The predictive value of gray matter atrophy in clinically isolated syndromes.
ABSTRACT Although gray matter (GM) atrophy is recognized as a common feature of multiple sclerosis (MS), conflicting results have been obtained in patients with clinically isolated syndromes (CIS). Methodologic and clinical constraints may take account for literature discrepancies.
A total of 105 patients presenting with CIS and 42 normal controls (NC) were studied. At baseline, 65/105 patients with CIS met the criterion of dissemination in space of lesions (DIS+). All patients were clinically assessed by means of the Expanded Disability Status Scale every 6 months and underwent MRI evaluation at study entry and then annually for 4 years. Global and regional cortical thickness and deep GM atrophy were assessed using Freesurfer.
No significant reduction in GM atrophy was observed between the entire CIS group and the NC, excepting for the cerebellum cortical volume. When the 59 patients with CIS (46 DIS+, 13 DIS-) who converted to MS during the follow-up were compared to the NC, a significant atrophy in the precentral gyrus, superior frontal gyrus, thalamus, and putamen was observed (p ranging from 0.05 to 0.001). The multivariate analysis identified the atrophy of superior frontal gyrus, thalamus, and cerebellum as independent predictors of conversion to MS. CIS with atrophy of such areas had a double risk of conversion compared to DIS+ (odds ratio 9.6 vs 5.0).
Selective GM atrophy is relevant in patients with CIS who convert early to MS. The inclusion of GM analysis in the MS diagnostic workup is worthy of further investigation.
SourceAvailable from: PubMed Central[Show abstract] [Hide abstract]
ABSTRACT: We aim to determine if machine learning techniques, such as support vector machines (SVMs), can predict the occurrence of a second clinical attack, which leads to the diagnosis of clinically-definite Multiple Sclerosis (CDMS) in patients with a clinically isolated syndrome (CIS), on the basis of single patient's lesion features and clinical/demographic characteristics. Seventy-four patients at onset of CIS were scanned and clinically reviewed after one and three years. CDMS was used as the gold standard against which SVM classification accuracy was tested. Radiological features related to lesional characteristics on conventional MRI were defined a priori and used in combination with clinical/demographic features in an SVM. Forward recursive feature elimination with 100 bootstraps and a leave-one-out cross-validation was used to find the most predictive feature combinations. 30 % and 44 % of patients developed CDMS within one and three years, respectively. The SVMs correctly predicted the presence (or the absence) of CDMS in 71.4 % of patients (sensitivity/specificity: 77 %/66 %) at 1 year, and in 68 % (60 %/76 %) at 3 years on average over all bootstraps. Combinations of features consistently gave a higher accuracy in predicting outcome than any single feature. Machine-learning-based classifications can be used to provide an “individualised” prediction of conversion to MS from subjects' baseline scans and clinical characteristics, with potential to be incorporated into routine clinical practice.01/2015; 7:281-7. DOI:10.1016/j.nicl.2014.11.021
Article: Brain atrophy in Multiple Sclerosis[Show abstract] [Hide abstract]
ABSTRACT: Multiple sclerosis (MS) has traditionally been considered to be primarily an inflammatory demyelinating disorder affecting the white matter. Nowadays it is recognized as both an inflammatory and a neurodegenerative condition involving the white and grey matter. Grey matter atrophy occurs in the earliest stages of MS, progresses faster than in healthy individuals, and shows significant correlations with cognitive function and physical disability; indeed, brain atrophy is the best predictor of subsequent disability and can be measured using magnetic resonance imaging (MRI). There are a number of MRI methods for measuring global or regional brain volume, including cross-sectional and longitudinal techniques. Preventing brain volume loss may therefore have important clinical implications affecting treatment decisions, with several clinical trials now demonstrating an effect of disease-modifying treatments (DMTs) on reducing brain volume loss. In clinical practice, it may therefore be important to consider the potential impact of a therapy on reducing the rate of brain volume loss. This article summarizes the knowledge on brain volume in MS.
[Show abstract] [Hide abstract]
ABSTRACT: Cortical lesions (CLs) and atrophy are pivotal in multiple sclerosis (MS) pathology. This study determined the effect of disease modifying drugs (DMDs) on CL development and cortical atrophy progression in patients with relapsing-remitting MS (RRMS) over 48 months. Patients (n = 165) were randomized to sc IFN β-1a 44 μg, im IFN β-1a 30 μg, or glatiramer acetate 20 mg. The reference population comprised 50 DMD-untreated patients with RRMS. After 24 months, 43 of the untreated patients switched to DMDs. The four groups of patients were followed up for an additional 24 months. At 48 months the mean standard deviation number of new CLs was significantly lower in patients treated with sc IFN β-1a (1.4 ± 1.0, range 0-5) compared with im IFN β-1a (2.3 ± 1.3, range 0-6, P = 0.004) and glatiramer acetate (2.2 ± 1.5, range 0-7, P = 0.03). Significant reductions in CL accumulation and new white matter and gadolinium-enhancing lesions were also observed in the 43 patients who switched to DMDs after 24 months, compared with the 24 months of no treatment. Concluding, this study confirms that DMDs significantly reduce CL development and cortical atrophy progression compared with no treatment.01/2015; 2015:369348. DOI:10.1155/2015/369348