| Peer-Reviewed

Application of Artificial Neural Network and Binary Logistic Regression in Detection of Diabetes Status

Published: 10 March 2013
Views:       Downloads:
Abstract

Various methods can be applied to build predictive models for the clinical data with binary outcome variables. This research aims to compare and explore the process of constructing common predictive models. Models based on an artificial neural network (the multilayer perceptron) and binary logistic regression were applied and compared in their ability to classifying disease-free subjects and those with diabetes mellitus(DM) diagnosed by glucose level. Demographic, enth-ropometric and clinical data were collected based on a total of 460 participants aged over 30 years from six villages in Bangladesh that were identified as mainly dependent on wells contaminated with arsenic. Out of 460 participants 133 (28.91%) suffered from DM, 116 (25.27%) had impaired glucose tolerance (IGT) and the remainder 211 (45.86%) were disease free. Among other factors, family history of diabetes and arsenic exposure were found as significant risk factors for developing diabetes mellitus (DM), with a higher value of odds ratio. This study shows that, binary logistic regression correctly classified 73.79% of cases with IGT or DM in the training datasets, 70.96% in testing datasets and 70.4% of all subjects. On the other hand, the sensitivities of artificial neural network architecture for training and testing datasets and for all subjects were 83.4%, 82.25% and 84.33% respectively, indicate better performance than binary logistic regression model.

Published in Science Journal of Public Health (Volume 1, Issue 1)
DOI 10.11648/j.sjph.20130101.16
Page(s) 39-43
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2013. Published by Science Publishing Group

Keywords

Artificial Neural Network (ANN), Binary Logistic (LR), Classification, Diabetes Mellitus (DM)

References
[1] Y. L. Eldon, "Artificial Neural Networks and Their Business Applications", Inf and Mang, 1994, 27(5): 303-313.
[2] S. S. Warren, "Neural Networks and Statistical Models", Preceedings of the 19the Annual SAS Users Group International conference, April 1994, USA.
[3] A. A. Betanzos, "Applying statistical uncertainty-based and connectionist approaches to the prediction of fetal outcome: a comparative study," Arti Intelli in Med, 1999, 17(1): 37-57.
[4] P. J. A. Lisboa,"A review of evidence of health benefit from artificial neural networks in medical intervention," Neural Networks, 2002, 15: 11-39.
[5] Y. C. Li, W. T. Chui, W. S. Jian, "Neural networks modeling for surgical decisions on traumatic brain injury patients," Int J Med Info, 2000, 57: 389-405.
[6] W. B. Schwartz, "Medicine and the computer: the promise and problems of change," New England Journal of Medicine, 1970, 283: 1257-64.
[7] E. H. Shortliffe, "The edolesence of Al in medicine: will the field come of age in the ‘90s?," Arti Intelli in Med, 1993, 5(2): 93-106.
[8] J. Park, D. E. Edington, "A sequential neural network model for diabetes prediction," Arti Intelli in Med, 2001, 23(3): 277-93.
[9] U. Ergun, "Classification of carotid artery stenosis of patients with diabetes by neural networks and logistic regression," Comp in Bio and Med, 2004, 34: 389-405.
[10] F. Rosenblatt, "The perceptron: a perceiving and recognizing automation," Cornell Aeronautical Laboratory report 85-460-I. Ithaca, New York, Cornell Aeronautical Laboratory, 1957.
[11] C. M. Bishop, "Neural networks for pattern recognition," 4th edition. Oxford, Oxford University Press, 1995.
[12] A. L. Ronco, "Use of artificial neural networks in modeling associations of discriminant factors: towards an intelligent selective breast cancer screening," Arti Intelli in Med, 1999, 16(30): 299-309.
[13] R. L. Kennedy, "An artificial neural network system for diagnosis of AMI in the accident and emergency department: evaluation and comparison with serum myoglobin measurements," Comp Meth and Prog in Bio, 1997, 52(2): 93-103.
[14] S. S. Cross, "Image analysis of low magnification images of fine needle aspirates of the breast produces useful discrimination between benign and malignant cases," Cytopathology, 1997, 8: 265-73.
[15] R. Dybowski, and V. Gant, "Artificial neural network in pathology and medical laboratories," Lancet, 1995, 346: 1203-7.
[16] P. Lapuerta, S. Rajan, and M. Bonacini, "Neural networks of outcomes in alcoholic patients with severe liver disease," Hepathology, 1997, 25: 302-306.
[17] P. J. A. Lisboa, "A Bayesian neural networks approach for modeling censored data with an application to prognosis after surgery for breast cancer," Arti Intelli in Med, 2003, 28(1): 1-25.
[18] E. Tafeit, "The determination of three subcutaneous adipose tissue compartments in non-insulin-dependent diabetes mellitus women with artificial neural networks and factor analysis," Arti Intelli in Med, 1999, 17: 181-193.
[19] M. Rahman, M. Tondel, I. A. Chowdhury, and O. Axelson, "Relations between exposure to arsenic, skin lesions, and glucosuria," Occup Env Meth, 1999, 56: 277-281.
[20] P. Bangla, and J. Kaiser, "India’s spreading health crisis draws global arsenic experts," Science , 1996, 274: 174-175.
[21] R. A. DeFronzo, R. C. Bonadonna., and E. Ferrannini, Pathogenesis of NIDDM. In: Alberti, K.G.M.M., Zimmet, P., DeFronzo, R.A., Keen, H. (Eds.), "International Test book of Diabetes Mellitus," 2nd edition. Wiley, New York, 1997, pp. 635-711.
[22] C. H. Tseng, C. P. Tseng, H. Y. Chiou, Y. M. Hsueh, C. K. Chong, and C. J. Chen," Epidemiologic evidence of diabetogenic effect of arsenic," Toxicology Letters, 2002, 133(1): 69-76.
[23] M. Rahman, M. Tondel, S. A. Ahmed, and O. Azelson, "Diabetes mellitus associated with arsenic exposure in Bangladesh", Am J of Epi, 1996, 148: 196-203.
[24] A. Kazemnejad, Z. Batvandi and J. Faradmal. "Comparison of artificial neural network and binary logistics regression for determination of impaired glucose tolerance/diabetes", Eastern Mediterranean Health Journal, 2010, 16(6):615-630.
[25] M. S. Lai, Y. M. Hsueh., C. J. Chen, et al. ., "Ingested inorganic arsenic and prevalence of diabetes mellitus," Am J of Epidemiol, 1994, 139: 484-492.
[26] M. Rahman, M. Tondel, S. A. Ahmed, and O. Azelson, "Diabetes mellitus associated with arsenic exposure in Bangladesh,"Am J of Epidemiol, 1998, 148: 198-203.
Cite This Article
  • APA Style

    Azizur Rahman, Karimon Nesha, Mariam Akter, Md. Sheikh Giash Uddin. (2013). Application of Artificial Neural Network and Binary Logistic Regression in Detection of Diabetes Status. Science Journal of Public Health, 1(1), 39-43. https://doi.org/10.11648/j.sjph.20130101.16

    Copy | Download

    ACS Style

    Azizur Rahman; Karimon Nesha; Mariam Akter; Md. Sheikh Giash Uddin. Application of Artificial Neural Network and Binary Logistic Regression in Detection of Diabetes Status. Sci. J. Public Health 2013, 1(1), 39-43. doi: 10.11648/j.sjph.20130101.16

    Copy | Download

    AMA Style

    Azizur Rahman, Karimon Nesha, Mariam Akter, Md. Sheikh Giash Uddin. Application of Artificial Neural Network and Binary Logistic Regression in Detection of Diabetes Status. Sci J Public Health. 2013;1(1):39-43. doi: 10.11648/j.sjph.20130101.16

    Copy | Download

  • @article{10.11648/j.sjph.20130101.16,
      author = {Azizur Rahman and Karimon Nesha and Mariam Akter and Md. Sheikh Giash Uddin},
      title = {Application of Artificial Neural Network and Binary Logistic Regression in Detection of Diabetes Status},
      journal = {Science Journal of Public Health},
      volume = {1},
      number = {1},
      pages = {39-43},
      doi = {10.11648/j.sjph.20130101.16},
      url = {https://doi.org/10.11648/j.sjph.20130101.16},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sjph.20130101.16},
      abstract = {Various methods can be applied to build predictive models for the clinical data with binary outcome variables. This research aims to compare and explore the process of constructing common predictive models. Models based on an artificial neural network (the multilayer perceptron) and binary logistic regression were applied and compared in their ability to classifying disease-free subjects and those with diabetes mellitus(DM) diagnosed by glucose level. Demographic, enth-ropometric and clinical data were collected based on a total of 460 participants aged over 30 years from six villages in Bangladesh that were identified as mainly dependent on wells contaminated with arsenic. Out of 460 participants 133 (28.91%) suffered from DM, 116 (25.27%) had impaired glucose tolerance (IGT) and the remainder 211 (45.86%) were disease free. Among other factors, family history of diabetes and arsenic exposure were found as significant risk factors for developing diabetes mellitus (DM), with a higher value of odds ratio. This study shows that, binary logistic regression correctly classified 73.79% of cases with IGT or DM in the training datasets, 70.96% in testing datasets and 70.4% of all subjects. On the other hand, the sensitivities of artificial neural network architecture for training and testing datasets and for all subjects were 83.4%, 82.25% and 84.33% respectively, indicate better performance than binary logistic regression model.},
     year = {2013}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Application of Artificial Neural Network and Binary Logistic Regression in Detection of Diabetes Status
    AU  - Azizur Rahman
    AU  - Karimon Nesha
    AU  - Mariam Akter
    AU  - Md. Sheikh Giash Uddin
    Y1  - 2013/03/10
    PY  - 2013
    N1  - https://doi.org/10.11648/j.sjph.20130101.16
    DO  - 10.11648/j.sjph.20130101.16
    T2  - Science Journal of Public Health
    JF  - Science Journal of Public Health
    JO  - Science Journal of Public Health
    SP  - 39
    EP  - 43
    PB  - Science Publishing Group
    SN  - 2328-7950
    UR  - https://doi.org/10.11648/j.sjph.20130101.16
    AB  - Various methods can be applied to build predictive models for the clinical data with binary outcome variables. This research aims to compare and explore the process of constructing common predictive models. Models based on an artificial neural network (the multilayer perceptron) and binary logistic regression were applied and compared in their ability to classifying disease-free subjects and those with diabetes mellitus(DM) diagnosed by glucose level. Demographic, enth-ropometric and clinical data were collected based on a total of 460 participants aged over 30 years from six villages in Bangladesh that were identified as mainly dependent on wells contaminated with arsenic. Out of 460 participants 133 (28.91%) suffered from DM, 116 (25.27%) had impaired glucose tolerance (IGT) and the remainder 211 (45.86%) were disease free. Among other factors, family history of diabetes and arsenic exposure were found as significant risk factors for developing diabetes mellitus (DM), with a higher value of odds ratio. This study shows that, binary logistic regression correctly classified 73.79% of cases with IGT or DM in the training datasets, 70.96% in testing datasets and 70.4% of all subjects. On the other hand, the sensitivities of artificial neural network architecture for training and testing datasets and for all subjects were 83.4%, 82.25% and 84.33% respectively, indicate better performance than binary logistic regression model.
    VL  - 1
    IS  - 1
    ER  - 

    Copy | Download

Author Information
  • Department of Statistics, Jagannath University, Dhaka-1100, Bangladesh

  • Department of Disaster management, University of Dhaka, 2School of Business, United International

  • Department of Disaster management, University of Dhaka, 2School of Business, United International

  • Department of Statistics, Jagannath University, Dhaka-1100, Bangladesh

  • Sections