Developing Fuzzy-set-theory-based Data Mining Methodologies for
Diabetes Data Analysis
L. Liang, Ph.D.
Department of Computer Science and Information
Diabetes is a group of diseases marked by high levels of blood glucose, also called blood sugar, resulting from defects in insulin production, insulin action, or both. Diabetes can lead to serious complications and premature death. The serious complications diabetes can be associated with include heart disease and stroke, high blood pressure, blindness, kidney disease, nervous system disease, amputations, dental disease, and complications of pregnancy. Diabetes was the seventh leading cause of death listed on U.S. death certificates in 2006. Overall, the risk of death among people with diabetes is about twice that of people without diabetes of a similar age (source: NIDDK, NIH).
The overall aim of this interdisciplinary research is to develop a series of fuzzy-set-theory-based data mining approaches for finding genetic, environmental and behavioral factors associated with diabetes. In an early phase of this project, Professor Liang’s research team has developed X-test family, a series of fuzzy-theory-based methodologies to effectively measure the divergence of gene microarray data between diabetic and non-diabetic groups. Now this team is planning to further develop X-test family to handle categorical and heterogeneous data which are collected clinically or through survey.
Click here to read more.