Search

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. Predictors of clinical outcomes were searched using Random Forest algorithms. Assessment of the algorithm performance was conducted in an independent prospective cohort of 271 MS patients from a single centre., Results: We found algorithms for predicting confirmed disability accumulation for the different scales, no evidence of disease activity (NEDA), onset of immunotherapy and the escalation from low- to high-efficacy therapy with intermediate to high-accuracy. This accuracy was achieved for most of the predictors using clinical data alone or in combination with imaging data. Still, in some cases, the addition of omics data slightly increased algorithm performance. Accuracies were comparable in both cohorts., Conclusion: Combining clinical, imaging and omics data with machine learning helps identify MS patients at risk of disability worsening., (© 2023. The Author(s).)

Multiple sclerosis (MS) is a chronic autoimmune disease characterized by demyelinating lesions that are often visible on magnetic resonance imaging (MRI). Segmentation of these lesions can provide imaging biomarkers of disease burden that can help monitor disease progression and the imaging response to treatment. Manual delineation of MRI lesions is tedious and prone to subjective bias, while automated lesion segmentation methods offer objectivity and speed, the latter being particularly important when analysing large datasets. Lesion segmentation can be broadly categorised into two groups: cross-sectional methods, which use imaging data acquired at a single time-point to characterise MRI lesions; and longitudinal methods, which use imaging data from the same subject acquired at two or more different time-points to characterise lesions over time. The main objective of longitudinal segmentation approaches is to more accurately detect the presence of new MS lesions and the growth or remission of existing lesions, which may be effective biomarkers of disease progression and treatment response. This paper reviews articles on longitudinal MS lesion segmentation methods published over the past 10 years. These are divided into traditional machine learning methods and deep learning techniques. PubMed articles using longitudinal information and comparing fully automatic two time point segmentations in any step of the process were selected. Nineteen articles were reviewed. There is an increasing number of deep learning techniques for longitudinal MS lesion segmentation that are promising to help better understand disease progression., (© 2022. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)

Purpose: To predict the occurrence of a second clinical event in patients with a CIS suggestive of MS, from baseline magnetic resonance imaging (MRI), by means of a pattern recognition approach., Methods: Two hundred sixty-six patients with a CIS were recruited from four participating centers. Over a follow-up of 3 years, 130 patients had a second clinical episode and 136 did not. Grey matter and white matter T1-hypointensities masks segmented from 3D T1-weighted images acquired on 3 T scanners were used as features for the classification approach. Differences between CIS that remained CIS and those that developed a second event were assessed at a global level and at a regional level, arranging the regions according to their contribution to the classification model., Results: All classification metrics were around or even below 50% for both global and regional approaches. Accuracies did not change when T1-hypointensity maps were added to the model; just the specificity was increased up to 80%. Among the 30 regions with the largest contribution, 26 were grey matter and 4 were white matter regions. For grey matter, regions contributing showed either a larger or a smaller volume in the group of patients that remained CIS, compared to those with a second event. The volume of T1-hypointensities was always larger for the group that presented a second event., Conclusions: Prediction of a second clinical event in CIS patients from baseline MRI seems to present a highly heterogeneous pattern, leading to very low classification accuracies. Adding the T1-hypointensity maps does not seem to improve the accuracy of the classification model., (© 2022. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)

Sneddon syndrome is a rare disorder affecting small and medium-sized blood vessels that is characterized by the association of livedo reticularis and stroke. We performed whole-exome sequencing (WES) in 2 affected siblings of a consanguineous family with childhood-onset stroke and identified a homozygous nonsense mutation within the epidermal growth factor repeat (EGFr) 19 of NOTCH3, p.(Arg735Ter). WES of 6 additional cases with adult-onset stroke revealed 2 patients carrying heterozygous loss-of-function variants in putative NOTCH3 downstream genes, ANGPTL4, and PALLD. Our findings suggest that impaired NOTCH3 signaling is one underlying disease mechanism and that bi-allelic loss-of-function mutation in NOTCH3 is a cause of familial Sneddon syndrome with pediatric stroke.

Objective: To analyze whether myelin oligodendrocyte glycoprotein antibody (MOG-Ab) titres at onset of the disease were different according to the clinical phenotype at presentation, and to investigate whether the titres were associated with risk of further relapses or predicted clinical outcome in adult patients. Finally, we assessed an alternative method to the classical measurement of MOG-Ab levels by serial dilutions., Methods: This is a retrospective study including 79 MOG-Ab-positive adult patients, whose samples were obtained at first episode. MOG-Ab were tested by cell-based assay. HEK293 cells were transfected (tHEK293) with human-MOG plasmid. Non-tHEK293 cells were used as negative controls. Assessment of antibody titres was performed by serial dilution, and delta mean fluorescence intensity ratio signal (MOG-ratio ΔMFI) by flow cytometry. MOG-ratio ΔMFI was calculated as follows: (MFI tHEK293cells- MFI non-tHEK293cells)/MFI non-tHEK293cells. MOG-ratio ΔMFI was calculated from the first serum dilution at 1:320. The association between MOG-Ab titres and risk of relapse was analyzed by Cox regression. The association between MOG-Ab titres and visual or motor disability at last follow-up was performed by binary logistic regression. Poor visual outcome was defined when patients displayed some degree of visual disability (visual acuity [VA] < 20/20) and poor motor outcome when patients displayed some degree of motor disability (Disability Status Scale [DSS] > 1). We also investigated correlations between MOG-Ab titres and MOG-ratio ΔMFI., Results: MOG-Ab titres were higher in Caucasians than in those with other ethnicities, and in patients with a more severe VA (VA ≤ 20/100) or motor disability (DSS ≥ 3.0) at onset (p = 0.006, 0.034, and 0.058, respectively). MOG-Ab titres were not associated with risk of relapses or with the final clinical outcome. MOG-ratio ΔMFI correlated with MOG-Ab titres in the whole cohort (ρ = 0.90; p < 0.001), and when stratified by initial clinical phenotype., Conclusion: High MOG-Ab titres at onset are associated with a more severe presentation, but do not predict the future disease course. MOG-ratio ΔMFI is an alternative and straightforward method to determine MOG-Ab levels.

Monitoring disease burden is an unmeet need in multiple sclerosis (MS). Identifying patients at high risk of disability progression will be useful for improving clinical-therapeutic decisions in clinical routine. To evaluate the role of visual field testing in non-optic neuritis eyes (non-ON eyes) as a biomarker of disability progression in MS. In 109 patients of the MS-VisualPath cohort, we evaluated the association between visual field abnormalities and global and cognitive disability markers and brain and retinal imaging markers of neuroaxonal injury using linear regression models adjusted for sex, age, disease duration and use of disease-modifying therapies. We evaluated the risk of disability progression associated to have baseline impaired visual field after 3 years of follow-up. Sixty-two percent of patients showed visual field defects in non-ON eyes. Visual field mean deviation was statistically associated with global disability; brain (normalized brain parenchymal, gray matter volume and lesion load) and retinal (peripapillary retinal nerve fiber layer thickness and macular ganglion cell complex thickness) markers of neuroaxonal damage. Patients with impaired visual field had statistically significative greater disability, lower normalized brain parenchymal volume and higher lesion volume than patients with normal visual field testing. MS patients with baseline impaired VF tripled the risk of disability progression during follow-up [OR = 3.35; 95 % CI (1.10-10.19); p = 0.033]. The association of visual field impairment with greater disability and neuroaxonal injury and higher risk of disability progression suggest that VF could be used to monitor MS disease burden.

Multiple Sclerosis (MS) results in color vision impairment regardless of optic neuritis (ON). The exact location of injury remains undefined. The objective of this study is to identify the region leading to dyschromatopsia in MS patients' NON-eyes. We evaluated Spearman correlations between color vision and measures of different regions in the afferent visual pathway in 106 MS patients. Regions with significant correlations were included in logistic regression models to assess their independent role in dyschromatopsia. We evaluated color vision with Hardy-Rand-Rittler plates and retinal damage using Optical Coherence Tomography. We ran SIENAX to measure Normalized Brain Parenchymal Volume (NBPV), FIRST for thalamus volume and Freesurfer for visual cortex areas. We found moderate, significant correlations between color vision and macular retinal nerve fiber layer (rho = 0.289, p = 0.003), ganglion cell complex (GCC = GCIP) (rho = 0.353, p < 0.001), thalamus (rho = 0.361, p < 0.001), and lesion volume within the optic radiations (rho = -0.230, p = 0.030). Only GCC thickness remained significant (p = 0.023) in the logistic regression model. In the final model including lesion load and NBPV as markers of diffuse neuroaxonal damage, GCC remained associated with dyschromatopsia [OR = 0.88 95 % CI (0.80-0.97) p = 0.016]. This association remained significant when we also added sex, age, and disease duration as covariates in the regression model. Dyschromatopsia in NON-eyes is due to damage of retinal ganglion cells (RGC) in MS. Color vision can serve as a marker of RGC damage in MS.

Walking limitation is a key component of disability in patients with multiple sclerosis (MS), but the information on daily walking activity and disability over time is limited. To determine, (1) the agreement between the standard measurements of MS-related disability [expanded disability status scale (EDSS), functional systems (FS) and ambulation index (AI)] obtained by conventional and remote evaluation using a multimedia platform; (2) the usefulness of monitoring 6-min walk test (6MWT) and average daily walking activity (aDWA) to better characterize patients disability. Twenty-five patients (EDSS score 1.0-6.5) were evaluated every 3 months for the first year, and aDWA repeated at year 2. Remote visits included the recording of a video with self-performed neurological examination and specific multimedia questionnaires. aDWA was measured by a triaxial accelerometer. All but two patients completed the study. Modest agreement between conventional and multimedia EDSS was found for EDSS ≤ 4.0 (kappa = 0.2) and good for EDSS ≥ 4.5 (kappa = 0.6). For the overall sample, pyramidal, cerebellar and brainstem FS showed the greatest agreement (kappa = 0.7). SR-AI showed a modest agreement for EDSS ≤ 4.0 and good for EDSS ≥ 4.5 (kappa = 0.3 and 0.6, respectively). There was a strong correlation between conventional and 6MWT measured by accelerometer (r = 0.76). The aDWA correlated strongly with the EDSS (r = -0.86) and a cut-off point of 3279.3 steps/day discriminated patients with ambulatory impairment. There was a significant decline in aDWA over 2 years in patients with ambulatory impairment that were not observed by standard measurements of disability. MS clinical monitoring by telemedicine is feasible, but the observed lower agreement in less disabled patients emphasizes the need to optimize the assessment methodology. Accelerometers capture changes that may indicate deterioration over time.