14th IFAC Symposium on System Identification, SYSID 2006

SYSID-2006 Paper Abstract


Paper FrA6.4

Gevaert, Olivier (Katholieke Univ. Leuven), De Smet, Frank (Katholieke Univ. Leuven), Timmerman, Dirk (Univ. Hospital Gasthuisberg, Katholieke Univ. Leuven), Moreau, Yves (Katholieke Univ. Leuven), De Moor, Bart (Katholieke Univ. Leuven)

Integration of Clinical and Microarray Data Using Bayesian Networks

Scheduled for presentation during the Regular Session "Identification in Biological Systems" (FrA6), Friday, March 31, 2006, 11:30−11:50, Newcastle Room

14th IFAC Symposium on System Identification, March 29 - 31, 2006, Newcastle, Australia

This information is tentative and subject to change. Compiled on July 16, 2018

Keywords Bayesian Methods, Machine Learning and Data Mining, Biological Systems


Microarrays have revolutionized research in molecular biology especially in cancer research. They allow to measure the expression of thousands of genes and can be used to guide clinical management of cancer. However, mathematical models based on microarray data often ignore the available clinical data, instead of integrating clinical and microarray data. We present and evaluate three methods for integrating clinical and microarray data using Bayesian networks: full integration, partial integration and decision integration, and use them to predict prognosis in breast cancer. Partial integration performs best on the test set and is promising for other types of cancer and data.