Risk stratification for LDL cholesterol using induction technique

Seung Hee Ho, Hyun Young Park, Yang Soo Jang, Sun Ha Jee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

We identified the combined patterns of LDL cholesterol risk factors including biometric, environmental and genetic factors using induction technique. In this hospital based cardiovascular genome study of Korean men and women, we found that CART (classification and regression tree) was a better method to predict LDL cholesterol compared to the regression method. The CART had a better prediction ability than the multiple regression for male and female, respectively. We also identified combined patterns of LDL cholesterol risk factors and segment specific information for LDL cholesterol management using induction rules. The CART method provided more detailed results according to each segmentation and subgroup. In addition, we demonstrated how the CART algorithm could be used in risk assessment and target segmentation of LDL cholesterol management.

Original languageEnglish
Title of host publicationMEDINFO 2007 - Proceedings of the 12th World Congress on Health (Medical) Informatics
Subtitle of host publicationBuilding Sustainable Health Systems
PublisherIOS Press
Pages571-575
Number of pages5
ISBN (Print)9781586037741
Publication statusPublished - 2007
Event12th World Congress on Medical Informatics, MEDINFO 2007 - Brisbane, QLD, Australia
Duration: 2007 Aug 202007 Aug 24

Publication series

NameStudies in Health Technology and Informatics
Volume129
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365

Other

Other12th World Congress on Medical Informatics, MEDINFO 2007
Country/TerritoryAustralia
CityBrisbane, QLD
Period07/8/2007/8/24

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Fingerprint

Dive into the research topics of 'Risk stratification for LDL cholesterol using induction technique'. Together they form a unique fingerprint.

Cite this