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. [ABSTRACT FROM AUTHOR]

The spatio-temporal characteristics of grey matter (GM) impairment in multiple sclerosis (MS) are poorly understood. We used a new surface-based diffusion MRI processing tool to investigate regional modifications of microstructure, and we quantified volume loss in GM in a cohort of patients with MS classified into three groups according to disease duration. Additionally, we investigated the relationship between GM changes with disease severity. We studied 54 healthy controls and 247 MS patients classified regarding disease duration: MS1 (less than 5 years, n = 67); MS2 (5–15 years, n = 107); and MS3 (more than15 years, n = 73). We compared GM mean diffusivity (MD), fractional anisotropy (FA) and volume between groups, and estimated their clinical associations. Regional modifications in diffusion measures (MD and FA) and volume did not overlap early in the disease, and became widespread in later phases. We found higher MD in MS1 group, mainly in the temporal cortex, and volume reduction in deep GM and left precuneus. Additional MD changes were evident in cingulate and occipital cortices in the MS2 group, coupled to volume reductions in deep GM and parietal and frontal poles. Changes in MD and volume extended to more than 80% of regions in MS3 group. Conversely, increments in FA, with very low effect size, were observed in the parietal cortex and thalamus in MS1 and MS2 groups, and extended to the frontal lobe in the later group. MD and GM changes were associated with white matter lesion load and with physical and cognitive disability. Microstructural integrity loss and atrophy present differential spatial predominance early in MS and accrual over time, probably due to distinct pathogenic mechanisms that underlie tissue damage. [ABSTRACT FROM AUTHOR]

Understanding of the role of focal inflammation, a treatable feature, on neuro-axonal injury, is paramount to optimize neuroprotective strategy in MS. To quantify the impact of focal inflammatory activity on the rate of neuro-axonal injury over the MS course. We quantified the annualized rates of change in peripapillary retinal nerve fiber layer, ganglion cell plus inner plexiform layer (GCIPL), whole-brain, gray matter and thalamic volumes in patients with and without focal inflammatory activity in 161 patients followed over 5 years. We used mixed models including focal inflammatory activity (the presence of at least one relapse or a new/enlarging T2-FLAIR or gadolinium- enhancing lesion), and its interaction with time adjusted by age, sex, use of disease-modifying therapies and steroids, and prior optic neuritis. The increased rate of neuro-axonal injury during the first five years after onset was more prominent among active patients, as reflected by the changes in GCIPL thickness (p = 0.02), whole brain (p = 0.002) and thalamic volumes (p < 0.001). Thereafter, rates of retinal and brain changes stabilized and were similar in active and stable patients. Focal inflammatory activity is associated with neurodegeneration early in MS which reinforces the use of an early intensive anti-inflammatory therapy to prevent neurodegeneration in MS. [ABSTRACT FROM AUTHOR]

Brain structural network modifications in multiple sclerosis (MS) seem to be clinically relevant. The discriminative ability of those changes to identify MS patients or their cognitive status remains unknown. Therefore, this study aimed to investigate connectivity changes in MS patients related to their cognitive status, and to define an automatic classification method to classify subjects as patients and healthy volunteers (HV) or as cognitively preserved (CP) and impaired (CI) patients. We analysed structural brain connectivity in 45 HV and 188 MS patients (104 CP and 84 CI). A support vector machine with k-fold cross-validation was built using the graph metrics features that best differentiate the groups (p < 0.05). Local efficiency (LE) and node strength (NS) network properties showed the largest differences: 100% and 69.7% of nodes had reduced LE and NS in CP patients compared to HV. Moreover, 55.3% and 57.9% of nodes had decreased LE and NS in CI compared to CP patients, in associative multimodal areas. The classification method achieved an accuracy of 74.8–77.2% to differentiate patients from HV, and 59.9–60.8% to discriminate CI from CP patients. Structural network integrity is widely reduced and worsens as cognitive function declines. Central network properties of vulnerable nodes can be useful to classify MS patients. [ABSTRACT FROM AUTHOR]

Our objective was to determine whether substantia nigra (SN) hyperechogenicity is greater in spinocerebellar ataxias (SCA) with nigrostriatal affectation than in ataxias without it. A cross-sectional case-control study analyzing four groups of patients was conducted: 1) nigrostriatal ataxias (SCA3 and SCA6), 2) nigrostriatal healthy controls matched by age and sex, 3) non-nigrostriatal ataxias (FRDA and SCA7), and 4) non-nigrostriatal healthy controls matched by age and sex. All the patients underwent a transcranial ultrasound performed by an experienced sonographer blinded to the clinical, genetic, and neuroimaging data. The SN area was measured and compared in the four groups. The SN area was also correlated with clinical features and genetic data in the two ataxia groups. We examined 12 patients with nigrostriatal ataxia (11 SCA3 and 1 SCA6), 12 nigrostriatal healthy control patients, 7 patients with non-nigrostriatal ataxia (5 FRDA and 2 SCA7), and 7 non-nigrostriatal healthy control patients. The median (IQR) SN area (cm) was greater in the nigrostriatal ataxias compared with the controls (right SN, 0.43 [0.44] vs. 0.11 [0.25]; P = 0.001; left SN, 0.32 [0.25] vs. 0.11 [0.16]; P = 0.001), but was similar among the non-nigrostriatal ataxias and controls. There were no statistically significant differences in the SN area between the nigrostriatal and non-nigrostriatal ataxias, although there was a tendency for a greater left SN area in the nigrostriatal compared with the non-nigrostriatal ataxias (0.32 [0.25] vs. 0.16 [0.24], P = 0.083). SN echogenicity is markedly greater in ataxias with nigrostriatal pathology than in controls. The role of SN hyperechogenicity in differentiating ataxias with and without nigrostriatal pathology should be elucidated in future studies. [ABSTRACT FROM AUTHOR]