. 비교한 결과 제안한 예측모델의 accuracy는 0.92, AUC는 0.92로 다른 기계 학습 방법보다 높은 정확도를 보였다. 따라서 본 연구에서 제안한 제2형 당뇨병 발생 예측 모델을 활용하여 발병을 조기 예측함으로써 생활습관 개선 및 혈당조절을 통해 당뇨병 발병을 예방하고 늦출 수 있을 것이다.

Keywords

References

  1. Z. Punthakee, R. Goldenberg & P. Katz. (2018). Definition, classification and diagnosis of diabetes, prediabetes and metabolic syndrome. Canadian journal of diabetes, 42, S10-S15.
  2. D. Atlas. (2015). International diabetes federation. IDF Diabetes Atlas, 7th edn. Brussels, Belgium: International Diabetes Federation.
  3. N. Cho, J. E. Shaw, S. Karuranga, Y. Huang, J. D. da Rocha Fernandes, A. W. Ohlrogge & B. Malanda. (2018). IDF Diabetes Atlas: Global estimates of diabetes prevalence for 2017 and projections for 2045. Diabetes research and clinical practice, 138, 271-281. https://doi.org/10.1016/j.diabres.2018.02.023
  4. Korea Centers for Disease Control. (2015). Korean national health and nutrition survey data. https://knkanes.cds.go.kr/
  5. I. Baik. (2019). Projection of Diabetes Prevalence in Korean Adults for the Year 2030 Using Risk Factors Identified from National Data. Diabetes & metabolism journal, 43(1), 90-96. https://doi.org/10.4093/dmj.2018.0043
  6. American Diabetes Association. (2004). Screening for type 2 diabetes. Diabetes care, 27(suppl 1), s11-s14. https://doi.org/10.2337/diacare.27.2007.S11
  7. J. L Gross, M. J. De Azevedo, S. P. Silveiro, L. H. Canani, M. L. Caramori & T. Zelmanovitz. (2005). Diabetic nephropathy: diagnosis, prevention, and treatment. Diabetes care, 28(1), 164-176. https://doi.org/10.2337/diacare.28.1.164
  8. J. Y. Lee et al. (2011). Development of a predictive model for type 2 diabetes mellitus using genetic and clinical data. Osong public health and research perspectives, 2(2), 75-82. https://doi.org/10.1016/j.phrp.2011.07.005
  9. A. M. Kanaya et al. (2005). Predicting the development of diabetes in older adults: the derivation and validation of a prediction rule. Diabetes Care, 28(2), 404-408. https://doi.org/10.2337/diacare.28.2.404
  10. J. Choi & Y. Suh. (2018). Deriving rules for identifying diabetic among individuals with metabolic syndrome. Journal of digital convergence, 16(11), 363-372. https://doi.org/10.14400/jdc.2018.16.11.363
  11. Y. M. Kim & S. H. Kang. (2015). Changes and determinants affecting on geographic variations in health behavior, prevalence of hypertension and diabetes in Korean. Journal of digital convergence, 13(11), 241-254. https://doi.org/10.14400/JDC.2015.13.11.241
  12. H. Y. Kim & H. S. Kim. (2018). Factors Affecting the Control of HbA1c in Type 2 Diabetic Patients. Journal of Convergence for Information Technology, 8(6), 75-84. https://doi.org/10.22156/CS4SMB.2018.8.6.075
  13. M. J. Lee, H. K. Kang & B. J. Seo. (2018). Correlation between Outpatient's Medical Adherence and National Insurance Types in the Type 2 Diabetes Mellitus. Journal of Convergence for Information Technology, 8(4), 9-14. https://doi.org/10.22156/CS4SMB.2018.8.4.009
  14. Z. C. Lipton, D. C. Kale, C. Elkan & R. Wetzel. (2015). Learning to diagnose with LSTM recurrent neural networks. arXiv preprint arXiv:1511.03677.
  15. E. Choi, M. T. Bahadori, A. Schuetz, W. F. Stewart & J. Sun. (2016, December). Doctor ai: Predicting clinical events via recurrent neural networks. In Machine Learning for Healthcare Conference (pp. 301-318).
  16. Y. S. Lee & S. S. Moon. (2011). The use of HbA1c for diagnosis of type 2 diabetes in Korea. The Korean Journal of Medicine, 80(3), 291-297.
  17. S. Hochreiter & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  18. A. Iyer, S Jeyalatha & R. Sumbaly. (2015) Diagnosis of Diabetes Using Classification Mining Techniques. International Journal of Data Mining & Knowledge Management Process (IJDKP), 5, 1-14. https://doi.org/10.5121/ijdkp.2015.5101]
  19. V. A. Kumari & R. Chitra. (2013). Classification of diabetes disease using support vector machine. International Journal of Engineering Research and Applications, 3(2), 1797-1801.
  20. A. Sarwar & V. Sharma. (2012). Intelligent Naive Bayes approach to diagnose diabetes Type-2. International Journal of Computer Applications, IJCA Special Edition Nov, 14-16.
  21. P. Venkatesan & S. Anitha. (2006). Application of a radial basis function neural network for diagnosis of diabetes mellitus. Current Science (00113891), 91(9), 1195-1199.
  22. X. H. Meng, Y. X. Huang, D. P. Rao, Q. Zhang & Q. Liu. (2013). Comparison of three data mining models for predicting diabetes or prediabetes by risk factors. The Kaohsiung journal of medical sciences, 29(2), 93-99. https://doi.org/10.1016/j.kjms.2012.08.016
  23. H. Temurtas, N. Yumusak & F. Temurtas. (2009). A comparative study on diabetes disease diagnosis using neural networks. Expert Systems with applications, 36(4), 8610-8615. https://doi.org/10.1016/j.eswa.2008.10.032
  24. R. Motka, V. Parmarl, B. Kumar & A. R. Verma. (2013, September). Diabetes mellitus forecast using different data mining techniques. In 2013 4th International Conference on Computer and Communication Technology (ICCCT) (pp. 99-103). IEEE.
  25. K. Polat & S. Gunes. (2007). An expert system approach based on principal component analysis and adaptive neuro-fuzzy inference system to diagnosis of diabetes disease. Digital Signal Processing, 17(4), 702-710. https://doi.org/10.1016/j.dsp.2006.09.005
  26. Z. Alhassan, A. S. McGough, R. Alshammari, T. Daghstani, D. Budgen & N. Al Moubayed. (2018). Type-2 diabetes mellitus diagnosis from time series clinical data using deep learning models. In International Conference on Artificial Neural Networks. p468-478.