The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.04 - July-Aug. (2012 vol.9)
pp: 1091-1105
Changhong Yu , Dept. of Quantitative Health Sci., Cleveland Clinic Found., Cleveland, OH, USA
ABSTRACT
In medical society, the prognostic models, which use clinicopathologic features and predict prognosis after a certain treatment, have been externally validated and used in practice. In recent years, most research has focused on high dimensional genomic data and small sample sizes. Since clinically similar but molecularly heterogeneous tumors may produce different clinical outcomes, the combination of clinical and genomic information, which may be complementary, is crucial to improve the quality of prognostic predictions. However, there is a lack of an integrating scheme for clinic-genomic models due to the P ≫ N problem, in particular, for a parsimonious model. We propose a methodology to build a reduced yet accurate integrative model using a hybrid approach based on the Cox regression model, which uses several dimension reduction techniques, L2 penalized maximum likelihood estimation (PMLE), and resampling methods to tackle the problem. The predictive accuracy of the modeling approach is assessed by several metrics via an independent and thorough scheme to compare competing methods. In breast cancer data studies on a metastasis and death event, we show that the proposed methodology can improve prediction accuracy and build a final model with a hybrid signature that is parsimonious when integrating both types of variables.
INDEX TERMS
tumours, bioinformatics, cancer, data analysis, genomics, maximum likelihood estimation, medical computing, modelling, patient treatment, regression analysis, sampling methods, death event, survival model building, clinical information, molecular information, censored data, prognostic models, clinicopathologic features, prognosis prediction, high dimensional genomic data, molecularly heterogeneous tumors, genomic information, clinical-genomic models, parsimonious model, Cox regression model, dimension reduction techniques, L2 penalized maximum likelihood estimation, PMLE, resampling methods, breast cancer data, breast cancer metastasis, Data models, Bioinformatics, Predictive models, Computational modeling, Feature extraction, Genomics, Indexes, data integration., Prognostic prediction model, dimension reduction, Clinico-genomic information, censored time to event data, feature selection, Cox model
CITATION
Changhong Yu, "A Hybrid Approach to Survival Model Building Using Integration of Clinical and Molecular Information in Censored Data", IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol.9, no. 4, pp. 1091-1105, July-Aug. 2012, doi:10.1109/TCBB.2012.31
27 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool