The Application of Data Mining Techniques to Oral Cancer Prognosis
- 612 Downloads
This study adopted an integrated procedure that combines the clustering and classification features of data mining technology to determine the differences between the symptoms shown in past cases where patients died from or survived oral cancer. Two data mining tools, namely decision tree and artificial neural network, were used to analyze the historical cases of oral cancer, and their performance was compared with that of logistic regression, the popular statistical analysis tool. Both decision tree and artificial neural network models showed superiority to the traditional statistical model. However, as to clinician, the trees created by the decision tree models are relatively easier to interpret compared to that of the artificial neural network models. Cluster analysis also discovers that those stage 4 patients whose also possess the following four characteristics are having an extremely low survival rate: pN is N2b, level of RLNM is level I-III, AJCC-T is T4, and cells mutate situation (G) is moderate.
KeywordsOral cancer Survival analysis Data mining Cluster analysis
- 1.Centers for Disease Control and Prevention http://www.cdc.gov/OralHealth/oral_cancer/index.htm Accessed 29 March 2014.
- 2.Health Pormotion Administration, Ministry of Health and Weifare http://www.hpa.gov.tw/BHPNet/Web/News/News.aspx?No=201404150002 Accessed 21 April 2014.
- 5.Health Pormotion Administration, Ministry of Health and Weifare http://www.doh.gov.tw/statistic/index.htm Accessed 21 December 2013.
- 6.Taiwan public health report 2009 http://www.mohw.gov.tw/MOHW_Upload/doc/98%E5%B9%B4%E4%B8%AD%E6%96%87%E7%89%88%E8%A1%9B%E7%94%9F%E5%B9%B4%E5%A0%B1_0042862000.pdf Accessed 21 April 2014.
- 10.de Melo, G. M., Ribeiro, K. D. C. B., Kowalski, L. P., and Deheinzelin, D., Risk factors for postoperative complications in oral cancer and their prognostic implications. Arch. Otolaryngol. Head Neck Surg. 127:828–833, 2001.Google Scholar
- 16.Joshi, S., and Nair, M. K., Prediction of heart disease using classification based data mining techniques. Comput Intell Data Min 2:503–511, 2015.Google Scholar
- 20.Cabena, P., Hadjinian, P., Stadler, R., Verhees, J., and Zanasi, A., Discovering data mining: from concept to implementation. Prentice Hall, New Jersey, 1997.Google Scholar
- 21.Kennedy, L., Lee, Y., Roy, V., Reed, C., and Lippman, R., Solving data mining problems through pattern recognition. Prentice Hall, New Jersey, 1997.Google Scholar
- 22.Quinlan, J. R., C4.5: programs for machine learning. Morgan Kaufmann Publishers, San Francisco, 1993.Google Scholar
- 23.Quinlan, J. R., Induction of decision trees. Mach. Learn. 1:81–106, 1986.Google Scholar
- 24.Tso, H. L. The application of data mining on the cardiovascular disease prediction. Dissertation, Southern Taiwan University of Science and Technology, 2005.Google Scholar
- 25.Ting, I. H., and Chen, M. Y., Data mining. Tsang Hai Book Publishing, Taiwan, 2005.Google Scholar
- 26.Jeng, C. C., Yang, I. C., Lain, T. J., Hsieh, K. L., and Lin, C. N., A methodology for constructing taxonomy trees and perceptual maps for microorganism classification. WSEAS Trans. Comput. 11:2571–2578, 2006.Google Scholar