Preprint

Article

Machine Learning Algorithms Introduce Evoked Potentials as the Alternative Biomarkers for the Edss Prognosis of Ms Patients

Altmetrics

Downloads

Views

Comments

Dionysia Chsyranthakopoulou,

Constantinos Koutsojannis^*

Dionysia Chsyranthakopoulou,

Constantinos Koutsojannis^*

This version is not peer-reviewed

This preprints belongs to the Topic

Advances in Diagnostics, Brain Delivery Systems and Therapeutics of Neurodegenerative Disease

Submitted:

14 November 2024

Posted:

19 November 2024

You are already at the latest version

Alerts

Abstract

Machine learning 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 machine learning algorithms. It 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. The strategic utilization of data can considerably elevate the quality of patient care, reduce healthcare costs, and promote the formulation of personalized and effective medical interventions. The healthcare industry reaps considerable benefits from the meticulous analysis of medical data, as it plays an integral role in promptly identifying diseases in patients. Timely detection of a disease can contribute to effective symptom management and guarantee that appropriate treatment is provided. The pronounced association between evoked potentials (EPs) and Expanded Disability Status Scale (EDSS) scores in individuals diagnosed with multiple sclerosis (MS) indicates that EPs may serve as dependable predictive markers for the progression of disability. Numerous studies have confirmed that variations in somatosensory evoked potentials (SEPs) demonstrate a relationship with EDSS scores, particularly during the early stages of the disease. The present study aims to apply artificial intelligence techniques to identify predictors linked to the progression of Multiple Sclerosis (MS) as assessed by the disability index (EDSS). It is essential to clarify the role of evoked potentials (EPs) in the prognostication of MS. We analyzed empirical data obtained from a medical database of 125 records. Our primary objective is to construct an expert Artificial Intelligence system capable of predicting the EDSS index by applying advanced knowledge-mining algorithms. We have developed intelligent systems that predict the progression of MS utilizing machine learning 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 which 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.

Keywords:

Subject: Biology and Life Sciences - Biophysics

Copyright: This open access article is published under a Creative Commons CC BY 4.0 license, which permit the free download, distribution, and reuse, provided that the author and preprint are cited in any reuse.