Nutrition Research and Practice

The Korean Nutrition Society (한국영양학회)
권호 표지
DOI QR코드

DOI QR Code

Classification and prediction of the effects of nutritional intake on diabetes mellitus using artificial neural network sensitivity analysis: 7th Korea National Health and Nutrition Examination Survey

  • Kyungjin Chang (Department of Mechanical Engineering, Kyung Hee University) ;
  • Songmin Yoo (Department of Mechanical Engineering, Kyung Hee University) ;
  • Simyeol Lee (Department of Home Economics Education, Dongguk University)
  • Received : 2023.07.14
  • Accepted : 2023.09.20
  • Published : 2023.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

BACKGROUND/OBJECTIVES: This study aimed to predict the association between nutritional intake and diabetes mellitus (DM) by developing an artificial neural network (ANN) model for older adults. SUBJECTS/METHODS: Participants aged over 65 years from the 7th (2016-2018) Korea National Health and Nutrition Examination Survey were included. The diagnostic criteria of DM were set as output variables, while various nutritional intakes were set as input variables. An ANN model comprising one input layer with 16 nodes, one hidden layer with 12 nodes, and one output layer with one node was implemented in the MATLAB® programming language. A sensitivity analysis was conducted to determine the relative importance of the input variables in predicting the output. RESULTS: Our DM-predicting neural network model exhibited relatively high accuracy (81.3%) with 11 nutrient inputs, namely, thiamin, carbohydrates, potassium, energy, cholesterol, sugar, vitamin A, riboflavin, protein, vitamin C, and fat. CONCLUSIONS: In this study, the neural network sensitivity analysis method based on nutrient intake demonstrated a relatively accurate classification and prediction of DM in the older population.

Keywords

References

  1. Jung CH, Son JW, Kang S, Kim WJ, Kim HS, Kim HS, Seo M, Shin HJ, Lee SS, Jeong SJ, et al. Diabetes fact sheets in Korea, 2020: an appraisal of current status. Diabetes Metab J 2021;45:1-10.  https://doi.org/10.4093/dmj.2020.0254
  2. Chentli F, Azzoug S, Mahgoun S. Diabetes mellitus in elderly. Indian J Endocrinol Metab 2015;19:744-52.  https://doi.org/10.4103/2230-8210.167553
  3. American Diabetes Association. 6. Glycemic targets. Diabetes Care 2017;40:S48-56.  https://doi.org/10.2337/dc17-S009
  4. Ma Y, Olendzki B, Chiriboga D, Hebert JR, Li Y, Li W, Campbell M, Gendreau K, Ockene IS. Association between dietary carbohydrates and body weight. Am J Epidemiol 2005;161:359-67.  https://doi.org/10.1093/aje/kwi051
  5. Frimpong EA, Oluwasanmi A, Baagyere EY, Zhiguang Q. A feedforward artificial neural network model for classification and detection of type 2 diabetes. J Phys Conf Ser 2020;1734:012026. 
  6. Soh DCK, Ng EYK, Jahmunah V, Oh SL, Tan RS, Acharya UR. Automated diagnostic tool for hypertension using convolutional neural network. Comput Biol Med 2020;126:103999. 
  7. Zhang Q, Liu Y, Liu G, Zhao G, Qu Z, Yang W. An automatic diagnostic system based on deep learning, to diagnose hyperlipidemia. Diabetes Metab Syndr Obes 2019;12:637-45.  https://doi.org/10.2147/DMSO.S198547
  8. Isin A, Ozdalili S. Cardiac arrhythmia detection using deep learning. Procedia Comput Sci 2017;120:268-75.  https://doi.org/10.1016/j.procs.2017.11.238
  9. Wagner JM, Shimshak DG. Stepwise selection of variables in data envelopment analysis: procedures and managerial perspectives. Eur J Oper Res 2007;180:57-67.  https://doi.org/10.1016/j.ejor.2006.02.048
  10. Pizarroso J, Alfaya D, Portela J, Munoz A. Metric tools for sensitivity analysis with applications to neural networks. arXiv. Forthcoming 2023. 
  11. Nourani V, Fard MS. Sensitivity analysis of the artificial neural network outputs in simulation of the evaporation process at different climatologic regimes. Adv Eng Softw 2012;47:127-46.  https://doi.org/10.1016/j.advengsoft.2011.12.014
  12. Cao M, Alkayem NF, Pan L, Novak D. Advanced methods in neural networks-based sensitivity analysis with their applications in civil engineering. In: Rosa JLG, editor. Artificial Neural Networks. Rijeka: IntechOpen; 2016. p. 335-53.
  13. Delen D, Walker G, Kadam A. Predicting breast cancer survivability: a comparison of three data mining methods. Artif Intell Med 2005;34:113-27.  https://doi.org/10.1016/j.artmed.2004.07.002
  14. Gevrey M, Dimopoulos I, Lek S. Review and comparison of methods to study the contribution of variables in artificial neural network models. Ecol Modell 2003;160:249-64.  https://doi.org/10.1016/S0304-3800(02)00257-0
  15. Borzouei S, Soltanian AR. Application of an artificial neural network model for diagnosing type 2 diabetes mellitus and determining the relative importance of risk factors. Epidemiol Health 2018;40:e2018007. 
  16. Agliata A, Giordano D, Bardozzo F, Bottiglieri S, Facchiano A, Tagliaferri R. Machine learning as a support for the diagnosis of type 2 diabetes. Int J Mol Sci 2023;24:6775. 
  17. Liu Q, Zhou Q, He Y, Zou J, Guo Y, Yan Y. Predicting the 2-year risk of progression from prediabetes to diabetes using machine learning among Chinese elderly adults. J Pers Med 2022;12:1055. 
  18. World Health Organization. Classification of diabetes mellitus. Geneva: World Health Organization; 2019.
  19. Olaniyi EO, Adnan K. Onset diabetes diagnosis using artificial neural network. Int J Sci Eng Res 2014;5:754-9.
  20. Ebrahim OA, Derbew G. Application of supervised machine learning algorithms for classification and prediction of type-2 diabetes disease status in Afar regional state, Northeastern Ethiopia 2021. Sci Rep 2023;13:7779. 
  21. Niedbala G, Kurasiak-Popowska D, Piekutowska M, Wojciechowski T, Kwiatek M, Nawracala J. Application of artificial neural network sensitivity analysis to identify key determinants of harvesting date and yield of soybean (Glycine max [L.] merrill) cultivar augusta. Agriculture 2022;12:754. 
  22. Jeczmionek E, Kowalski PA. Input reduction of convolutional neural networks with global sensitivity analysis as a data-centric approach. Neurocomputing 2022;506:196-205.  https://doi.org/10.1016/j.neucom.2022.07.027
  23. Kowalski PA, Kusy M. Sensitivity analysis for probabilistic neural network structure reduction. IEEE Trans Neural Netw Learn Syst 2018;29:1919-32.  https://doi.org/10.1109/TNNLS.2017.2688482
  24. Franceschini S, Tancioni L, Lorenzoni M, Mattei F, Scardi M. An ecologically constrained procedure for sensitivity analysis of artificial neural networks and other empirical models. PLoS One 2019;14:e0211445. 
  25. Choi SK, Park CG. The study of blood glucose level prediction model using ballistocardiogram and artificial intelligence. J Digit Converg 2021;19:257-69. 
  26. Singla V, Singla S, Feizi S, Jacobs D. Low curvature activations reduce overfitting in adversarial training. Proceedings of the IEEE/CVF International Conference on Computer Vision; 2021 Oct 11-17; Montreal, Canada. Scarsdale (NY): Computer Vision Foundation; 2021. p. 16423-33.
  27. Guldogan E, Zeynep T, Ayca A, Colak C. Performance evaluation of different artificial neural network models in the classification of type 2 diabetes mellitus. J Cogn Syst 2020;5:23-32.
  28. Ryu KS, Lee SW, Batbaatar E, Lee JW, Choi KS, Cha HS. A deep learning model for estimation of patients with undiagnosed diabetes. Appl Sci 2020;10:421. 
  29. Pizarroso J, Portela J, Munoz A. NeuralSens: sensitivity analysis of neural networks. J Stat Softw 2022;102:1-36. https://doi.org/10.18637/jss.v102.i07