Interdisciplinary Bio Central
 
Full Report (Bioinformatics/Computational biology/Molecular modeling)

Finding key factors of metabolic syndrome in lifestyle with National Health and Nutrition Examination Survey (NHANES)
Seunghwan Jung1, Suhyun Ha2 and Doheon Lee2,*
1Department of Biological Sciences, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 305-701, South Korea
2Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 305-701, South Korea
*Corresponding author
  Received : April 16, 2015
  Accepted : May 15, 2015
  Published : May 29, 2015
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Main text PDF(2214KB)
(pre-print version)
Synopsis

Metabolic syndrome is combination of factors that raise the risk of cardiovascular disease and diabetes mellitus. Previous studies suggested that metabolic syndrome is associated with lifestyle. Identification of associated lifestyle factors with metabolic syndrome would help its prevention and management. With the National Health and Nutrition Examination Survey (NHANES) data from 1999 to 2012, this study develops a classifier to identify metabolic syndrome patients. Lifestyle data set from NHANES is based on demographic data, dietary data, and questionnaire data. According to the US National Cholesterol Education Program (NCEP), metabolic syndrome has four states; central obesity, pre-diabetes mellitus, prehypertension, and dyslipidemia. Associated key factors are identified through feature selection out of 217 attributes based on information gain. Most attributes show no significant association with metabolic syndrome except age. We developed a decision tree classifier to investigate associations between attributes, and age is the most important attribute that contribute the decision tree as well. Interestingly, the decision tree shows several different features are associated with metabolic syndrome at different ages. Sleep disorders are the most significant factor for young persons under the age of 33, while exercise habit, gender and ethnicity are the most significant factors for elders over the age of 50. Consequently, this study can give insight into prevention and treatment of metabolic syndrome.

Keyword: metabolic syndrome, NHANES, decision tree, information gain, lifestyle
IBC   ISSN : 2005-8543   Contact IBC