Journals / Anadolu Kardiyoloji Dergisi / 2005 / Cilt: 5 - Sayı: 1

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

Hipertansiyonun tahmini için çoklu tahmin modellerinin karşılaştırılması (Sinir ağları, lojistik regresyon ve esnek ayırma analizleri)

Pages
24–28
Publication Date
2022-10-10
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

ROC curve areas of SA and LR, and SA and EAA were statistically different (p

📌 3 Key Takeaways

🎯
Objective & Hypothesis: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.
📊
Key Findings & Data:The data were collected from Cardiology Clinic of Trakya University Medical Faculty in Turkey, 2001.
💡
Conclusion & Impact:ROC curve areas of SA and LR, and SA and EAA were statistically different (p
🔬Design:Modeling & Simulation
📍Scope:2001 Verileri
⚙️Variables:Domain Parameters

Abstract

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 ne-ural 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

Özet

Amaç: Bu çalışmada, primer hipertansiyonun tahminlenmesinde lojistik regresyon analizi (LR, Logistic Regression Analysis), esnek diskriminant analizi (EAA, Flexible Discriminant Analysis) ve sinir ağları (SA, Neural Networks) yöntemlerinin karşılaştırılması amaçlandı. Yöntemler: Aile hikayesi, lipoprotein A, trigliserid, sigara kullanımı ve vücut kitle indeksi tahminleyici değişkenler olarak ele alındı. Veriler, 2001 yılında Trakya Üniversitesi Tıp Fakültesi Kardiyoloji Kliniğinden elde edildi. Kontrol ve hipertansiyonlu bireylerden oluşan grupların tahminlenmesinde LR, EAA ve SA yöntemleri kullanıldı. Modellerin performansları ROC analiz ile karşılaştırıldı. Bulgular: Bütün modellerin ROC eğrisi altındaki alanları 0.793-0.984 aralığında yer aldı. Sinir ağlarının duyarlılık, özgüllük ve doğruluk oran-ları %90'dan daha yüksek bulundu. Sinir ağları ve LR ile SA ve EAA'nın ROC eğrisi altında kalan alanları istatistiksel olarak farklı bulundu (sırasıyla, p

🔖

Cite This Article

TÜRE, M., KURT, İ., KÜRÜM, T., YAVUZ, E. (2022). Comparison of multiple prediction models for hypertension (Neural network, logistic regression and flexible discriminant analyses). Anadolu Kardiyoloji Dergisi, Cilt: 5 - Sayı: 1, 24–28. https://ajindex.com/articles/437364

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (18)

  1. Jo I, Ahn Y, Lee J, Shin KR, Lee HK, Shin C. Prevalence, awareness, treatment, control and risk factors of hypertension in Korea: The Ansan Study. J Hypertens 2001
  2. Cheitlin MD. Systemic hypertension. In: Sokolow M, McIlroy MB, editors. 6th ed. Clinical Cardiology. Norwalk, Connecticut: Appleton & Lange
  3. p.247-51. 3. Hall WD, Wollam G, Tuttle EP Jr. Diagnostic evaluation of the patient with systemic arterial hypertension: An overview. In: Schlant RC, Alexander RW, O’Rourke RA, Roberts R, Sonnenblick E, editors. 8th ed. Hurst`s the Heart. New York: McGraw-Hill Inc.
  4. p.1403-25. 4. Cruickshank JM, Neil-Dwyer G, Dorrance DE, Hayes Y, Patel S. Acute effects of smoking on blood pressure and cerebral blood flow. J Hum Hypertens 1989
  5. Williams RR. Will gene markers predict hypertension? Hypertension 1989
  6. Williams RR, Hunt SC, Hasstedt SJ, et al. Current knowledge regarding the genetics of human hypertension. J Hypertens 1989
  7. 7(Suppl): S8-13. 7. Speers MA, Kasl SV, Freeman DH Jr, Ostfeld AM. Blood pressure concordance between spouses. Am J Epidemiol 1986
  8. Elfor J, Phillips A, Thomson AG, Shaper AG. Migration and geographic variations in blood pressure in Britain. BMJ 1990
  9. Folkow R. The pathophysiology of hypertension. Differences between young and elderly patients. Drugs 1993
  10. 46 (suppl 2): 3-7. 10. Kaplan NM. Clinical hypertension. Baltimore: Williams and Wilkins
  11. Schieken RM. Genetic factors that predispose the child to develop hypertension. Pediatr Clin North Am 1992
  12. Hosmer DW, Lemeshow S. Applied logistic regression. New York: John Wiley & Sons, 2000. 13. Özdamar K. Paket programlar ile istatistiksel veri analizi 1. Eskişehir: Kaan Kitabevi
  13. Sharma S. Applied multivariate techniques. New York: John Wiley & Sons
  14. Özdamar K. Paket programlar ile istatistiksel veri analizi 2. Eskişehir: Kaan Kitabevi
  15. Hastie T, Tibshirani R, Buja A. Flexible discriminant and mixture models. In: Kay J & Titterington D, editors. Proceedings of "Neural Networks and Statistics" conference, Edinburgh: Oxford University Press
  16. p.1-23. 17. Hastie T, Tibshirani R, Buja A. Flexible discriminant analysis by optimal scoring. J Am Stat Assoc 1994
  17. Hastie T, Tibshirani R. Discriminant analysis by Gaussian mixtures. J Roy Stat Soc B 1996
  18. 58, 155-76. 19. Kim H, Loh W-Y. Classification trees with bivariate linear discriminant node