Copula Modeling for Developing a Biomarker Panel for Prediction of Dengue Hemorrhagic Fever

• Activity Number: 503
• Type: Contributed
• Date/Time: Wednesday, August 12, 2015 : 8:30 AM to 10:20 AM
• Sponsor: Biometrics Section
• Author(s): Hyunsu Ju* and Jong-Min Kim
• Companies: The University of Texas Medical Branch and University of Minnesota, Morris
• Keywords: Copula model ; Variable selection ; Classification ; Dependent structure

Abstract

The choice of model selection methods to identify correlated important variables for binary classification modeling is critical to produce stable models that are interpretable, that generate accurate predictions and have minimum bias. This work is motivated by data on clinical and laboratory features of Dengue infections obtained from 51 individuals enrolled in a prospective observational study of acute human dengue infections. We carry out semi-parametric Gaussian copula model to estimate the marginal distribution and dependence structure separately. Bootstrapping applications for evaluating predictive regression coefficients in support vector machine classifier are performed. These results suggest that IL-10, Days Fever, Sex and Lymphocyte cytokine are the major features for predicting dengue hemorrhagic fever on the basis of blood chemistries and cytokine measurements.