Abstract
Cancer is one of main non-communicable disease. Analysis of cancer prognosis is necessary to determine the proper treatment for each patient. However, cancer data analysis is challenging because multiple risk factors may influence the prognosis of cancer, including genes and clinical condition of patients. This study aims to develop prediction model for cancer prognosis using clinical and gene expression (microarray) data. In this research, Principal Component Analysis (PCA) is applied to microarray data to reduce its dimension, then two Deep Belief Network (DBN) models for both clinical and microarray data are trained separately. Probabilities obtained from Clinical DBN model and Microarray DBN model are integrated using softmax nodes on Bayesian Network structure. Based on various experiments, the best DBN-BN integration model obtains prediction accuracy 73.3535% for overall survival prediction and 71.3434% for disease-free survival prediction.
Original language | English |
---|---|
Pages (from-to) | 5369-5378 |
Number of pages | 10 |
Journal | Journal of Theoretical and Applied Information Technology |
Volume | 95 |
Issue number | 20 |
Publication status | Published - 31 Oct 2017 |
Keywords
- Bayesian network
- Cancer
- Data harmonization
- Data integration
- Deep belief network
- Dimensionality reduction
- Gene expression
- Microarray
- Principal component analysis
- Prognosis