Prediction of sleep disorders using Novel decision support  neutrosophic based machine learning models

Nihar Ranjan Panda; Surapati Paramanik; Prasanta Kumar Raut; Ruchi Bhuyan

Authors

Nihar Ranjan Panda Department of Medical Research. IMS & SUM Hospital, SOA Deemed to be university, India.
Surapati Paramanik Department of Mathematics, Nandalal Ghosh B.T. College Panpur, Narayanpur, Dist- North 24 Parganas, W.B.-743126, India.
Prasanta Kumar Raut Department of Mathematics, Trident Academy of Technology, Bhubaneswar, Odisha, India.
Ruchi Bhuyan Institute of Dental science, SOA Deemed to be university, India

Keywords:

Neutrosophic sets, Machine Learning, Uncertainty handling, Sleep disorder, Classification

Abstract

Sleep disorders significantly impact human health, productivity, and overall
quality of life. Early diagnosis and prediction of these disorders are crucial for effective
treatment. This study introduces a novel decision support system utilizing a neutrosophic
machine learning prediction model to enhance the accuracy and reliability of sleep disorder
diagnosis. Unlike traditional machine learning approaches, our model integrates neutrosophic
logic, which considers three values—truth, indeterminacy, and falsity—to effectively handle
uncertainty and inconsistencies in sleep-related data. The proposed model processes diverse
patient information, including demographics, clinical parameters, and polysomnography
details, ensuring comprehensive analysis. Experimental results demonstrate that our
approach surpasses conventional machine learning methods in predictive accuracy,
robustness, and interpretability. Furthermore, this research provides an advanced framework for clinicians to assess potential sleep disorders while accommodating inherent uncertainties
in medical data. The study highlights the impact of neutrosophic machine learning in
healthcare decision support systems and outlines potential avenues for future research.

DOI: 10.5281/zenodo.14991712