Subspace Discovery for Disease Management : A Case Study in Metabolic Syndrome

This paper identifies key subspaces for better disease management. Disease affects individuals differently based on features such as age, race, and gender. The authors use data mining methods to discover which key factors of a disease are more relevant for particular strata of the population using b...
Ausführliche Beschreibung

This paper identifies key subspaces for better disease management. Disease affects individuals differently based on features such as age, race, and gender. The authors use data mining methods to discover which key factors of a disease are more relevant for particular strata of the population using bin wise clustering. The authors use a case study on Metabolic Syndrome (MetS). MetS is a combination of abnormalities that occur in the body during the processing of food and nutrients. A number of definitions have been studied to classify MetS. No clear criterion exists that can generally fit into a single satisfactory protocol. This domain encompasses a variety of demographics in society, leading to an implication that different criteria may be appropriate for different demographic strata. The authors address this issue and identify the cross section of demographic strata and the disease characteristics that are critical for understanding the disease in that subset of the population. Findings in real world NHANESIII data support this hypothesis, thus the approach can be used by clinical scientists to narrow down specific demographic pools to further study impacts of key MetS characteristics Ausführliche Beschreibung