Journal
CELL REPORTS MEDICINE
Volume 1, Issue 4, Pages -Publisher
CELL PRESS
DOI: 10.1016/j.xcrm.2020.100053
Keywords
-
Categories
Funding
- Merck-Serono
- Italian Ministry of Health [RF-2011-02349698]
Ask authors/readers for more resources
Peripheral blood mononuclear cells (PBMCs) bear specific dysregulations in genes and pathways at distinct stages of multiple sclerosis (MS) that may help with classifying MS and non-MS subjects, specifying the early stage of disease, or discriminating among MS courses. Here we describe an unbiased machine learning workflow to build MS stage-specific classifiers based on PBMC transcriptomics profiles from more than 300 individuals, including healthy subjects and patients with clinically isolated syndromes, relapsing-remitting MS, primary or secondary progressive MS, or other neurological disorders. The pipeline, designed to optimize and compare the performance of distinct machine learning algorithms in the training cohort, generates predictive models not influenced by demographic features, such as age and gender, and displays high accuracy in the independent validation cohort. Proper application of machine learning to transcriptional profiles of circulating blood cells may allow identification of disease state and stage in MS.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available