| Peer-Reviewed

Osteoporosis Risk Predictive Model Using Supervised Machine Learning Algorithms

Received: 24 October 2017     Accepted: 9 November 2017     Published: 20 January 2018
Views:       Downloads:
Abstract

In this paper, we developed a model to forecast the risk of osteoporosis using supervised machine learning algorithm. The study identified the variables that were monitored by experts in determining osteoporosis risk, formulated and simulated the predictive model. The performance of the model validation was also performed. This was with a view of developing a predictive model for the classification of osteoporosis risk among patients in Nigeria. A review of extensive literature surrounding the body of knowledge of osteoporosis risk revealed the associated risk factors used were identified and validated by experts, while historical data explaining the relationship between the risk factors and osteoporosis risk was collected. The predictive model for osteoporosis risk was formulated using two (2) supervised machine learning algorithms, namely Naïve Bayes’ (NB) classifier and the Multi-layer Perceptron (MLP) based on the identified risk factors. The results of the identification and data collection showed that there were 20 risk factors identified including the CD4 count level stratified as low, moderate and high risk based on information collected from 45 patients in Nigerian hospitals. The results of the model validation using the 10-fold cross validation revealed that the MLP had the best performance with a value of 100% over the accuracy of NB with a value of 71.4%. The result further showed that the performance of the MLP over the NB was influenced by the ability of the complex nature of the perceptron network to model the problem of identifying the risk of osteoporosis from the values of the risk factors presented in the training dataset. The study concluded that a better understanding of the relationship between the variables will improve the ability of the experts to determine the risk of osteoporosis during the examination of patients.

Published in Science Research (Volume 5, Issue 6)
DOI 10.11648/j.sr.20170506.11
Page(s) 78-87
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), 2018. Published by Science Publishing Group

Keywords

Osteoporosis Risk Classification, Predictive Modeling, Machine Learning

References
[1] Moudani, W., Shahin, A., Chakik, F. and Rajab, D. (2011). Intelligent Predictive Osteoporosis System. International Journal of Computer Applications 32 (5): 28–37.
[2] Taylor, B. C., Schreiner, P. J. and Stone, K. L. (2004). Long-term prediction of incident hip fracture risk in elderly white women: study of osteoporotic fractures. American Journal of Geriatr Soc 52: 1479–1486.
[3] Kanis, J. A. and Johnell, O. (2005). Requirements for DXA for the management of osteoporosis in Europe. Osteoporosis International 16: 229–238.
[4] Moudani, W., Shahin, A., Chakik, F. and Mora-Camino, F. (2011a). Dynamic Rough Sets Features Reduction. International Journal of Computer Science and Information Security 9 (4): 1–12.
[5] Kanis, J. A., Johansson, H. and Johnell, O. (2005a). Alcohol intake as a risk factor for fracture. Osteoporosis International 16: 737–742.
[6] Idowu, P. A., Aladekomo, T. A., Williams, K. O. and Balogun, J. A. (2015). Predictive model for likelihood of Sickle cell aneamia (SCA) among pediatric patients using fuzzy logic. Transactions in networks and communications 31 (1): 31–44.
[7] Waijee, A., Mukherjee, A. and Singal, A. (2013). Comparison of modern imputation methods for missing laboratory data in medicine. BMJ Open 3 (8): 1–7.
[8] Megala, S. and Hemalatha, M. (2011). A Novel Data Mining Approach to Determine the Vanished Agricultural Land in Tamilnadu. International Journal of Computer Applications 23 (3): 23–28.
[9] Agbelusi, O. (2014). Development of a predictive model for survival of HIV/AIDS patients in South-western Nigeria, Unpublished MPhil Thesis, Obafemi Awolowo University, Ile-Ife, Nigeria.
[10] Kälvesten, J., Lui, L.-Y., Brismar, T. and Cummings, S. (2016). Digital X-Ray Radio-grammetry in the Study of Osteoporotic Fractures: Comparison to dual energy X-ray absorptiometry and FRAX. Bone 86: 30–35.
[11] Ordonez, C., Matias, J. M., de Cos Juez, J. F. and Garcia, P. J. (2009). Machine Learning Techniques applied to the Determination of Osteoporosis Incidence in Post-Menopausal Women. Journal of Mathematical and Computational Modeling 50: 673–679.
[12] Hseuh-Wei, C., Yu-Hsien, C., Hao-Yun, K., Cheng-Hing, Y. and Wen-Hsien, H. (2013). Comparison of Classification Algorithms with Wrapper-Based Feature Selection for Predicting Osteoporosis Outcome Based on Genetic Factors in a Taiwanese Women Population. International Journal of Endocrinology 2013: 1–8.
[13] Saranya, M. and Sarojimi, K. (2016). An Improved and Optimal Prediction of Bone Disease Based in Risk Factors. International Journal of Computer Science and Information Technologies 7 (2): 820–823.
Cite This Article
  • APA Style

    Egejuru Ngozi Chidozie, Mhambe Priscilla Dooshima, Balogun Jeremiah Ademola, Femi Komolafe, Idowu Peter Adebayo. (2018). Osteoporosis Risk Predictive Model Using Supervised Machine Learning Algorithms. Science Research, 5(6), 78-87. https://doi.org/10.11648/j.sr.20170506.11

    Copy | Download

    ACS Style

    Egejuru Ngozi Chidozie; Mhambe Priscilla Dooshima; Balogun Jeremiah Ademola; Femi Komolafe; Idowu Peter Adebayo. Osteoporosis Risk Predictive Model Using Supervised Machine Learning Algorithms. Sci. Res. 2018, 5(6), 78-87. doi: 10.11648/j.sr.20170506.11

    Copy | Download

    AMA Style

    Egejuru Ngozi Chidozie, Mhambe Priscilla Dooshima, Balogun Jeremiah Ademola, Femi Komolafe, Idowu Peter Adebayo. Osteoporosis Risk Predictive Model Using Supervised Machine Learning Algorithms. Sci Res. 2018;5(6):78-87. doi: 10.11648/j.sr.20170506.11

    Copy | Download

  • @article{10.11648/j.sr.20170506.11,
      author = {Egejuru Ngozi Chidozie and Mhambe Priscilla Dooshima and Balogun Jeremiah Ademola and Femi Komolafe and Idowu Peter Adebayo},
      title = {Osteoporosis Risk Predictive Model Using Supervised Machine Learning Algorithms},
      journal = {Science Research},
      volume = {5},
      number = {6},
      pages = {78-87},
      doi = {10.11648/j.sr.20170506.11},
      url = {https://doi.org/10.11648/j.sr.20170506.11},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sr.20170506.11},
      abstract = {In this paper, we developed a model to forecast the risk of osteoporosis using supervised machine learning algorithm. The study identified the variables that were monitored by experts in determining osteoporosis risk, formulated and simulated the predictive model. The performance of the model validation was also performed. This was with a view of developing a predictive model for the classification of osteoporosis risk among patients in Nigeria. A review of extensive literature surrounding the body of knowledge of osteoporosis risk revealed the associated risk factors used were identified and validated by experts, while historical data explaining the relationship between the risk factors and osteoporosis risk was collected. The predictive model for osteoporosis risk was formulated using two (2) supervised machine learning algorithms, namely Naïve Bayes’ (NB) classifier and the Multi-layer Perceptron (MLP) based on the identified risk factors. The results of the identification and data collection showed that there were 20 risk factors identified including the CD4 count level stratified as low, moderate and high risk based on information collected from 45 patients in Nigerian hospitals. The results of the model validation using the 10-fold cross validation revealed that the MLP had the best performance with a value of 100% over the accuracy of NB with a value of 71.4%. The result further showed that the performance of the MLP over the NB was influenced by the ability of the complex nature of the perceptron network to model the problem of identifying the risk of osteoporosis from the values of the risk factors presented in the training dataset. The study concluded that a better understanding of the relationship between the variables will improve the ability of the experts to determine the risk of osteoporosis during the examination of patients.},
     year = {2018}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Osteoporosis Risk Predictive Model Using Supervised Machine Learning Algorithms
    AU  - Egejuru Ngozi Chidozie
    AU  - Mhambe Priscilla Dooshima
    AU  - Balogun Jeremiah Ademola
    AU  - Femi Komolafe
    AU  - Idowu Peter Adebayo
    Y1  - 2018/01/20
    PY  - 2018
    N1  - https://doi.org/10.11648/j.sr.20170506.11
    DO  - 10.11648/j.sr.20170506.11
    T2  - Science Research
    JF  - Science Research
    JO  - Science Research
    SP  - 78
    EP  - 87
    PB  - Science Publishing Group
    SN  - 2329-0927
    UR  - https://doi.org/10.11648/j.sr.20170506.11
    AB  - In this paper, we developed a model to forecast the risk of osteoporosis using supervised machine learning algorithm. The study identified the variables that were monitored by experts in determining osteoporosis risk, formulated and simulated the predictive model. The performance of the model validation was also performed. This was with a view of developing a predictive model for the classification of osteoporosis risk among patients in Nigeria. A review of extensive literature surrounding the body of knowledge of osteoporosis risk revealed the associated risk factors used were identified and validated by experts, while historical data explaining the relationship between the risk factors and osteoporosis risk was collected. The predictive model for osteoporosis risk was formulated using two (2) supervised machine learning algorithms, namely Naïve Bayes’ (NB) classifier and the Multi-layer Perceptron (MLP) based on the identified risk factors. The results of the identification and data collection showed that there were 20 risk factors identified including the CD4 count level stratified as low, moderate and high risk based on information collected from 45 patients in Nigerian hospitals. The results of the model validation using the 10-fold cross validation revealed that the MLP had the best performance with a value of 100% over the accuracy of NB with a value of 71.4%. The result further showed that the performance of the MLP over the NB was influenced by the ability of the complex nature of the perceptron network to model the problem of identifying the risk of osteoporosis from the values of the risk factors presented in the training dataset. The study concluded that a better understanding of the relationship between the variables will improve the ability of the experts to determine the risk of osteoporosis during the examination of patients.
    VL  - 5
    IS  - 6
    ER  - 

    Copy | Download

Author Information
  • Department of Computer Science and Engineering, Obafemi Awolowo University, Ile-Ife, Nigeria

  • Department of Computer Science and Engineering, Obafemi Awolowo University, Ile-Ife, Nigeria

  • Department of Computer Science and Engineering, Obafemi Awolowo University, Ile-Ife, Nigeria

  • Engineering Materials Development Institute, Federal Ministry of Science & Technology, Akure, Nigeria

  • Department of Computer Science and Engineering, Obafemi Awolowo University, Ile-Ife, Nigeria

  • Sections