Abstract
Machine learning (ML) has witnessed a notable increase in significance within the medical field, primarily due to the increasing availability of health-related data and the progressive enhancements in ML algorithms. Thus, ML can be utilized to formulate predictive models that aid in disease diagnosis, anticipate disease progression, tailor treatment to fulfill individual patient needs, and improve the operational efficiency of healthcare systems. Timely detection of a disease contributes to effective symptom management and guarantees that appropriate treatment is provided. In multiple sclerosis (MS), evoked potentials (EPs) show a strong correlation with the Expanded Disability Status Scale (EDSS), suggesting their potential as reliable predictors of disability progression. The aim of the present study is to apply artificial intelligence (AI) techniques to identify predictors linked to the progression of MS as assessed by the disability index (EDSS). It is essential to clarify the role of EPs in the prognostication of MS. We conducted an analysis of empirical data obtained from a medical database consisting of 125 records. Our primary objective is to construct an expert AI system capable of predicting the EDSS index through the application of advanced knowledge-mining algorithms. We have developed intelligent systems that predict the progression of MS utilizing ML algorithms, specifically decision trees and neural networks. In our experimental evaluation, decision trees, neural networks, and Bayes for EPs achieved accuracies of 88.9%, 92.9%, and 88.2% respectively, which are comparable to MRI that obtained accuracies of 88.2%, 96.0%, and 85.0%. The EPs can be established as predictors of MS with efficacy analogous to that of MRI findings. Further investigation is necessary to validate EPs, which are significantly less expensive, portable, and simpler to administer than MRI, as equally effective as imaging or biochemical methods in functioning as biomarkers for MS.