ISSN 2149-2263 | E-ISSN 2149-2271 Home      
 
Volume : 22 Issue : 2
Current Issue Archive Popular Article Ahead of Print

   
Quick Search





 
Comparison of multiple prediction models for hypertension (Neural network, logistic regression and flexible discriminant analyses) [Anatol J Cardiol]
Anatol J Cardiol. 2005; 5(1): 24-28

Comparison of multiple prediction models for hypertension (Neural network, logistic regression and flexible discriminant analyses)

Mevlüt Türe1, İmran Kurt2, Ebru Yavuz3, Turhan Kürüm4
1Department of Biostatistics Medical Faculty, Trakya University, Edirne
2Department of Biostatistics, Medical Faculty, Eskişehir Osmangazi University, Eskişehir, Turkey
3Trakya Üniversitesi Tıp Fakültesi Biyoistatistik Anabilim Dalı, Edirne
4Department of Cardiology, School of Medicine, Trakya University, Edirne

Objective: In this study, we compared performances of logistic regression analysis (LR), flexible discriminant analysis (EAA) and neural networks (SA) in prediction of primary hypertension. Methods: Predictor variables were family history, lipoprotein A, triglyceride, smoking and body mass index. The data were collected from Cardiology Clinic of Trakya University Medical Faculty in Turkey, 2001. Logistic regression analysis, flexible discriminant analysis and neural networks were used for prediction of control and hypertension groups. Comparison of the performance of all models was done using receiver operating characteristic (ROC) curve analysis. Results: All models had areas under the ROC curve in the range of 0.793-0.984 and SA had sensitivity, specificity, and accuracy greater than 90% at ideal threshold. ROC curve areas of SA and LR, and SA and EAA were statistically different (p<0.001 and p<0.001 respectively), while ROC curve areas of EAA and LR did not differ (p>0.05). Conclusion: We concluded that family history, lipoprotein A, triglyceride, smoking and body mass index variables can be used for prediction of control and hypertension groups with statistically better performance of SA over LR and EAA.

Keywords: Logistic regression analysis, neural networks, flexible discriminant analysis, ROC curve


Mevlüt Türe, İmran Kurt, Ebru Yavuz, Turhan Kürüm. Comparison of multiple prediction models for hypertension (Neural network, logistic regression and flexible discriminant analyses). Anatol J Cardiol. 2005; 5(1): 24-28


TOOLS
Full Text PDF
Print
Download citation
RIS
EndNote
BibTex
Medlars
Procite
Reference Manager
Share with email
Share


Similar articles
PubMed
Google Scholar




 
 
KARE Publishing | Copyright © 2018 Turkish Society of Cardiology