A Comparison Between Classification Algorithms for Postmenopausal Osteoporosis Prediction in Tunisian Population

  • Naoual GuannoniEmail author
  • Rim Sassi
  • Walid Bedhiafi
  • Mourad Elloumi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9832)


In this paper, we make an experimental study to compare the performances of different data mining classification algorithms for predicting osteoporosis in Tunisian postmenopausal women. This study aims to identify the best algorithms with the optimum classification parameters values and to determine the most important risk factors that have a significant impact on the osteoporosis occurrence. The obtained results show that Support Vector Machine (SVM) classifier and Artificial Neural Network (ANN) classifier give the best classification performances when dealing with the three bone statuses (normal, osteopenia, osteoporosis). On the other hand, the decision tree classifier C4.5 enables to extract the most important risk factors for osteoporosis occurrence. The selected risk factors are validated by biologists.


Data mining Classification algorithms comparison Optimum parameters Prediction Osteoporosis risk factors 


  1. 1.
    Iliou, T., Anagnostopoulos, C.N., Anastassopoulos, G.: Osteoporosis detection using machine learning techniques and feature selection. Int. J. Artif. Intell. Tools 23(05), 1450014 (2014)CrossRefGoogle Scholar
  2. 2.
    Masood, Z., Shahzad, S., Saqib, A., Khizer, A.: Osteopenia and osteoporosis; frequency among females. Prof. Med. J. 21, 477 (2014)Google Scholar
  3. 3.
    International osteoporosis foundation (IOF).
  4. 4.
    Kim, S.K., Yoo, T.K., Kim, D.W: Osteoporosis risk prediction using machine learning and conventional methods. In: Engineering in Medicine and Biology Society (EMBC 35th Annual International Conference of the IEEE), pp. 188–191 (2013)Google Scholar
  5. 5.
    Younesi, E.: A knowledge-based integrative modeling approach for in-silico identification of mechanistic targets in neurodegeneration with focus on Alzheimer’s disease. Ph.D., Universitäts-und Landesbibliothek Bonn (2014)Google Scholar
  6. 6.
    Chang, H.W., Chiu, Y.H., Kao, H.Y., Yang, C.H., Ho, W.H: Comparison of classification algorithms with wrapper-based feature selection for predicting osteoporosis outcome based on genetic factors in a taiwanese women population. Int. J. Endocrinol. (2013)Google Scholar
  7. 7.
    Yoo, T.K., Kim, S.K., Oh, E., Kim, D.W.: Risk prediction of femoral neck osteoporosis using machine learning and conventional methods. In: Rojas, I., Joya, G., Cabestany, J. (eds.) IWANN 2013, Part II. LNCS, vol. 7903, pp. 181–188. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  8. 8.
    Xu, Y., Li, D., Chen, Q., Fan, Y.: Full supervised learning for osteoporosis diagnosis using micro-CT images. Microsc. Res. Tech. 76(4), 333–341 (2013)CrossRefGoogle Scholar
  9. 9.
    Han, J., Kamber, M., Pei, J.: Data Mining: Concepts and Techniques: Concepts and Techniques. Elsevier, New York (2011)zbMATHGoogle Scholar
  10. 10.
    Mhamdi, F., Elloumi, M.: A new survey on knowledge discovery and data mining. In: RCIS, pp. 427–432 (2008)Google Scholar
  11. 11.
    Aleem, S., Capretz, L.F., Ahmed, F: Benchmarking machine learning technologies for software defect detection (2015). arXiv preprint arXiv:1506.07563
  12. 12.
  13. 13.
    Moudani, W., Shahin, A., Chakik, F., Rajab, D.: Intelligent predictive osteoporosis system. Int. J. Comput. Appl. (IJCA) 32(5), 28–37 (2011)Google Scholar
  14. 14.
    Sassi, R., Sahli, H., Souissi, C., Sellami, S., Ben Ammar El Gaaied, A.: Polymorphisms in VDR gene in Tunisian postmenopausal women are associated with osteopenia phenotype. Climacteric 18, 624–630 (2015)CrossRefGoogle Scholar
  15. 15.
    Sassi, R., Sahli, H., Souissi, C., El Mahmoudi, H., Zouari, B., ElGaaied, A.B.A., Ferrari, S.L.: Association of LRP5 genotypes with osteoporosis in Tunisian post-menopausal women. BMC Musculoskeletal Disorders 15(1), 144 (2014)CrossRefGoogle Scholar
  16. 16.
    Markov, Z., Russell, I.: An introduction to the weka data mining system. In: ACM SIGCSE Bulletin, vol. 38, pp. 367–368. ACM (2006)Google Scholar
  17. 17.
    Optimizing parameters. The University of WaikatoGoogle Scholar
  18. 18.
    Koblar, V.: Optimizing parameters for machine learning algorithm. Technical report, Jozef Stefan International postgraduate school (2012)Google Scholar
  19. 19.
    Wu, C.H., McLarty, J.W. (eds.): Neural networks and genome informatics, 1st edn. Elsevier, Amsterdam (2012)Google Scholar
  20. 20.
    Baskin, I., Tetko, I., Varnek, A.: Tutorial on machine learning, Part 1. In: Benchmarking of Different Machine Learning Regression Methods. (last visited January 21, 2016)
  21. 21.
    Ferrier, J.L., Bernard, A., Gusikhin, O., Madani, K. (eds.): Selected Papers from the International Conference on Informatics in Control Automation and Robotics 2006, vol. 283. Springer, Heidelberg (2014)zbMATHGoogle Scholar
  22. 22.
    Batsaikan, O., Ho, C.K., Singh, Y.P.: A genetic algorithm-based multi-class support vector machine for mongolian character recognition. INFOCOMP J. Comput. Sci. 8(1), 1–7 (2009)Google Scholar
  23. 23.
    Wang, Q., Zhang, L., Chi, M., Guo, J.: MTForest: ensemble decision trees based on multi-task learning. In: ECAI, pp. 122–126 (2008)Google Scholar
  24. 24.
    Amrani, M.: Surveillance et diagnostic d’une ligne de production par les réseaux de neurones artificiels. Ph.d., Université M’hamedBougara de Boumerdès (2010)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Naoual Guannoni
    • 1
    Email author
  • Rim Sassi
    • 2
  • Walid Bedhiafi
    • 2
  • Mourad Elloumi
    • 1
  1. 1.Laboratory of Technologies of Information and Communication and Electrical Engineering (LaTlCE), National Superior School of Engineers of Tunis (ENSIT)University of TunisTunisTunisia
  2. 2.LR05ES05 Laboratory of Genetic, Immunology and Human Pathologies (LGIPH), Faculty of Sciences of TunisUniversité de Tunis El ManarTunisTunisia

Personalised recommendations