Heart Disease Prediction using Neutrosophic C-Means Clustering Algorithm

Piedad Acurio Padilla^1,*, Evelyn Betancourt Rubio¹, Walter Vayas Valdiviezo¹, Mohammed k. Hassan²

¹Universidad Regional Autónoma de los Andes, Ecuador

²Mechatronics department, Faculty of Engineering, Horus university-Egypt (HUE), Egypt

Emails: ua.piedadacurio@uniandes.edu.ec; us.evelynbr17@uniandes.edu.ec; ua.waltervayas@uniandes.edu.ec; mkhassan@horus.edu.eg

Abstract

Heart disease, often known as cardiovascular illness, encompasses a broad range of heart-related disorders and has emerged as the leading cause of mortality during the last few decades everywhere in the globe. Numerous hazards are linked to cardiovascular disease, and timely, effective, and practical methods for making an early diagnosis are required for effective and efficient treatment. In this study, we describe a novel clustering technique for data that is unreliable clustering called neutrosophic c-means (NCM), which draws inspiration from both fuzzy c-means and the neutrosophic set architecture. The NCM is used to predict heart disease. There are four different databases included in the collection, all of which were created in 1988: Cleveland, Hungary, Switzerland, and Long Beach V. There are 76 qualities total, such as the anticipated characteristic, however only 14 have been used in any of the published trials.

Keywords: Neutrosophic C-Means Clustering; Clustering; Heart Disease Prediction.