Severity Classification of Multiple Sclerosis Disease: A Rough Set-Based Method
Afzal Hussain Shahid1, M. P. Singh2, Gunjan Kumar3

1Afzal Hussain Shahid, B.Tech, Department of Computer Science and Engineering, Netaji Subhash Engineering College Garia (Kolkata), India.

2Dr. M. P. Singh, P.H.D., Department of Computer Science and Engineering, Motilal Nehru National Institute of Technology Allahabad (Uttar Pradesh), India.

3Dr. Gunjan Kumar,Post Graduate, Institute of Medical Education and Research, New Delhi India.

Manuscript received on 20 August 2019 | Revised Manuscript received on 27 August 2019 | Manuscript Published on 26 August 2019 | PP: 307-314 | Volume-8 Issue-9S August 2019 | Retrieval Number: I10490789S19/19©BEIESP | DOI: 10.35940/ijitee.I1049.0789S19

Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (

Abstract: Multiple sclerosis (MS) is among the world’s most common neurologic disorder. Severity classification of MS disease is necessary for treatment and medication dosage decisions and to understand the disease progression. To the best of authors’ knowledge, this is the first study for the severity classification of MS disease. In this study, Rough set (RS) approach is applied to discern the three classes (mild, moderate, and severe) of the severity of MS disease. Furthermore, the performance of the RS approach is compared with Machine learning (ML) classifiers namely, random forest, K-nearest neighbour, and support vector machine. The performance is evaluated on the dataset acquired from Multiple sclerosis outcome assessments consortium (MSOAC), Arizona, US. The weighted average accuracy, precision, recall, and specificity values for the RS approach are found to be 84.04%, 76.99%, 76.75%, and 83.84% respectively. However, among the ML classifiers, the performance of random forest classifier is found best for which the weighted average accuracy, precision, recall, and specificity values are 62.19 %, 52.65 %, 56.84 %, and 59.87 % respectively. The RS approach is found much superior to ML classifiers and may be used for MS disease severity classification. This study may be helpful for the clinicians to assess the severity of the MS patients and to take medication and dosage decisions.

Keywords: Multiple Sclerosis, Severity Classification, Rough Sets, Machine Learning.
Scope of the Article: Classification