Medical Sciences
Integrated modeling of clinical and gene expression information for personalized prediction of disease outcomes
Jennifer Pittman *
, Erich Huang 
, Holly Dressman , Cheng-Fang Horng 
, Skye H. Cheng , Mei-Hua Tsou , Chii-Ming Chen , Andrea Bild , Edwin S. Iversen *, Andrew T. Huang ¶, Joseph R. Nevins ||, and Mike West ***
*Institute of Statistics and Decision Sciences, Computational and Applied Genomics Program, Institute for Genome Sciences and Policy, and ||Howard Hughes Medical Institute, Duke University, Durham, NC 27708; Departments of Molecular Genetics and Microbiology and ¶Medicine, Duke University Medical Center, Durham, NC 27710; and Koo Foundation Sun Yat-Sen Cancer Center, 125 Lih-Der Road, Pei-Tou District, Taipei 112, Taiwan
Communicated by James O. Berger, Duke University, Durham, NC, March 15, 2004 (received for review June 18, 2003)
We describe a comprehensive modeling approach to combining genomic and clinical data for personalized prediction in disease outcome studies. This integrated clinicogenomic modeling framework is based on statistical classification tree models that evaluate the contributions of multiple forms of data, both clinical and genomic, to define interactions of multiple risk factors that associate with the clinical outcome and derive predictions customized to the individual patient level. Gene expression data from DNA microarrays is represented by multiple, summary measures that we term metagenes; each metagene characterizes the dominant common expression pattern within a cluster of genes. A case study of primary breast cancer recurrence demonstrates that models using multiple metagenes combined with traditional clinical risk factors improve prediction accuracy at the individual patient level, delivering predictions more accurate than those made by using a single genomic predictor or clinical data alone. The analysis also highlights issues of communicating uncertainty in prediction and identifies combinations of clinical and genomic risk factors playing predictive roles. Implicated metagenes identify gene subsets with the potential to aid biological interpretation. This framework will extend to incorporate any form of data, including emerging forms of genomic data, and provides a platform for development of models for personalized prognosis.
