A predication survival model for colorectal cancer

The paper demonstrates an artificial neural networks (ANN) model for prediction survival of colorectal cancer. Data model is collected from SEER which is one of the largest and most comprehensive sources of information on cancer incidence and survival in the USA. Data set consists of over 100000 of colorectal cancer patients. Experimental results are carried out to get the minimum number of extracted features with an optimum ANN architecture without decreasing the prediction accuracy rate. Two models of prediction survival are described. In the first model, the experimental results show that the maximum prediction rate is 84.73%. In the second model, the main objective is to discover the minimum subset of input features that yields the highest accuracy. The experiment results reveal that 73.68% of selected features are sufficient for discrimination and the maximum prediction rate achieves 86.51%. Moreover, 72.72% of hidden neurons are sufficient to get optimum ANN architecture.

[1]  Yoshio Hirose,et al.  Backpropagation algorithm which varies the number of hidden units , 1989, International 1989 Joint Conference on Neural Networks.

[2]  R. Hecht-Nielsen,et al.  Theory of the Back Propagation Neural Network , 1989 .

[3]  Rich Caruana,et al.  Greedy Attribute Selection , 1994, ICML.

[4]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[5]  Ron Kohavi,et al.  Feature Subset Selection Using the Wrapper Method: Overfitting and Dynamic Search Space Topology , 1995, KDD.

[6]  P. Dreyer.  Classification of land cover using optimized neural nets on SPOT data , 1993 .

[7]  Yong-Moo Suh,et al.  Copyright � The Korean Academy of Medical Sciences Comparison of Hospital Charge Prediction Models for Colorectal Cancer Patients: Neural Network vs. Decision Tree Models , 2004 .

[8]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[9]  José Antonio Lozano,et al.  Sensitivity Analysis of k-Fold Cross Validation in Prediction Error Estimation , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Chun-Nan Hsu,et al.  The ANNIGMA-wrapper approach to fast feature selection for neural nets , 2002, IEEE Trans. Syst. Man Cybern. Part B.

[11]  Peter Protzel,et al.  FlexNet - A flexible neural network construction algorithm , 1996, ESANN.

[12]  Russell Reed,et al.  Pruning algorithms-a survey , 1993, IEEE Trans. Neural Networks.

[13]  Ron Kohavi,et al.  Irrelevant Features and the Subset Selection Problem , 1994, ICML.

[14]  Farid E Ahmed,et al.  Molecular Cancer BioMed Central Review , 2005 .

[15]  Kenneth W. Bauer,et al.  Integrated feature architecture selection , 1996, IEEE Trans. Neural Networks.

[16]  High Accuracy Optical Character Recognition Using Neural Networks with Centroid Dithering , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[18]  Ehud D. Karnin,et al.  A simple procedure for pruning back-propagation trained neural networks , 1990, IEEE Trans. Neural Networks.

[19]  Kenneth W. Bauer,et al.  Integrated Feature and Architecture Selection for Radial Basis Neural Networks , 2003 .

[20]  R.J.F. Dow,et al.  Neural net pruning-why and how , 1988, IEEE 1988 International Conference on Neural Networks.

[21]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[22]  Sung-Bae Cho,et al.  Prediction of colon cancer using an evolutionary neural network , 2004, Neurocomputing.