Predicting disease severity in multiple sclerosis using multimodal data and machine learning.

Background: Multiple sclerosis patients would benefit from machine learning algorithms that integrates clinical, imaging and multimodal biomarkers to define the risk of disease activity.

Methods: We have analysed a prospective multi-centric cohort of 322 MS patients and 98 healthy controls from four MS centres, collecting disability scales at baseline and 2 years later. Imaging data included brain MRI and optical coherence tomography, and omics included genotyping, cytomics and phosphoproteomic data from peripheral blood mononuclear cells.

Immune cell subpopulations and serum neurofilament light chain are associated with increased risk of disease worsening in multiple sclerosis.

Changes is lymphocyte subpopulations in peripheral blood have been proposed as biomarkers for evaluation of disease activity in multiple sclerosis (MS). Serum neurofilament light chain (sNfL) is a biomarker reflecting neuro-axonal injury in MS that could be used to monitor disease activity, response to drugs and to prognosticate disease course. Here we show a moderate correlation between sNfL and lymphocyte cell subpopulations, and our data furthermore suggest that sNfL and specific immune cell subpopulations together could predict future disease worsening in MS.

Intranasal delivery of mesenchymal stem cell secretome repairs the brain of Alzheimer's mice.

The multiplicity of systems affected in Alzheimer's disease (AD) brains calls for multi-target therapies. Although mesenchymal stem cells (MSC) are promising candidates, their clinical application is limited because of risks related to their direct implantation in the host. This could be overcome by exploiting their paracrine action.

Characterization of mouse spinal cord vascular network by means of synchrotron radiation X-ray phase contrast tomography.

High resolution Synchrotron-based X-ray Phase Contrast Tomography (XPCT) allows the simultaneous detection of three dimensional neuronal and vascular networks without using contrast agents or invasive casting preparation. We show and discuss the different features observed in reconstructed XPCT volumes of the ex vivo mouse spinal cord in the lumbo-sacral region, including motor neurons and blood vessels. We report the application of an intensity-based segmentation method to detect and quantitatively characterize the modification in the vascular networks in terms of reduction in experimental visibility.