Detecting Alzheimer’s Disease using Rough Set-based Classification Approach
Abstract
Alzheimer’s is a memory deficiency disease that frequently affects elderly persons. Though it cannot be cured or stopped, its progression may be delayed if early diagnosis is possible. Early diagnosis of Alzheimer’s disease is one of the most challenging problems for researchers, since it minimizes time, cost, and suffering for the patients, their caregivers, and health institutions. Many methods were already proposed for this purpose, and the rough set-based classification technique is one of them. In this paper, a rough set theory-based classification algorithm is proposed to classify early detection and diagnosis of the disease. The efficacy of the method can be demonstrated with the experiments conducted on a dataset collected from the National Alzheimer Coordination Centre (NACC). To make the classifier compatible with the NACC datasets, it has been customized. The results convincingly show that our method outperforms other known methods.