An AI-driven Multimodal Approach for Prediction and Progression Monitoring in Multiple Sclerosis

Kamallesh Kumar R K; Dhivvya Bhalan Duraivelan Jeyabhalan; Dil Divya Prabhakar; Kalaivani Muniyan; Arun Prasad Arunachalam Sivagurulingam

doi:10.36948/ijfmr.2025.v07i04.51708

An AI-driven Multimodal Approach for Prediction and Progression Monitoring in Multiple Sclerosis

Author(s)	Mr. Kamallesh Kumar R K, Mr. Dhivvya Bhalan Duraivelan Jeyabhalan, Ms. Dil Divya Prabhakar, Ms. Kalaivani Muniyan, Dr. Arun Prasad Arunachalam Sivagurulingam
Country	India
Abstract	Multiple Sclerosis (MS) is a complex immune-mediated neurologic condition with heterogeneous disease course and diagnostic challenge. In this paper, an AI-based multimodal model is introduced that integrates clinical, MRI, and ophthalmic imaging features for better early diagnosis and monitoring of disease progression, with special focus on EDSS (Expanded Disability Status Scale) score prediction. Several machine learning and deep learning models were evaluated, such as Logistic Regression, Random Forest, and XGBoost. Out of them, XGBoost achieved the highest accuracy (92.72%) and showed enhanced precision, recall, and F1-score for MS conversion prediction. While Logistic Regression performance was slightly worse, high cross-validation stability was shown by it. Feature importance analysis showed MRI-derived markers—more specifically periventricular and infratentorial lesions—and early clinical symptoms as key predictors. Additionally, SHAP-based explainable AI methods were employed in order to enhance the explainability of models and to make them more clinically confidence-generating. The paper establishes the effectiveness of the combination of structured clinical data and imaging biomarkers with state-of-the-art machine learning models to enable early, accurate, and personalized MS treatment.
Keywords	Multiple Sclerosis, XGBoost, Multimodal Data Integration, Optical Coherence Tomography (OCT), Multimodal Data Integration.
Field	Medical / Pharmacy
Published In	Volume 7, Issue 4, July-August 2025
Published On	2025-07-23
DOI	https://doi.org/10.36948/ijfmr.2025.v07i04.51708
Short DOI	https://doi.org/g9t2dr

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 7 Isu 4 Cover Page Vol 7 Isu 3 Cover Page Vol 7 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

An AI-driven Multimodal Approach for Prediction and Progression Monitoring in Multiple Sclerosis

Share this