Examination of the effect of ANN and NLPCA technique on prediction performance in patients with breast tumors

Abstract

Breast cancer is among the most prevalent cancer kinds worldwide. The aim of this study is to examine the effect of combining Artificial Neural Networks and Nonlinear Principal Component Analysis techniques on prediction performance in patients with breast tumors. In the application, a network containing 5 layers, including the input, the coding, the bottleneck, the decoding and the output, was used for the 30 variable data set of 569 breast tumor patients. The training algorithm of choice was the Conjugate Gradient Descent (CGD) algorithm. In this study, artificial neural networks (ANN) and nonlinear principal component analysis were coupled. NLPCA was first applied to dimension reduction in artificial neural networks. Using both the original data set and the decreased size, artificial neural networks were used in the second stage to develop prediction models. By contrasting the performance of these two prediction models with one another, the outcomes were understood. 96.37% of the variation was explained by the two fundamental components that were found using NLPCA. The prediction models developed for the original data set and the dimension-reduced data set have R2 values of 91% and 87%, respectively. The advantages of the NLPCA and ANN combination for breast tumor patients are demonstrated by this study. It is believed that utilizing principal components as inputs can cut down on complexity and extraneous information.

Keywords

• Artificial neural networks
• Breast tumor
• Dimensional reduction
• Nonlinear principal component analysis
• Variance

References

1. [1] A. Haydaroğlu, S. Dubova, S. Özsaran, et al., “Breast Cancer in Ege University “Evaluation Of 3897 Cases””, The Journal of Breast Health, vol. 1, pp. 6-11, 2005.
2. [2] C. Hocaoglu, G. Kandemir and F. Civil, “The Influence of Breast Cancer to Family Relationships: a Case Report”, The Journal of Breast Health, vol. 3, pp. 163-165, 2007.
3. [3] C. Eroğlu, M. A. Eryılmaz, S. Civcik, et al., “Breast Cancer Risk Assessment: 5000 Cases”, International Journal of Hematology and Oncology, vol. 20, pp. 27-33, 2010.
4. [4] N. Akyolcu and G. A. Ugras, “Breast Self-Examination: how Important is it in Early Diagnosis?”, The Journal of Breast Health, vol. 7, pp. 10-14, 2011.
5. [5] A. Tumer, and H. Baybek, “The Risk Level of Breast Cancer at The Working Women”, The Journal of Breast Health, vol. 6, pp. 17-21, 2010, https://hdl.handle.net/20.500.12809/4656.
6. [6] A. Buciński, T. Bączek, T. Waśniewski and M. Stefanowicz, “Clinical data analysis with the use of artificial neural networks (ANN) and principal component analysis (PCA) of patients with endometrial carcinoma”, Rep. Pract. Oncol. Radiother, vol. 10, pp. 239-248, 2005, doi:10.1016/S1507-1367(05)71096-8.
7. [7] S. I. V. Sousa, F. G. Martins, M. C. M. Alvim-Ferraz and M.C. Pereira, “Multiple linear regression and artificial neural networks based on principal components to predict ozone concentrations”, Environmental Modelling & Software, vol. 22, pp. 97-103, 2007, doi:10.1016/j.envsoft.2005.12.002.
8. [8] C. Demir and S. Keskin, “Artificial neural network approach for nonlinear principal components analysis”, International Journal of Current Research, vol. 13, no. 1, pp. 15987-15992, 2021, doi:10.24941/ijcr.40671.01.2021.

9. [9] M. O. Kaya, C. Colak and E. Ozdemir, “The Prediction of Prostate Cancer Using Different Artificial Neural Network Models with The Help of Prostate Specific Antigen”, İnönü University Journal of Health Sciences, vol. 1, pp. 19-22, 2013.
10. [10] S. Samarasinghe, “Neural networks for applied sciences and engineering: from fundamentals to complex pattern recognition”, Crc Press, pp. 245-281. 2006.
11. [11] W. Wolberg, O. Mangasarian, N. Street and W. Street, “Breast Cancer Wisconsin (Diagnostic)”, UCI Machine Learning Repository, 1995, doi:10.24432/C5DW2B.
12. [12] M. Scholz, F. Kaplan, C. L. Guy, J. Kopka and J. Selbig, “Non-linear PCA: a missing data approach”, Bioinformatics, vol. 21, pp. 3887-3895, 2005, doi:10.1093/bioinformatics/bti634.
13. [13] W. W. Hsieh, “Nonlinear principal component analysis by neural networks”, Tellus, vol. 53, pp. 599-615, 2001, doi:10.3402/tellusa.v53i5.12230.
14. [14] M.A. Kramer, “Nonlinear principal component analysis using auto-associative neural networks”, AIChE Journal, vol. 37, pp. 233-43, 1991, doi:10.1002/aic.690370209.
15. [15] W. W. Hsieh, “Nonlinear principal component analysis of noisy data”, Neural Networks, vol. 20, no. 4, pp. 434-443, 2006. doi:10.1016/j.neunet.2007.04.018.
16. [16] D. Anderson and G. McNeill, “Artificial Neural Networks Technology”, New York: Rome Laboratory RL/C3C Griffiss AFB. 83. A011, 1992.
17. [17] A. Gülbağ, “Quantitative Determination Of Volatile Organic Compounds By Using Artificial Neural Network And Fuzzy Logic Based Algorithm”, [dissertation], Sakarya: Sakarya University, 2006.
18. [18] H. Güler, “Prediction of Elements On Corrosion Behavior Of Zinc-Aluminum Alloys Using Artificial Neural Networks”, [dissertation]. Sakarya, Sakarya University, 2007.
19. [19] H. Okut, “Bayesian Regularized Neural Networks for Small n Big p Data. Rosa JLG”, Artificial Neural Networks-Models and Applications. London: InTechOpen, 2016.
20. [20] V.S.A. Kargı, “Artificial Neural Network Models and an Application at a Textile Firm”, [dissertation]. Bursa, Uludağ University, 2013.
21. [21] B. Taşar, F. Üneş, M. Demirci and Y. Z. Kaya, “Forecasting of Daily Evaporation Amounts Using Artificial Neural Networks Technique”, Dicle University Engineering Faculty Journal of Engineering, vol. 9, no. 1, pp. 543-551, 2018.
22. [22] Trainlm [Internet]. [access date 29 november 2021]. Access address:https://uk.mathworks.com/help/deeplearning/ref/trainlm.html
23. [23] Y. Gültepe, “A Comparative Assessment on Air Pollution Estimation by Machine Learning Algorithms”, European Journal of Science and Technology, vol. 16, pp. 8-15, 2019, doi:10.31590/ejosat.530347.
24. [24] M. O’Farrella, E. Lewisa, C. Flanagana, W. B. Lyonsa and N. Jackman, “Combining principal component analysis with an artificial neural network to perform online quality assessment of food as it cooks in a large-scale industrial oven”, Sensors and Actuators B: Chemical, vol. 107, pp. 104–112, 2005, doi:10.1016/j.snb.2004.09.050
25. [25] S. Ayesha, M. K. Hanif, and R. Talib, “Overview and comparative study of dimensionality reduction techniques for high dimensional data”, Information Fusion, vol. 59, pp. 44-58, 2020, https://doi.org/10.1016/j.inffus.2020.01.005.
26. [26] R. Zebari, A. Abdulazeez, D. Zeebaree, D. Zebari and J. Saeed, “A comprehensive review of dimensionality reduction techniques for feature selection and feature extraction”, Journal of Applied Science and Technology Trends, vol. 1, no. 1, pp. 56-70, 2020, doi:10.38094/jastt1224.
27. [27] G. T. Reddy, M. P. K. Reddy, K. Lakshmanna, R. Kaluri, D. S. Rajput, G. Srivastava and T. Baker, “Analysis of dimensionality reduction techniques on big data”, Ieee Access. 8, 54776-54788. 2020, doi: 10.1109/ACCESS.2020.2980942
28. [28] I. K. Omurlu, F. Cantas, M. Ture and H. Ozturk, “An empirical study on performances of multilayer perceptron, logistic regression, ANFIS, KNN and bagging CART”, Journal of Statistics and Management Systems, vol. 23, no. 4, pp. 827-841, 2020, doi:10.1080/09720510.2019.1696924.