Dataset Information

Inferring Multiple Sclerosis Stages from the Blood Transcriptome via Machine Learning.

ABSTRACT: 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.

SUBMITTER: Acquaviva M

PROVIDER: S-EPMC7659538 | biostudies-literature | 2020 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Inferring Multiple Sclerosis Stages from the Blood Transcriptome via Machine Learning.

Acquaviva Massimo M Menon Ramesh R Di Dario Marco M Dalla Costa Gloria G Romeo Marzia M Sangalli Francesca F Colombo Bruno B Moiola Lucia L Martinelli Vittorio V Comi Giancarlo G Farina Cinthia C

Cell reports. Medicine 20200721 4

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 ...[more]

PMID: 33205062

Similar Datasets

Project description:BackgroundIdentifying active lesions in magnetic resonance imaging (MRI) is crucial for the diagnosis and treatment planning of multiple sclerosis (MS). Active lesions on MRI are identified following the administration of Gadolinium-based contrast agents (GBCAs). However, recent studies have reported that repeated administration of GBCA results in the accumulation of Gd in tissues. In addition, GBCA administration increases health care costs. Thus, reducing or eliminating GBCA administration for active lesion detection is important for improved patient safety and reduced healthcare costs. Current state-of-the-art methods for identifying active lesions in brain MRI without GBCA administration utilize data-intensive deep learning methods.ObjectiveTo implement nonlinear dimensionality reduction (NLDR) methods, locally linear embedding (LLE) and isometric feature mapping (Isomap), which are less data-intensive, for automatically identifying active lesions on brain MRI in MS patients, without the administration of contrast agents.Materials and methodsFluid-attenuated inversion recovery (FLAIR), T2-weighted, proton density-weighted, and pre- and post-contrast T1-weighted images were included in the multiparametric MRI dataset used in this study. Subtracted pre- and post-contrast T1-weighted images were labeled by experts as active lesions (ground truth). Unsupervised methods, LLE and Isomap, were used to reconstruct multiparametric brain MR images into a single embedded image. Active lesions were identified on the embedded images and compared with ground truth lesions. The performance of NLDR methods was evaluated by calculating the Dice similarity (DS) index between the observed and identified active lesions in embedded images.ResultsLLE and Isomap, were applied to 40 MS patients, achieving median DS scores of 0.74 ± 0.1 and 0.78 ± 0.09, respectively, outperforming current state-of-the-art methods.ConclusionsNLDR methods, Isomap and LLE, are viable options for the identification of active MS lesions on non-contrast images, and potentially could be used as a clinical decision tool.

Dataset Information

Inferring Multiple Sclerosis Stages from the Blood Transcriptome via Machine Learning.

Publications

Inferring Multiple Sclerosis Stages from the Blood Transcriptome via Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets