Operations Research
Neural networks and logistic regression: Part I
Computational Statistics & Data Analysis
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Machine Learning
Mining breast cancer data with XCS
Proceedings of the 9th annual conference on Genetic and evolutionary computation
Hi-index | 0.00 |
This paper is intended to assess the survival analysis of Bayesian Network models, Neural Network models, and Logistic Regression models. Our analysis will be performed on the SEER data set, a registry of women with breast cancer from the National Cancer Institute. Each model will include the following prognostic variables; progesterone (PR), estrogen (ER), lymph involvement (N), morphology (M), extension and tumor size (T), and histological grade (G). These variables have proven to be significant to the model in regards to breast cancer survival. We have found that a Bayesian network model, which is a combination of an automatically generated network by the BKD software and human expert knowledge, performs comparatively better than the Neural Networks and logistic regression models. The Bayesian network also offers the advantage of explaining the causal relationships among the variables, thus it is the most promising model