Multiple Sclerosis Biomarker Data for Diagnostic Classification

A pilot study dataset integrating inflammatory and neurodegenerative biomarkers to classify Multiple Sclerosis subtypes. The data includes retinal imaging, serum protein levels, and immunophenotyping from a study by Tobias Hegelmaier, last updated in May 2026. The dataset is a 735.6 KB supplementary document describing the study's methodology and results.

Use Cases

• Training classification models to distinguish relapsing from secondary progressive MS based on biomarker combinations.
• Analyzing correlations between retinal layer thickness and serum neurofilament light chain levels.
• Exploring the predictive power of monocyte subsets for disease progression independent of relapse activity.

Strengths

• Dataset is openly licensed under CC-BY-4.0.
• The described CART and Random Forest models achieved approximately 80% classification accuracy.
• Multimodal approach combines retinal, serum, and immunophenotyping data.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data is described as a pilot study, suggesting a limited sample size.

Provenance

Source

figshare, author Tobias Hegelmaier.

Collection Method

Combined multifocal electroretinography, optical coherence tomography, serum assays, and immunophenotyping in a clinical study.

Time Range

null

Freshness

Last updated 2026-05-20 04:32:52; freshness should be verified.

Geography

null