A Stochastic and State Space Mixture Model of Human Liver Cancer: Multiple Pathway Model Involving Both Hereditary and Non-Hereditary Cancer

• Activity Number: 516
• Type: Contributed
• Date/Time: Wednesday, August 1, 2012 : 10:30 AM to 12:20 PM
• Sponsor: ENAR
• Author(s): Xiaowei Yan*+ and Wai-Yuan Tan
• Companies: and University of Memphis
• Keywords: Stochastic Model ; Multiple-pathway carcinogenesis ; Hereditary and Non-hereditary Liver Cancer

Abstract

Based on recent biological studies, we have developed a state space mixture model for human liver cancer. The state space model joins stochastic system model with a statistical model, in which the stochastic system model composes of two parts: first is a stochastic model involving 2 different pathways for Non-hereditary liver cancer, the second part is hereditary pattern, which was represented by a mixture model. To this end, the probability of liver cancer developed from each pathway was derived. Then the statistical model combines the liver cancer incidence rate with observational data. Based on this model we have developed a generalized Bayesian approach to estimate the parameters through the posterior modes of the parameters via Gibbs sampling procedures. We have applied this model to fit and analyze the SEER data of human liver cancer incidence from NCI/NIH. Our results indicate that the model not only provides a logical avenue to incorporate biological information but also fits the data much better than other models including the 4-stage single pathway model. This model would provide more insights into human liver cancer also would provide useful guidance in prevention.