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

Basit Öğe Kaydı
dc.authorscopusid55882854000
dc.authorscopusid8668792500
dc.authorscopusid6603969746
dc.authorscopusid6601908707
dc.contributor.authorTüre M.
dc.contributor.authorKurt I.
dc.contributor.authorYavuz E.
dc.contributor.authorKürüm T.
dc.date.accessioned2024-06-12T10:28:57Z
dc.date.available2024-06-12T10:28:57Z
dc.date.issued2005
dc.description.abstractObjective: 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.en_US
dc.identifier.endpage28en_US
dc.identifier.issn1302-8723
dc.identifier.issue1en_US
dc.identifier.pmid15755697en_US
dc.identifier.scopus2-s2.0-14944340294en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.startpage24en_US
dc.identifier.urihttps://hdl.handle.net/20.500.14551/17495
dc.identifier.volume5en_US
dc.indekslendigikaynakScopusen_US
dc.indekslendigikaynakPubMeden_US
dc.language.isotren_US
dc.relation.ispartofAnadolu Kardiyoloji Dergisien_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectFlexible Discriminant Analysis; Logistic Regression Analysis; Neural Networks; Roc Curveen_US
dc.subjectLipoprotein A; Triacylglycerol; Accuracy; Adult; Article; Artificial Neural Network; Body Mass; Cigarette Smoking; Controlled Study; Discriminant Analysis; Experimental Model; Family History; Human; Hypertension; Information Processing; Intermethod Comparison; Logistic Regression Analysis; Major Clinical Study; Prediction; Receiver Operating Characteristic; Sensitivity And Specificity; Turkey (Republic); Body Mass Index; Case-Control Studies; Discriminant Analysis; Female; Genetic Predisposition To Disease; Humans; Hypertension; Lipoprotein(A); Logistic Models; Male; Middle Aged; Models, Statistical; Neural Networks (Computer); Predictive Value Of Tests; Roc Curve; Sensitivity And Specificity; Smoking; Triglyceridesen_US
dc.titleComparison of multiple prediction models for hypertension (Neural network, logistic regression and flexible discriminant analyses)en_US
dc.title.alternativeHipertansiyonun tahmini için çoklu tahmin modellerinin karşilaştirilmasi (Sinir a?lari, lojistik regresyon ve esnek ayirma analizleri)en_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
PubMed İndeksli Yayınlar Koleksiyonu