Hipertansiyon Tahmini İçin Temel Bileşen Analizinin Kullanımı

Amaç: Otuz yaş ve üzerindeki 150 hastadan, hipertansiyona etki etmesi muhtemel bilgilerden; cinsiyet, yaş, lipid profili, trigliserid, vücut kütle indeksi, ürik asit ve sigara kullanımı verileri toplanmış ve bir hipertansiyon veritabanı oluşturulmuştur. Bu kişilerden 65’i sağlıklı, geriye kalan 85 kişi ise hipertansiyon hastasıdır. Bu veritabanından hipertansiyon hastalığının Temel Bileşen Analizi kullanılarak tahmin edilmesi amaçlanmıştır. Gereç ve Yöntem: Naive Bayes, Çok Katmanlı Algılayıcı Ağ (ÇKA), Karar Tablosu ve C4.5 sınıflandırma algoritmaları uygulanmış, ardından Temel Bileşenler Analizi uygulanarak hipertansiyon veritabanının boyutu indirgenmiş ve aynı sınıflandırma algoritmaları tekrar uygulanmış ve sonuçlar karşılaştırılmıştır. Bulgular: Aynı şartlarda işleme sokulan algoritmalardan en başarılı sonucu %88 doğruluk oranıyla Naive Bayes sınıflandırıcısı vermiştir. Naive Bayes sınıflandırıcısını sırasıyla %85,33 başarı oranıyla Karar Tablosu algoritması, %82,67 başarı oranıyla ÇKA algoritmaları takip etmiştir. Hipertansiyon veritabanına TBA analizi uygulanıp, aynı şartlarda aynı algoritmalar tekrar işleme sokulup, TBA uygulanmayan sonuçlarla kıyaslandığında ise, C4.5 algoritması normalden %4 daha başarılı sonuç vererek en başarılı algoritma olmuştur. C4.5 algoritmasını sırasıyla %2,67 daha başarılı sonuç veren Karar Tablosu algoritması ve %1,33 daha başarılı sonuç veren ÇKA izlemiştir. Sonuç: Naive Bayes sınıflandırıcı haricindeki tüm algoritmalarda Temel Bileşenler Analizi’nin sınıflandırma başarısını artırdığı görülmüştür.

Principal Component Analysis Using For Estimating Hypertension

Aim: 150 patients which aged 30 years and over were exposed to possible hypertension; age, gender, lipid profile, body mass index, triglyceride , cigarette use and uric acid data are collected and hypertension database are created. 65 people is healthy, and the remaining one is suffering from hypertension. It is aimed to estimate the hypertension disease from this database using the Principal Component Analysis. Material and Method: Decision Table, Naive Bayes, C4.5 and Multilayer Perceptron Network(MLP) classification algorithms are applied to this database, then the size of the hypertension database is reduced by applying Principal Component Analysis and the same methods are applied again and the results are compared. Results: The most successful result of the algorithms that were processed under the same conditions gave Naive Bayes classifier with 88% accuracy. Naive Bayes classifier was followed by the Decision Table algorithm with success rate of 85.33%, and ÇKA algorithms with success rate of 82.67%. If the TBA analysis is applied to the hypertension database and the same algorithms are re-processed under the same conditions and the TBA is compared to the untreated results, the C4.5 algorithm is normally the most successful algorithm with 4% more successful results. The Decision Table algorithm, which yielded C4.5 algorithm with 2.67% more success rate respectively, and ÇKA which has a more successful result than 1.33%. Conclusion: Algorithms except the Naive Bayes algorithm, improved their classification accuracy rate.

Kaynakça

A global brief on hypertension | A global brief on Hyper tension. (2013). Retrieved from http://apps.who.int/iris/bitstream/10665/79059/1/ WHO_ DCO_WHD_2013.2_eng.pdf?ua=1

Abd El Baky Mahmoud, M., Shaaban, M. A. A., & Ali Ramzy, A. (2018). Clinical role of serum Copeptin in acute coronary syndrome. Egyptian Heart Journal, 70(3), 155–159. https://doi.org/10.1016/j.ehj.2018.04.008

Abdi, H., & Williams, L. J. (2010, July 1). Principal component analysis. Wiley Interdisciplinary Reviews: Computational Statistics. John Wiley & Sons, Ltd. https://doi.org/10.1002/wics.101

Alderman, M. H. (2004). JNC 7: Brief summary and critique. In Clinical and Experimental Hypertension. https://doi.org/10.1081/CEH-200032158

Almazyad, A. S., Ahamad, M. G., Siddiqui, M. K., & Almazyad, A. S. (2010). Effective hypertensive treatment using data mining in Saudi Arabia. Journal of Clinical Monitoring and Computing, 24(6), 391–401. https://doi.org/10.1007/s10877-010-9260-2

Azuaje, F. (2006). Witten IH, Frank E: Data Mining: Practical Machine Learning Tools and Techniques 2nd edition: San

Francisco: Morgan Kaufmann Publishers; 2005:560. ISBN 0-12-088407-0, £34.99. BioMedical Engineering OnLine. https://doi.org/10.1186/1475-925X-5-51

Bishop, C. (1995). Neural networks for pattern recognition. Retrieved from https://books.google.com/books?hl=tr&lr=&id=T0S0BgAAQBAJ&oi=fnd&pg=PP1&dq=Bishop+C.+Neural+Networks+for+Pa ttern+Recognition+1995%3B+Oxford+Univ.+Press,+N+Y.&ots=jN20qL8Dod&sig=2-F-ubwZLqvUlNsroDpVxQ1Dt6w

Carretero, O. A., & Oparil, S. (2000). Essential Hypertension. Circulation, 101(3), 329–335. https://doi.org/10.1161/01.CIR.101.3.329

Chae, Y. M., Ho, S. H., Cho, K. W., Lee, D. H., & Ji, S. H. (2001). Data mining approach to policy analysis in a health insurance domain. International Journal of Medical Informatics, 62(2–3), 103–111. https://doi.org/10.1016/S1386-5056(01)00154-X

Chalmers, J., MacMahon, S., Mancia, G., Whitworth, J., Beilin, L., Hansson, L., … Clark, T. (1999). 1999 World Health Organization-International Society of Hypertension Guidelines for the management of hypertension. Guidelines sub-committee of the World Health Organization. Clinical and Experimental Hypertension (New York, N.Y. : 1993), 21(5–6), 1009—1060. https://doi.org/10.3109/10641969909061028

Demuth, H., Beale, M., Jess, O. De, & Hagan, M. (2014). Neural network design. Retrieved from https://dl.acm.org/citation.cfm?id=2721661

Haykin, S. (2007). Neural networks: a comprehensive foundation. Retrieved from https://dl.acm.org/citation.cfm?id=1213811

KÖKVER, Y., BARIŞÇI, N., ÇİFTÇİ, A., & EKMEKÇİ, Y. (2014). DETERMINING AFFECTING FACTORS OF HYPERTENSION WITH DATA MINING TECHNIQUES. Qualitative Studies, 9(2), 15–25. https://doi.org/10.12739/NWSA.2014.9.2.1A0352

Li, J., Wang, L., Wang, Q., Xin, Z., Liu, Y., & Zhao, Q. (2018). Diagnostic value of carotid artery ultrasound and hypersensitive C-reactive protein in Type 2 diabetes mellitus patients with acute myocardial infarction in Chinese population. Medicine (United States), 97(41). https://doi.org/10.1097/MD.0000000000012334

Sancho-Gómez, J. L., García-Laencina, P. J., & Figueiras-Vidal, A. R. (2009). Combining missing data imputation and pattern classification in a multi-layer perceptron. Intelligent Automation and Soft Computing, 15(4), 539–553. https://doi.org/10.1080/10798587.2009.10643048

Sehn Körting, T., & Sehn Korting, T. (n.d.). C4.5 algorithm and Multivariate Decision Trees GeoDMA-Geographic Data Mining Analyst View project Brazil Data Cube View project C4.5 algorithm and Multivariate Decision Trees. researchgate.net. Retrieved from https://www.researchgate.net/publication/267945462

Siddiqui, M. K., & Aljumah, A. A. (2014). Hypertension Interventions using Classification Based Data Mining. Research Journal of Applied Sciences, Engineering and Technology, 7(17), 3593–3602. Retrieved from http://www.mayoclinic.com/health/high-

Tang, L., & Zhou, X. J. (2019). Diffusion MRI of cancer: From low to high b-values. Journal of Magnetic Resonance Imaging, 49(1), 23–40. https://doi.org/10.1002/jmri.26293

Ture, M., Kurt, I., Turhan Kurum, A., & Ozdamar, K. (2005). Comparing classification techniques for predicting essential hypertension. Expert Systems with Applications, 29(3), 583–588. https://doi.org/10.1016/j.eswa.2005.04.014

Türk, F., Barişçi, N., Çiftçi, A., & Ekmekçi, Y. (2015). Comparison of Multi Layer Perceptron and Jordan Elman Neural Networks for Diagnosis of Hypertension. Intelligent Automation and Soft Computing, 21(1), 123–134. https://doi.org/10.1080/10798587.2014.959312

Wang, G., Yu, H., COMPUTERS, D. Y.-C. J. O., & 2002, undefined. (n.d.). Decision table reduction based on conditional information entropy. Cjc.Ict.Ac.Cn. Retrieved from http://cjc.ict.ac.cn/eng/qwjse/view.asp?id=1076

Wang, J. (2010). Encyclopedia of Data Warehousing and Mining, Second Edition. Encyclopedia of Data Warehousing and Mining, Second Edition. Information Science Reference. https://doi.org/10.4018/978-1-60566-010-3

Kaynak Göster