A Neutrosophic Logic Ruled Based Machine Learning Approaches for  Chronic Kidney Disease Risk Prediction

Bhabani S. Mohanty; Krishna Priya R; Liya Alias; R. Vijaya Kumar Reddy; Prasanta Kumar  Raut; Samson Isaac; Manibharathi.D; C. Saravanakumar; Nihar Ranjan Panda; Said  Broumi

Authors

Bhabani S. Mohanty Department of Statistics and Applied Mathematics, Central University of Tamil Nadu, India.
Krishna Priya R Research and Consultancy Department, University of Technology and Applied Sciences, Musandam, P.O. Box: 12, Postal Code:811, Khasab, Governorate of Musandam, Sultanate of Oman.
Liya Alias College of Engineering and Technology, University of Technology and Applied Science Shinas, Oman.
R. Vijaya Kumar Reddy Department of CSE, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Guntur, AP, India.
Prasanta Kumar Raut Department of Mathematics, Trident Academy of Technology, Bhubaneswar, Odisha, India.
Samson Isaac Division of Biomedical Engineering, Karunya Institute of Technology and Sciences, Coimbatore, India.
Manibharathi.D Department of Electronics and Communication Engineering, Government College of Engineering, Salem, Tamilnadu, India.
C. Saravanakumar Department of Electronics and Communication Engineering, SRM Valliammai Engineering College, Kattankulathur, Chengalpattu, Tamilnadu, India.
Nihar Ranjan Panda Department of Medical Research. IMS & SUM Hospital, SOA Deemed to be university.
Said Broumi 0Laboratory of Information Processing, Faculty of Science Ben M’Sik, University Hassan II, Casablanca, Morocco

Keywords:

Classifier; Kidney Disease; Neutrosophic Logic; Risk Prediction Model

Abstract

Chronic kidney disease (CKD) represents a significant global health challenge in
society, and early detection of risk is essential for on-time treatment and intervention.
This research suggests a novel machine-learning technique to create a reliable and
accurate CKD risk prediction model by combining neutrosophic logic with various
classification algorithms. We use neutrosophic logic to address the inherent imprecision
and uncertainty in medical data, resulting in a more realistic portrayal of real-world
scenarios. We measure the effectiveness of the proposed neutrosophic logic-based
models using various metrics, including precision, specificity, and sensitivity. The
results show that the neutrosophic logic method is better than traditional machine
learning methods at finding people who are likely to develop CKD because it is more
accurate and stable. This study illustrates the potential for incorporating neutrosophic
logic into machine learning frameworks to improve risk prediction in medical fields.

DOI: 10.5281/zenodo.14507089