A machine learning approach for mapping and accelerating multiple sclerosis research

Aug 3, 2026

The medical and research ecosystem is constrained by the sheer volume of publications, proceedings, and clinical trials, making it difficult for practitioners to stay current while balancing clinical responsibilities. The work proposes an intelligent reinforcement learning–driven recommender framework that maps and recommends research items—papers and clinical trials—tailored to multiple sclerosis. Multiple machine learning algorithms are tested and evaluated to identify the most promising approach for building an effective model that surfaces relevant MS research and accelerates discovery.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

Introduction

Related Work

Methods and System Development

Experimental Results

Conclusion and Future Work

[Available online at www.sciencedirect.com](Available online at www.sciencedirect.com) ScienceDirect Procedia Computer Science 219 (2023) 1193–1199 CENTERIS – International Conference on ENTERprise Information Systems / ProjMAN – International Conference on Project MANagement / HCist – International Conference on Health and Social Care Information Systems and Technologies 2022 A machine learning approach for mapping and accelerating multiple sclerosis research António Lopesa*, Bruno Amaralb aIscte – Instituto Universitário de Lisboa, Lisboa, Portugal bLisbon Collective, Lisboa, Portugal Abstract The medical field, as many others, is overwhelmed with the amount of research-related information available, such as journal papers, conference proceedings and clinical trials. The task of parsing through all this information to keep up to date with the most recent research findings on their area of expertise is especially difficult for practitioners who must also focus on their clinical duties. Recommender systems can help make decisions and provide relevant information on specific matters, such as for these clinical practitioners looking into which research to prioritize. In this paper, we describe the early work on a machine learning approach, which through an intelligent reinforcement learning approach, maps and recommends research information (papers and clinical trials) specifically for multiple sclerosis research. We tested and evaluated several different machine learning algorithms and present which one is the most promising in developing a complete and efficient model for recommending relevant multiple sclerosis research. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license ([https://creativecommons.org/licenses/by-nc-nd/4.0](https://creativecommons.org/licenses/by-nc-nd/4.0)) Peer-review under responsibility of the scientific committee of the CENTERIS–International Conference on ENTERprise Information Systems / ProjMAN-International Conference on Project MANagement / HCist-International Conference on Health and Social Care Information Systems and Technologies 2022 Keywords: machine learning; recommender systems; multiple-sclerosis; artificial intelligence; research information; * Corresponding author. Tel.: +0-000-000-0000 ; fax: +0-000-000-0000 . E-mail address: [alsl@iscte-iul.pt](alsl@iscte-iul.pt) 1877-0509 © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license ([https://creativecommons.org/licenses/by-nc-nd/4.0](https://creativecommons.org/licenses/by-nc-nd/4.0)) Peer-review under responsibility of the scientific committee of the CENTERIS – International Conference on ENTERprise Information Systems / ProjMAN-International Conference on Project MANagement / HCist-International Conference on Health and Social Care Information Systems and Technologies 2022 10.1016/j.procs.2023.01.401 1194 António Lopes et al. / Procedia Computer Science 219 (2023) 1193–1199 1. Introduction The amount of research in the health sciences is staggering and overwhelming for researchers trying to keep up with the most recent and relevant papers and studies for their respective areas. As depicted in Fig. 1, the number of indexed papers in Scopus for the research areas of medicine, neuroscience and pharmacology alone are now surpassing the 1 million mark per year. The uptick in 2020 and 2021 can be naturally explained by the important reaction to the COVID-19 pandemic, but the trend before that period was already indicative of the overwhelming amount of research done in these areas. Fig. 1. Number of indexed papers in Scopus in the areas of Medicine/Neuroscience/Pharmacology The inability to accompany the research evolution in these areas is especially difficult for practitioners that also must deal with their clinical duties, such as overseeing patient care. This raises the importance of havi

FAQs

What problem does the proposed approach address in multiple sclerosis research?

It addresses the difficulty for practitioners to keep up with rapidly expanding research volumes while prioritizing relevant papers and clinical trials for multiple sclerosis.

How does the system recommend MS research items?

It uses supervised learning to build a relevancy model for MS items and integrates it into a recommender system that collects data, aggregates it into a pipeline, and classifies items for downstream access.

What role does reinforcement learning play in the Gregory-MS system?

Reinforcement learning supports continuous improvement as administrators periodically review recommendations and tag articles, helping the model focus on accelerating MS research.

Aug 3, 2026

Upload by Lucas Martin