Background: Radiologically isolated syndrome (RIS) is defined by MRI findings that are suggestive of multiple sclerosis (MS) in the absence of prior clinical demyelinating events. We aimed to compare the health-related quality of life (HRQoL) between RIS and relapsing–remitting MS (RRMS) after adjusting for fatigue, cognition, and psychological distress, and to contextualize generic HRQoL, relative to healthy controls. Methods: In this cross-sectional analysis of the baseline data, 30 RIS, 29 RRMS, and 30 healthy controls were analyzed. MS-specific HRQoL (patients only) was assessed with the Functional Assessment of Multiple Sclerosis (FAMS), and generic HRQoL (all participants) was assessed with the EuroQol-5D (EQ-5D) visual analogue scale and utility index. Multi-variable linear regression models with robust (HC3) standard errors were used, adjusting for demographics, fatigue impact, cognitive performance, and psychological distress. Results: The FAMS totals were similar in RIS vs. RRMS (median 167.5 vs. 164.0; p = 0.694) and remained non-different after adjustment (β= −2.37, 95% CI −10.18 to 5.44; p = 0.544). EQ-5D outcomes showed an unadjusted gradient across groups, but adjusted differences relative to RIS were not statistically significant. Greater fatigue impact was associated with poorer HRQoL across all models (all p < 0.001). Psychological distress was associated with lower FAMS (β = −14.53; p < 0.001) but not with EQ-5D outcomes. Conclusions: HRQoL in RIS was comparable to RRMS, and fatigue impact was the most consistent correlate of poorer HRQoL.
Background: Radiologically isolated syndrome (RIS) is defined by MRI findings suggestive of multiple sclerosis (MS) in the absence of prior clinical demyelinating events. We aimed to compare health-related quality of life (HRQoL) between RIS and relapsing–remitting MS (RRMS) after adjusting for fatigue, cognition, and psychological distress, and to contextualize generic HRQoL relative to healthy controls. Methods: Data from 30 RIS, 29 RRMS, and 30 healthy controls were analyzed. MS-specific HRQoL (patients only) was assessed with the Functional Assessment of Multiple Sclerosis (FAMS), and generic HRQoL (all participants) was assessed with the EuroQol-5D (EQ-5D) visual analogue scale and utility index. Multivariable linear regression with robust (HC3) standard errors adjusted for demographics, fatigue impact, cognitive performance, and psychological distress. Results: FAMS totals were similar in RIS vs RRMS (median 167.50 vs 164.0; p=0.694) and remained non-different after adjustment (β=−2.37, 95% CI −10.18 to 5.44; p=0.544). EQ-5D outcomes showed an unadjusted gradient across groups, but adjusted differences relative to RIS were not statistically significant. Greater fatigue impact was associated with poorer HRQoL across all models (all p < 0.001). Psychological distress was associated with lower FAMS (β = -14.53; p < 0.001) but not with EQ-5D outcomes. Conclusion: HRQoL in RIS was comparable to RRMS; fatigue impact was the most consistent correlate of poorer HRQoL.
Background and purpose: The unanticipated detection by magnetic resonance imaging (MRI) in the brain of asymptomatic subjects of white matter lesions suggestive of multiple sclerosis (MS) has been named radiologically isolated syndrome (RIS). As the difference between early MS [i.e. clinically isolated syndrome (CIS)] and RIS is the occurrence of a clinical event, it is logical to improve detection of the subclinical form without interfering with MRI as there are radiological diagnostic criteria for that. Our objective was to use machine-learning classification methods to identify morphometric measures that help to discriminate patients with RIS from those with CIS. Methods: We used a multimodal 3-T MRI approach by combining MRI biomarkers (cortical thickness, cortical and subcortical grey matter volume, and white matter integrity) of a cohort of 17 patients with RIS and 17 patients with CIS for single-subject level classification. Results: The best proposed models to predict the diagnosis of CIS and RIS were based on the Naive Bayes, Bagging and Multilayer Perceptron classifiers using only three features: the left rostral middle frontal gyrus volume and the fractional anisotropy values in the right amygdala and right lingual gyrus. The Naive Bayes obtained the highest accuracy [overall classification, 0.765; area under the receiver operating characteristic (AUROC), 0.782]. Conclusions: A machine-learning approach applied to multimodal MRI data may differentiate between the earliest clinical expressions of MS (CIS and RIS) with an accuracy of 78%. Keywords: Bagging; Multilayer Perceptron; Naive Bayes classifier; clinically isolated syndrome; diffusion tensor imaging; machine-learning; magnetic resonance imaging; multiple sclerosis; radiologically isolated syndrome.