| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 546.55 KB | Adobe PDF |
Advisor(s)
Abstract(s)
Introduction: Familial Hypercholesterolemia (FH) is a monogenic disorder of lipid metabolism, resulting
in severe dyslipidemia and increased risk of cardiovascular disease. Simon Broome
(SB) criteria for the diagnostic of FH are among the most frequently used in clinical
setting, and are based on elevated total (CT) and low density lipoprotein (LDL-c)
cholesterol levels, presence of tendinous xanthomas and family history, although only
genetic testing can confirm the diagnostic. The main purpose of this work was to
develop an alternative classification model for FH based on a modified version of the
classic decision tree (DT), using several biochemical indicators as predictor variables: CT,
LDL-c, high density lipoprotein cholesterol (HDL-c) and triglycerides (TG) concentrations.
The DT model was fitted to sample data, and correspondent operating characteristics
were compared to the ones obtained with the biochemical indicators used in SB criteria,
through bootstrap resampling techniques.
Description
The research by João Albuquerque was supported by the programmme Norte2020 (operação NORTE-08-5369-FSE-000018); The research by Marília Antunes was supported by national funds through FCT under the project UID/MAT/00006/2013.
Keywords
Familial Hypercholesterolemia Dyslipidemia Decision Trees Simon Broome Criteria Operating Characteristics Doenças Cardio e Cérebro-vasculares Hipercolesterolemia Familiar
Pedagogical Context
Citation
Publisher
Instituto Nacional de Saúde Doutor Ricardo Jorge, IP
