Sains Malaysiana 41(5)(2012): 633–640

 

Determining the Critical Success Factors of Oral Cancer Susceptibility

Prediction in Malaysia Using Fuzzy Models

(Menentukan Faktor Kejayaan Kritikal dalam Peramalan Kecenderungan Terjadinya

Kanser Mulut di Malaysia Menggunakan Model Kabur)

 

 

Rosma Mohd Dom

Department of Mathematics, Faculty of Computer & Mathematical Sciences, Universiti Teknologi MARA , 40450 Shah Alam, Selangor D.E. Malaysia

 

Basir Abidin

Director, Foundation in Science , Cyberjaya University College of Medical Sciences, Unit No 2, Street Mall 2, 63000 Cyberjaya, Selangor D.E. Malaysia

 

Sameem Abdul Kareem

Faculty of Computer Science & Information Teknology, University of Malaya, 50603 Kuala Lumpur

Malaysia

 

Siti Mazlipah Ismail

Oral Cancer Research & Coordinating Center, Faculty of Dentistry, Universiti of Malaya

50603 Kuala Lumpur, Malaysia

 

Norzaidi Mohd Daud*

Faculty of Business Management/Accounting Research Institute/Institute of Business Excellence

Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia

 

Diserahkan: 3 Februari 2010 / Diterima: 18 November 2011

 

ABSTRACT

The aim of the study was to determine the success factors of oral cancer susceptibility prediction using fuzzy models. Three fuzzy prediction models including fuzzy logic, fuzzy neural network and fuzzy linear regression models were constructed and applied to a Malaysian oral cancer data set for cancer susceptibility prediction. The three models’ prediction performances were evaluated and compared. All the three fuzzy models were found to have 64% prediction accuracies for 1-input and 2-input predictor sets. However, when the number of input predictor set was increased to 3-input and 4-input, both fuzzy neural networks’ and fuzzy linear regression’s prediction accuracies increased to 80%, while fuzzy logic prediction accuracy remains at 64%. Fuzzy linear regression model was found to have the capability of quantifying the relationships between input predictors and the predicted outcomes and also suitable for small sample size. Fuzzy neural network model on the other hand, handles ambiguous relationship between variables well but lacks the ability to describe input-output association. The third model, fuzzy logic, is easy to construct but highly dependent on human expert-input. The outcome of this study is a computer-based prediction tool which can be used in cancer screening programs.

 

Keywords: Fuzzy logic; fuzzy neural networks; fuzzy regression; oral cancer; prediction performance

 

ABSTRAK

Matlamat kajian ini adalah untuk mengenal pasti faktor kejayaan dalam menentukan kecenderungan terjadinya kanser mulut menggunakan model kabur. Tiga model kabur termasuk model mantik kabur, rangkaian neuro-kabur dan regresi kabur telah dibangun dan diaplikasikan ke atas data kanser mulut di Malaysia bagi tujuan menentukan kemungkinan terjadinya kanser. Kejituan ramalan terjadinya kanser mulut untuk ketiga-tiga model diukur dan dibandingkan. Ketiga-tiga model kabur didapati memberikan 64% kejituan ramalan semasa diuji menggunakan satu dan dua faktor penentu. Walau bagaimanapun, apabila bilangan faktor penentu ditambah kepada tiga dan empat, kejituan ramalan model rangkaian neuro-kabur dan regresi kabur meningkat kepada 80% tetapi kejituan ramalan model mantik kabur kekal di paras 64%. Model regresi kabur mampu mengukur kuantiti hubung kait di antara faktor penentu dengan hasilannya dan ia juga sesuai digunakan untuk sampel yang kecil. Model rangkaian neuro-kabur mengambil kira hubungan ketidaktentuan di antara faktor penentu dan hasilannya tetapi tidak mempunyai keupayaan mengukur kuantiti hubung kait di antara mereka. Model ketiga iaitu mantik kabur pula mudah untuk dibangunkan tetapi terlalu bergantung kepada input pakar. Kajian ini menghasilkan satu alat pengukur berasaskan komputer yang boleh digunakan bagi tujuan saringan pesakit kanser.

 

Kata kunci: Kanser mulut; kejituan ramalan; mantik kabur; rangkaian neuro-kabur; regresi kabur

RUJUKAN

Abd-Kareem, S. 2002. Application of artificial neural network for the prognosis of nasopharyngeal carcinoma. Computer Science Department. University of Malaya, Kuala Lumpur, PhD thesis (unpublished).

Castellano, G. & C., Fanelli, A. 2005. Knowledge discovery by a neuro-fuzzy modeling framework. Fuzzy Sets and Systems 149: 187–207.

Coppin, B. 2004. Artificial Intelligence Illuminated. Sudbury, Massachusetts: Jones & Barllett Publishers.

Dreiseitl, S. & Ohno-Machado, L. 2002. Logistic regression and artificial neural network classification models: a methodology review. Jounal of Biomedical Informatics 35: 352-359.

Gorzalczany, M & Piasta Z. 1999. Neuro-fuzzy approach versus rough-set inspired methodology for Intelligent decision support. Information Sciences 120(1): 45-48.

Jang, R. 1993. ANFIS: Adaptive- Network-Based Fuzzy Inference System. IEEE Trans. On Systems, Man and Cybernetics 23(3): 665-685.

Kononenko, I. 2000. Machine learning for medical diagnosis: History, state of the art and perspective. Artificial Intelligence in Medicine 23(1): 89-109.

Lasko, T., Bhagwat, J., Zou, K., Machado, L. 2005. The use of receiver operating characteristic curves in biomedical informatics. Jounal of Biomedical Informatics 38: 404-415.

Mohan, J. & Yaacob, R. 2004. The Malaysian Telehealth Flagship Application: A national approach to health data protection and utilisation and consumer rights. International Journal of Medical Informatics 73: 217-227.

Mohd Dom, R. 2009. A fuzzy regression model for the prediction of oral cancer susceptibility.Computer Science Department, University of Malaya, Kuala Lumpur, PhD Thesis (unpublished).

Moraga, C. 2000. Neuro-fuzzy modeling with standard feedforward neural networks. European Symposium on Intelligent Techniques Proceedings. Aachen, Germany.

Muzio, L., D’Angelo, M., Procaccini, M., Bambini, F., Calvino, F., Florena, AM., Franco, V., Giovanelli, L., Ammatuna, P. And Campisi, G. 2005. Expression of cell cycle markers and human papilloma virus infection in oral squamous cell carcinoma: Use of fuzzy neural networks. Int. J. Cancer 115: 717- 723.

Nasrabadi, M. & Nasrabadi, E. 2004. A mathematical-programming approach to fuzzy linear regression analysis. Applied Mathematics and Computation 155: 873-881.

Savic, D. & Pedrycz, W. 1991. Evaluation of fuzzy linear regression models. Fuzzy Sets and Systems 39(1): 51-63.

Speight, P., Elliott, A., Jullien, J., Downer & M., Zakzrewska, J. 1995. The use of artificial intelligence to identify people at risk of oral cancer and precancer. British Dental Journal 179: 382-387.

Tanaka, H. & H. Lee 1998. Interval Regression Analysis by Quadratic Programming Approach. IEEE Transactions on Fuzzy Systems 6(4):

Wang, H. & Tsaur, R. 2000. Insight of a fuzzy regression model. Fuzzy set and systems 112: 355-369.

Zadeh, L. A, 1965. Fuzzy Sets. Information and Control 8: 338-353.

Zain, R. 2001. Cultural and dietary risk factors of oral cancer and pre-cancer – A brief overview. Oral Oncology 37:205-210.

 

*Pengarang untuk surat-menyurat; email: zaidiuitm2000@yahoo.com

 

 

 

 

sebelumnya