Cluster Analysis and Data Mining Techniques with Several Applications

• Activity Number: 418
• Type: Topic Contributed
• Date/Time: Tuesday, August 11, 2015 : 2:00 PM to 3:50 PM
• Sponsor: Scientific and Public Affairs Advisory Committee
• Author(s): Kelly H. Zou* and Ching-Ray Yu and Jason Pan and Franklin W. Sun
• Companies: Pfizer Inc. and Pfizer Inc. and Pfizer Inc and Pfizer Inc.
• Keywords: Receiver Operating Characteristic curve ; Area under the Curve ; Data Mining ; Cluster Analysis ; Heterogeneity ; Monte-Carlo Simulations

Abstract

It is important to develop precision medicine when there is significant heterogeneity or dissimilarity among individuals, compared with the overall population. Data mining tools based on clustering algorithms, such as cumulative distribution curve, receiver operating characteristic curve, and various distance measures, are proposed and utilized to help identify and visualize different clusters. These measures may help assess the heterogeneity or closeness between various clusters. We illustrate these methods using existing data from the literature. Monte-Carlo simulations are performed to compare their performances.