Abstract
This paper illustrates the use of combined neural network (CNN) models to guide model selection for diagnosis of internal carotid arterial (ICA) disorders. The ICA Doppler signals were decomposed into time-frequency representations using discrete wavelet transform and statistical features were calculated to depict their distribution. The first level networks were implemented for the diagnosis of ICA disorders using the statistical features as inputs. To improve diagnostic accuracy, the second level network was trained using the outputs of the first level networks as input data. The CNN models achieved accuracy rates which were higher than that of the stand-alone neural network models.
Similar content being viewed by others
References
West, D., and West, V., Model selection for a medical diagnostic decision support system: A breast cancer detection case. Artif. Intell. Med. 20(3):183–204, 2000.
West, D., and West, V., Improving diagnostic accuracy using a hierarchical neural network to model decision subtasks. Int. J. Med. Inf. 57(1):41–55, 2000.
Kordylewski, H., Graupe, D., and Liu, K., A novel large-memory neural network as an aid in medical diagnosis applications. IEEE Tran. Inf. Technol. Biomed. 5(3):202–209, 2001.
Wolpert, D. H., Stacked generalization. Neural Netw. 5:241–259, 1992.
Taniguchi, M., and Tresp, V., Combining regularized neural networks. Proceedings of the ICANN’97, Lecture Notes in Computer Science 1327, Springer, Berlin, pp. 349–354, 1997.
Hayashi, Y., and Setiono, R., Combining neural network predictions for medical diagnosis. Comput. Biol. Med. 32(4):237–246, 2002.
Übeyli, E. D., and Güler, İ., Neural network analysis of internal carotid arterial Doppler signals: Predictions of stenosis and occlusion. Expert Syst. Appl. 25(1):1–13, 2003.
Übeyli, E. D., and Güler, İ., Comparison of eigenvector methods with classical and model-based methods in analysis of internal carotid arterial Doppler signals. Comput. Biol. Med. 33(6):473–493, 2003.
Übeyli, E. D., and Güler, İ., Spectral analysis of internal carotid arterial Doppler signals using FFT, AR, MA, and ARMA methods. Comput. Biol. Med. 34(4):293–306, 2004.
Daubechies, The wavelet transform, time-frequency localization and signal analysis. IEEE Trans. Inf. Theory 36(5):961–1005, 1990.
Zhang, Y., Wang, Y., Wang, W., and Liu, B., Doppler ultrasound signal denoising based on wavelet frames. IEEE Trans. Ultrason. Ferroelectr. Frequency Control 48(3):709–716, 2001.
Güler, N. F., and Übeyli, E.D., Wavelet-based neural network analysis of ophthalmic artery Doppler signals. Comput. Biol. Med. 34(7):601–613, 2004.
Soltani, S., On the use of the wavelet decomposition for time series prediction. Neurocomputing 48:267–277, 2002.
Acknowledgements
This study has been supported by Scientific Research Project of TOBB Economics and Technology University (Project No: ETU-BAP-2006/06).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Übeyli, E.D. Combining Neural Network Models for Automated Diagnostic Systems. J Med Syst 30, 483–488 (2006). https://doi.org/10.1007/s10916-006-9034-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10916-006-9034-z