TY - JOUR
T1 - Hierarchical bayesian neural networks
T2 - An application to a prostate cancer study
AU - Ghosh, Malay
AU - Maiti, Tapabrata
AU - Kim, Dalho
AU - Chakraborty, Sounak
AU - Tewari, Ashutosh
N1 - Funding Information:
Malay Ghosh is Distinguished Professor, Department of Statistics, University of Florida, Gainesville, FL 32611 (E-mail: [email protected]). Tapabrata Maiti is Associate Professor, Department of Statistics, Iowa State University, Ames, IA 50011 (E-mail: [email protected]). Dalho Kim is Associate Professor, Department of Statistics, Kyungpook National University, Taegu 702-701, Korea (E-mail: [email protected]). Sounak Chakraborty is a doctoral student of Malay Ghosh, Department of Statistics, University of Florida, Gainesville, FL 32611 (E-mail: [email protected]). Ashutosh Tewari is a Physic, Vattikuti Institute of Urology and Josephine Ford Cancer Center and Department of Urology, Henry Ford Health System, Detroit, MI 48202. Ghosh and Chakraborty’s research was supported in part by National Institutes of Health (NIH) grant R01 CA-85414. Maiti’s research was supported in part by National Science Foundation (NSF) grant SES-9911466 and NIH grant R01 CA-85414. Kim’s research was supported in part by NSF grant SES-9911485. Tewari’s research was supported in part by NIH grant R01 CA-85414. The authors thank the associate editor and two referees for their helpful comments on the manuscript.
PY - 2004/9
Y1 - 2004/9
N2 - Prostate cancer is one of the most common cancers in American men. Management depends on the staging of prostate cancer. Only cancers that are confined to organs of origin are potentially curable. The article considers a hierarchical Bayesian neural network approach for posterior prediction probabilities of certain features indicative of non-organ-confined prostate cancer. The Bayesian procedure is implemented by an application of the Markov chain Monte Carlo numerical integration technique. For the problem at hand, the hierarchical Bayesian neural network approach is shown to be superior to the approach based on hierarchical Bayesian logistic regression model as well as the classical feedforward neural networks.
AB - Prostate cancer is one of the most common cancers in American men. Management depends on the staging of prostate cancer. Only cancers that are confined to organs of origin are potentially curable. The article considers a hierarchical Bayesian neural network approach for posterior prediction probabilities of certain features indicative of non-organ-confined prostate cancer. The Bayesian procedure is implemented by an application of the Markov chain Monte Carlo numerical integration technique. For the problem at hand, the hierarchical Bayesian neural network approach is shown to be superior to the approach based on hierarchical Bayesian logistic regression model as well as the classical feedforward neural networks.
KW - Bayesian prediction
KW - Feedforward neural networks
KW - Logistic regression
KW - Marginal positivity
KW - Markov chain Monte Carlo
KW - Seminal vesicle positivity
UR - http://www.scopus.com/inward/record.url?scp=4944241445&partnerID=8YFLogxK
U2 - 10.1198/016214504000000665
DO - 10.1198/016214504000000665
M3 - Review article
AN - SCOPUS:4944241445
SN - 0162-1459
VL - 99
SP - 601
EP - 608
JO - Journal of the American Statistical Association
JF - Journal of the American Statistical Association
IS - 467
ER -