Model-Driven Decision Making in Multiple Sclerosis Research: Existing Works and Latest Trends

Area of Science:

• Neurology
• Medical Informatics
• Artificial Intelligence in Healthcare

Background:

• Multiple sclerosis (MS) is a complex neurological disorder impacting the central nervous system.
• There is a growing need for accessible clinical decision support systems (DSSs) in MS management.
• Current tools require enhancement for both technical and non-technical healthcare professionals.

Purpose of the Study:

• To review the current state-of-the-art decision support systems (DSSs) in multiple sclerosis (MS) research.
• To focus specifically on model-driven decision-making processes within these DSSs.
• To identify common methodologies and future directions for DSS application in MS.

Main Methods:

• Literature review of decision support systems in MS research.
• Clustering of methodologies for MS classification, diagnosis, prediction, and treatment.
• Analysis of knowledge-based and machine learning (ML) approaches, including ontology utilization.

Main Results:

• The majority of reviewed DSSs utilize knowledge-based and machine learning (ML) techniques.
• Ontology and ML are significant components in developing advanced DSS for MS.
• Identified commonalities in methodologies across various DSS applications in MS.

Conclusions:

• Decision support systems, particularly those using ML and ontology, show significant promise in improving MS care.
• Further research and development are needed to fully integrate DSS technologies into clinical practice for MS.
• Model-driven approaches are central to advancing decision-making tools for neurological disorders like MS.