Analysis of Significant Prognostic Factors of Patients with Bladder Cancer Using Self-Organizing Maps

Abstract:

This study presents a new approach to determine significant prognostic factors for patients suffering from the bladder cancer. The analysis of medical data has been performed by the use of the Kohonen self-organizing map (SOM). The SOM allows visualizing and identifying the prognostic factors indicating which of them are significant. A database comprised of ninety patients has been used in this study. Seven predictors were investigated. The cluster analysis indicates that the significant prognostic factors for the bladder cancer are: histological grade (cG) and stage (cT). The obtained results also showed that the sex and the cG variables are highly correlated and that the number of non-classic differentiation (NDNc) features in bladder cancer is somewhat correlated to surgically removed lymphnode number (LN) and metastatic positive lymphnode number (PLN).

• Periodical: Solid State Phenomena (Volume 199)
• Pages: 223-228
• DOI: https://doi.org/10.4028/www.scientific.net/SSP.199.223
• Online since: March 2013
• Authors: Marta Kolasa, Rafał Długosz, Wojciech Jóźwicki, Jolanta Pauk, Aleksandra Świetlicka, Pierre André Farine
• Keywords: Bladder Cancer, Clusters Analysis, Kohonen SOM, Prognostic Factors

References

[1] M.F. Abbod, J.W.F. Catto, D.A. Linkens, P.J. Wild, A. Herr, C. Wissmann, C. Pilarsky, A. Hartmann, F.C. Hamdy, Artificial Intelligence Technique for Gene Expression Profiling of Urinary Bladder Cancer, In: 3rd Inter. IEEE Conference Intelligent Systems. (2006).

DOI: 10.1109/is.2006.348495

[2] J.W.F. Catto, D.A. Linkens, M.F. Abbod, M. Chen, J.L. Burton, K.M. Feeley, F.C. Hamdy, Artificial Intelligence in Predicting Bladder Cancer Outcome, A Comparison of Neuro-Fuzzy Modeling and Artificial Neural Networks, Clinical Cancer Research. 9 (2003).

DOI: 10.1016/s1569-9056(03)80262-2

[3] R.N.G. Naguib, K.N. Qureshi, F.C. Hamdy, D.E. Neal, Neural Network analysis of Prognostic Markers in Bladder Cancer, In: 19th International Conference IEEE/EMBS. 3 (1997) 646-651.

DOI: 10.1109/iembs.1997.756515

[4] E.J. Tkacz, P. Kostka, K. Jonderko, B. Mika, Supervised and Unsupervised Learning Systems as a Part of Hybrid Structures Applied in EGG Signals Classifiers, IEEE Annual Conference Engineering in Medicine and Biology. (2005).

DOI: 10.1109/iembs.2005.1617042

[5] J.T. Wei, A. Tewari, Artificial Neural Networks in Urology, Pro. Urology. 54 (1999) 945–948.

DOI: 10.1016/s0090-4295(99)00341-6

[6] T. Habuchi, M. Marberger, M.J. Droller, et al., Prognostic markers for bladder cancer, International Consensus Panel on Bladder Tumor Markers. Urology. 66 (2005) 64-74.

DOI: 10.1016/j.urology.2005.08.065

[7] A. Tewari, P. Narayan, Novel staging tool for localized prostate cancer: a pilot study using genetic adaptive neural networks, J Urol. 160 (1998) 430–438.

DOI: 10.1016/s0022-5347(01)62916-1

[8] P.B. Snow, D.M. Rodvold, J.M. Brandt, Artificial Neural Networks in Clinical Urology, Urology. 54 (1999) 787-790.

DOI: 10.1016/s0090-4295(99)00327-1

[9] P.B. Snow, D.S. Smith, W.J. Catalona, Artificial neural networks in the diagnosis and prognosis of prostate cancer: a pilot study, J Urol. 152 (1994) 1923-(1926).

DOI: 10.1016/s0022-5347(17)32416-3

[10] E.K. Michaels, C.S. Niederberger, R.M. Golden, et al., Use of a Neural Network to Predict Stone Growth After Shock Wave Lithotripsy, Urology. 51 (1998) 335–338.

DOI: 10.1016/s0090-4295(97)00611-0

[11] S.F. Shariat, P.I. Karakiewicz, G.S. Palapattu, G.E. Amiel, Y. Lotan, C.G. Rogers, A. Vazina, et al., Nomograms Provide Improved Accuracy for Predicting Survival after Radical Cystectomy, Clin Cancer Res. 12, 22 (2006) 6663-76.

DOI: 10.1158/1078-0432.ccr-06-0372

[12] A.J. Colquhoun, G.D. Jones, M.A. Moneef, et al., Improving and predicting radiosensitivity in muscle invasive bladder cancer, J Urol. 169 (2003) 1983–(1992).

DOI: 10.1097/01.ju.0000067941.12011.40

[13] A. Lopez-Beltran, G. Sauter, T. Gasser, et al., Infiltrating urothelial carcinoma, In: Eble JN, et al, editors, WHO classification of tumours, Pathology and genetics, Tumours of the urinary system and male genital organs. Lyon, France7 IARC Press. (2004).

[14] W. Jóźwicki , P. Jarzemski , M. Kolasa , R. Golda , J. Domaniewski, Nonclassic differentiation number (NDN)-important additional information about urothelial cancer, European Urology Supplements. 7, 3 (2008) 560.

DOI: 10.1016/s1569-9056(08)60556-4

[15] T. Kohonen, Self-Organizing Maps, third edition, Springer Berlin, (2001).

[16] T. Mokriš, R. Forgáč, Decreasing the Feature Space Dimension by Kohonen Self-Orgaizing Maps, 2nd Slovakian – Hungarian Joint Symposium on Applied Machine Intelligence. (2004).

[17] E. Uriarte and F. Martin, Topology preservation in SOM, Int. J. Appl. Math. Comput. Sci. 1, 1 (2005) 19–22.

[18] D. Beaton, I. Valova, and D. MacLean, CQoCO: A measure for comparative quality of coverage and organization for self-organizing maps, Neurocomputing. 73, 10–12 (2010) 2147–2159.

DOI: 10.1016/j.neucom.2010.02.004

[19] T. Faisal, M. N. Taib, F. Ibrahim, Reexamination of risk criteria in dengue patients using the self-organizing map, Medical & Biological Engineering & Computing. 48, 3 (2010) 293-301.

DOI: 10.1007/s11517-009-0561-x

[20] J. Vesanto, E. Alhoniemi, Clustering of the self-organizing map, IEEE Transactions on Neural Networks. 11, 3 (2000) 586-600.

DOI: 10.1109/72.846731

[21] M. Kolasa, R. Długosz, W. Pedrycz, M. Szulc, Programmable Triangular Neighborhood Function for Kohonen Self-Organizing Map Implemented on Chip, Neural Networks, Elsevier. 25 (2012) 146–160.

DOI: 10.1016/j.neunet.2011.09.002