Enhanced Neutrosophic Set and Machine Learning Approach for  Kidney Disease Prediction

Humam M Al-Doori; Tareef S Alkellezli; Ahmed Abdelhafeez; Mohamed Eassaa; Mohamed S. Sawah; Ahmed A El-Douh

Authors

Humam M Al-Doori Cybersecurity Sciences Department, College of Science, Ashur University, Baghdad, Iraq
Tareef S Alkellezli Cybersecurity Engineering Department, College of Engineering, Ashur University, Baghdad, Iraq
Ahmed Abdelhafeez Computer Science Department, Faculty of Information System and Computer Science, October 6 University, Giza, 12585, Egypt
Mohamed Eassaa Computer Science Department, Faculty of Information System and Computer Science, October 6 University, Giza, 12585, Egypt
Mohamed S. Sawah Department of Computer Science, Faculty of Information Technology, Ajloun National University P.O.43, Ajloun 26810, Jordan
Ahmed A El-Douh Cybersecurity Technology Engineering Department, College of Engineering Technology, Ashur University, Baghdad, Iraq

Keywords:

Neutrosophic Sets; Machine Learning Models; Kidney Disease; Uncertainty Models; Logistic Regression.

Abstract

Kidney disease (KD) is a gradually increasing global health concern. It is a chronic illness linked to higher
rates of morbidity and mortality, a higher risk of cardiovascular disease and numerous other illnesses, and
expensive medical expenses. The machine learning (ML) models are applied for KD prediction with higher
accuracy and precision. The KD dataset has uncertainty and vague information, so, we used the
neutrosophic set (NS) to deal with vague and uncertainty information in the KD dataset. The KD dataset is
converted into the N-KD dataset with three membership functions: truth, indeterminacy, and falsity. Three
ML models are used in this study such as logistic regression (LR), support vector machine (SVM), and k
nearest neighbor (KNN). These ML models are applied to the N-KD dataset. The results show the LR has
higher accuracy and precision on the N-KD dataset than the original KD dataset.

DOI: 10.5281/zenodo.14720474