EVALUATION OF PERFORMANCE OF CLASSIFICATION ALGORITHMS IN PREDICTION OF HEART FAILURE DISEASE

Cevdet Coşkun; Fatma Kuncan

doi:10.17780/ksujes.1144570

TR EN

KALP YETMEZLİĞİ HASTALIĞININ TAHMİN EDİLMESİNDE SINIFLANDIRICI ALGORİTMALARININ PERFORMANSLARININ DEĞERLENDİRİLMESİ

Öz

Kalp Yetmezliği Tahmin veri seti kullanılarak makine öğrenmesi yöntemlerinden Gaussian Naive Bayes, Support Vector Machines, Linear Discriminant Analysis, Decision Tree ve Random Forest sınıflandırıcı algoritmalarının başarı oranları ve performansları değerlendirilmiştir. Data set üzerinde öncelikle veri ön işleme tekniklerinde label encoder yöntemi kullanılmıştır. Data setteki katalog veriler (5 adet) sayısal verilere dönüştürülmüştür. Ayrıca bir alandaki verilerde negatif değerlerin olduğu gözlemlenmiş ve bu durum min-max dönüşüm yöntemleri ile 0 - 1 aralığındaki değerlere dönüştürülmüştür. Yapılan ön işlemlerden sonra sınıflandırma algoritmaları ile analizler yapılmıştır. Bu analizler neticesinde bir ensemble (topluluk) sınıflandırıcı olan random forest algoritması ile %90,76 oranında bir başarı elde edilmiştir. Yapılan çalışmada verilerin %80’i eğitim, %20’si test için kullanılmıştır. Test için kullanılan 184 tane verinin 102 tanesi kalp yetmezliği hastalığı olanlar, 72 tanesi ise hastalığı olmayanlardan oluşmaktadır. Random forest algoritmasının kalp yetmezliği hastalığı olanları tahminlime başarısı %93,1 (95 gözlem), hastalığı olmayanları tahminlime başarısı ise %87,8 (72 gözlem) olarak gerçekleşmiştir.

Anahtar Kelimeler

EVALUATION OF PERFORMANCE OF CLASSIFICATION ALGORITHMS IN PREDICTION OF HEART FAILURE DISEASE

Abstract

Success rates and performances of Gaussian Naive Bayes, Support Vector Machines, Linear Discriminant Analysis, Decision Tree and Random Forest classifier algorithms from machine learning methods were evaluated using the Heart Failure Prediction dataset. Label encoder method was used primarily in data preprocessing techniques on the data set. Catalog data (5 pieces) in the data set have been converted into numerical data. In addition, it was observed that there were negative values in the data in a field and this situation was converted to values in the range of 0 - 1 with min-max conversion methods. After the pre-processing, analyzes were made with classification algorithms. As a result of these analyzes, a success rate of 90.76% was achieved with the random forest algorithm, which is an ensemble classifier. In the study, 80% of the data was used for training and 20% for testing. Of the 184 data used for the test, 102 of them were patients with heart failure and 72 of them were from those without the disease. The success of the random forest algorithm in estimating those with heart failure disease was 93.1% (95 observations), and the success in predicting those without the disease was 87.8% (72 observations).

Keywords

Thanks

This study was carried out in Siirt University Engineering Faculty Human-Computer Interaction Laboratory. The authors of this article thank the Human-Computer Interaction Laboratory staff for their support.

References

Ali Bagheri, M., Montazer, G. A., & Escalera, S. (2012). Error correcting output codes for multiclass classification: application to two image vision problems. The 16th CSI International Symposium on Artificial Intelligence and Signal Processing (AISP 2012), 508–513.
Coşar, M., & Deniz, E. (2021). Makine Öğrenimi Algoritmalar Kullanarak Kalp Hastalklarnn Tespit Edilmesi. Avrupa Bilim ve Teknoloji Dergisi, 28, 1112–1116.
Heart Failure: Investigation of an Epidemic. (2013). https://doi.org/10.1161/CIRCRESAHA.113.300268
Heart Failure Prediction Dataset. (n.d.). www.kaggle.com.
Ng, A., & Jordan, M. (2001). On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes. Advances in Neural Information Processing Systems, 14.
Onat, A. (2001). Risk factors and cardiovascular disease in Turkey. In Atherosclerosis (Vol. 156). www.elsevier.com/locate/atherosclerosis
Reddy, V. S. K., Meghana, P., Reddy, N. V. S., & Rao, B. A. (2022). Prediction on Cardiovascular disease using Decision tree and Na\"\ive Bayes classifiers. Journal of Physics: Conference Series, 2161(1), 12015.
Srinivas, P., & Katarya, R. (2022). hyOPTXg: OPTUNA hyper-parameter optimization framework for predicting cardiovascular disease using XGBoost. Biomedical Signal Processing and Control, 73, 103456.

Details

Primary Language

English

Subjects

Computer Software

Journal Section

Research Article

Authors

Cevdet Coşkun
0000-0002-1351-0590
Türkiye

Fatma Kuncan ^*
0000-0003-0712-6426
Türkiye

Publication Date

December 3, 2022

Submission Date

July 18, 2022

Acceptance Date

September 26, 2022

Published in Issue

Year 2022 Volume: 25 Number: 4

DOI

https://doi.org/10.17780/ksujes.1144570

IZ

https://izlik.org/JA98EF49RZ

Cite

RIS / Bibtex

APA

Coşkun, C., & Kuncan, F. (2022). EVALUATION OF PERFORMANCE OF CLASSIFICATION ALGORITHMS IN PREDICTION OF HEART FAILURE DISEASE. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 25(4), 622-632. https://doi.org/10.17780/ksujes.1144570

Cited By

Early-stage heart failure disease prediction with deep learning approach

Journal of Scientific Reports-A

https://doi.org/10.59313/jsr-a.1341663

Exploring the Frontiers of Unsupervised Learning Techniques for Diagnosis of Cardiovascular Disorder: A Systematic Review

IEEE Access

https://doi.org/10.1109/ACCESS.2024.3468163

Development of a Lumped Parameter Model of Human Whole Body Circulatory Loop

IEEE Access

https://doi.org/10.1109/ACCESS.2024.3491112

MULTILAYER ANALYSIS OF NICOTINE-INDUCED GENE EXPRESSION ALTERATIONS IN BREAST CANCER CELLS USING CLUSTERING AND SUPERVISED LEARNING METHODS

Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi

https://doi.org/10.17780/ksujes.1730962