New benchmark MS-MLB uses machine learning for blood-based MS classification

Researchers have introduced MS-MLB, a new open benchmark designed for machine learning classification of multiple sclerosis (MS) using whole blood RNA expression data. The benchmark utilizes the public GSE17048 cohort and implements a rigorous, reproducible pipeline with controlled leakage to evaluate various algorithms. Gradient Boosting emerged as the top-performing model, achieving a high MS Research Score of 93.83 and an AUC-ROC of 0.989 on a holdout set, though the scores are intended for research comparison only and are not clinically validated. AI

IMPACT Establishes a standardized benchmark for ML-based MS classification from blood RNA data, potentially accelerating research in the field.

RANK_REASON The item is a research paper introducing a new benchmark for machine learning classification. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• gradient boosting
• GSE17048
• MS-MLB
• multiple sclerosis

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →