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 language | English |
|---|---|
| Title of host publication | MEDINFO 2007 - Proceedings of the 12th World Congress on Health (Medical) Informatics |
| Subtitle of host publication | Building Sustainable Health Systems |
| Pages | 571-575 |
| Number of pages | 5 |
| Volume | 129 |
| Publication status | Published - 2007 Dec 1 |
| Event | 12th World Congress on Medical Informatics, MEDINFO 2007 - Brisbane, QLD, Australia Duration: 2007 Aug 20 → 2007 Aug 24 |
Other
| Other | 12th World Congress on Medical Informatics, MEDINFO 2007 |
|---|---|
| Country | Australia |
| City | Brisbane, QLD |
| Period | 07/8/20 → 07/8/24 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Biomedical Engineering
- Health Informatics
- Health Information Management
Cite this
}
Risk stratification for LDL cholesterol using induction technique. / Ho, Seung Hee; Park, Hyun Young; Jang, Yangsoo; Jee, Sun Ha.
MEDINFO 2007 - Proceedings of the 12th World Congress on Health (Medical) Informatics: Building Sustainable Health Systems. Vol. 129 2007. p. 571-575.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Risk stratification for LDL cholesterol using induction technique
AU - Ho, Seung Hee
AU - Park, Hyun Young
AU - Jang, Yangsoo
AU - Jee, Sun Ha
PY - 2007/12/1
Y1 - 2007/12/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=80052916002&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80052916002&partnerID=8YFLogxK
M3 - Conference contribution
SN - 9781586037741
VL - 129
SP - 571
EP - 575
BT - MEDINFO 2007 - Proceedings of the 12th World Congress on Health (Medical) Informatics
ER -