Optimization the initial weights of artificial neural networks via genetic algorithm applied to hip bone fracture prediction

Article English OPEN
Chang, Y-T ; Lin, J ; Shieh, J-S ; Abbod, MF (2012)
  • Publisher: Hindawi Publishing Corporation
  • Journal: (issn: 1687-7101, eissn: 1687-711X)
  • Related identifiers: doi: 10.1155/2012/951247
  • Subject: Hip bone fracture prediction | Artificial neural networks (ANNs) | Electrical engineering. Electronics. Nuclear engineering | TK1-9971 | Computer software | Article Subject | QA76.75-76.765 | Genetic algorithms (GA)

This paper aims to find the optimal set of initial weights to enhance the accuracy of artificial neural networks (ANNs) by using genetic algorithms (GA). The sample in this study included 228 patients with first low-trauma hip fracture and 215 patients without hip fracture, both of them were interviewed with 78 questions. We used logistic regression to select 5 important factors (i.e., bone mineral density, experience of fracture, average hand grip strength, intake of coffee, and peak expiratory flow rate) for building artificial neural networks to predict the probabilities of hip fractures. Three-layer (one hidden layer) ANNs models with back-propagation training algorithms were adopted. The purpose in this paper is to find the optimal initial weights of neural networks via genetic algorithm to improve the predictability. Area under the ROC curve (AUC) was used to assess the performance of neural networks. The study results showed the genetic algorithm obtained an AUC of 0.858±0.00493 on modeling data and 0.802 ± 0.03318 on testing data. They were slightly better than the results of our previous study (0.868±0.00387 and 0.796±0.02559, resp.). Thus, the preliminary study for only using simple GA has been proved to be effective for improving the accuracy of artificial neural networks. This research was supported by the National Science Council (NSC) of Taiwan (Grant no. NSC98-2915-I-155-005), the Department of Education grant of Excellent Teaching Program of Yuan Ze University (Grant no. 217517) and the Center for Dynamical Biomarkers and Translational Medicine supported by National Science Council (Grant no. NSC 100- 2911-I-008-001).
  • References (31)
    31 references, page 1 of 4

    Johnell, O., Kanis, J. A.. An estimate of the worldwide prevalence and disability associated with osteoporotic fractures. Osteoporosis International. 2006; 17 (12): 1726-1733

    Cooper, C., Atkinson, E. J., Jacobsen, S. J., O'Fallon, W. M., Melton, L. J.. Population-based study of survival after osteoporotic fractures. American Journal of Epidemiology. 1993; 137 (9): 1001-1005

    Leibson, C. L., Tosteson, A. N. A., Gabriel, S. E., Ransom, J. E., Melton, L. J.. Mortality, disability, and nursing home use for persons with and without hip fracture: a population-based study. Journal of the American Geriatrics Society. 2002; 50 (10): 1644-1650

    Magaziner, J., Lydick, E., Hawkes, W., Fox, K. M., Zimmerman, S. I., Epstein, R. S., Hebel, J. R.. Excess mortality attributable to hip fracture in White women aged 70 years and older. American Journal of Public Health. 1997; 87 (10): 1630-1636

    Keene, G. S., Parker, M. J., Pryor, G. A.. Mortality and morbidity after hip fractures. British Medical Journal. 1993; 307 (6914): 1248-1260

    Jette, A. M., Harris, B. A., Cleary, P. D., Campion, E. W.. Functional recovery after hip fracture. Archives of Physical Medicine and Rehabilitation. 1987; 68 (10): 735-740

    Shawe-Taylor, J., Bartlett, P. L., Williamson, R. C., Anthony, M.. Structural risk minimization over data-dependent hierarchies. IEEE Transactions on Information Theory. 1998; 44 (5): 1926-1940

    Campbell, C.. Kernel methods: a survey of current techniques. Neurocomputing. 2002; 48: 63-84

    Shawe-Taylor, J., Sun, S.. A review of optimization methodologies in support vector machines. Neurocomputing. 2011; 74 (17): 3609-3618

    Chou, Y. C.. Predicting the risk of hip bone fracture for elders in Taiwan by ensemble back-propagation neural networks, BS thesis. 2009

  • Metrics
    No metrics available
Share - Bookmark