Applications of Generalized Kullback-Leibler Divergence as a Measure of Medical Diagnostic and Cut-Point Criterion for K-Stages Diseases
Abstract or Description
Presented at ENAR Conference
Recently, Kullback-Leibler divergence measure (KL), which captures the disparity between two distributions, has been considered as an index for determining the diagnostic performance of biomarkers. Our study investigates variety of applications of the generalized KL divergence (GKL) in medical diagnostics, including overall measures of rule-in and rule-out potential and proposes an optimization criterion based on KL divergence for cut-point selection for k-stage disease. Moreover, the study links the KL divergence with some common Receiver Operating Characteristic (ROC) measures and presents analytically and numerically the relations in situations of one cut-point as well as multiple cut-points. Furthermore, the graphical application and interpretation of GKL divergence, which is referred as the information graph, is discussed. A comprehensive data analysis of the real data example to illustrate the proposed applications is provided.
Eastern North American Region International Biometric Society Conference
Mo, Chen, Hani Samawi, Jingjing Yin, Haresh Rochani, Xinyan Zhang, Jing Kersey.
"Applications of Generalized Kullback-Leibler Divergence as a Measure of Medical Diagnostic and Cut-Point Criterion for K-Stages Diseases."
Department of Biostatistics, Epidemiology, and Environmental Health Sciences Faculty Presentations.
Link to program: https://www.enar.org/meetings/spring2019/program/ENAR_Abstracts.pdf