Background and purpose The prevalence of fatigue and its relation with clinical, neuropsychological and brain magnetic resonance imaging (MRI) variables in a large cohort of multiple sclerosis (MS) patients was investigated. Method The Modified Fatigue Impact Scale and its subdomains were collected from 725 healthy controls and 366 MS patients [238 relapsing–remitting (RRMS) and 128 progressive (PMS)]. For the Modified Fatigue Impact Scale global and subdomains, MS patients were classified as fatigued (F‐MS) or non‐fatigued (NF‐MS) according to cut‐off values provided by logistic regression models with a specificity of 90% (i.e. a 10% false‐positive rate in classifying healthy controls). MS patients underwent neurological, neuropsychological and MRI evaluations. Clinical and MRI measures were compared between F‐MS and NF‐MS patients using age‐, sex‐ and phenotype‐adjusted linear models. Heterogeneities between phenotypes were tested with specific interaction terms. Results Global fatigue affected 174 (47.5%) MS patients, being more prevalent in PMS (PMS 64.1% vs. RRMS 38.7%, P < 0.001). For all dichotomizations, F‐MS were older (P from <0.001 to 0.012) and more depressed (P < 0.001) than NF‐MS patients. Compared to NF‐MS, cognitive F‐MS patients had lower education (P = 0.035). Compared to NF‐MS, patients with global and physical fatigue had higher Expanded Disability Status Scale only for RRMS (P < 0.001). Only RRMS patients with physical fatigue had lower brain (P = 0.05), white matter (P = 0.039) and thalamic volumes (P = 0.022) compared to NF‐MS patients. Conclusions In MS, fatigue is associated with older age, lower education and higher depression. Only in RRMS, fatigue is associated with Expanded Disability Status Scale and brain atrophy. A plateauing effect of disability and structural damage can explain the lack of associations in PMS.

No abstract

ObjectivesMagnetic resonance imaging (MRI) is an important tool for diagnosis and monitoring of disease course in multiple sclerosis (MS). However, its prognostic value for predicting disease worsening is still being debated. The aim of this study was to propose a deep learning algorithm to predict disease worsening at 2 years of follow-up on a multicenter cohort of MS patients collected from the Italian Neuroimaging Network Initiative using baseline MRI, and compare it with 2 expert physicians.Materials and MethodsFor 373 MS patients, baseline T2-weighted and T1-weighted brain MRI scans, as well as baseline and 2-year clinical and cognitive assessments, were collected from the Italian Neuroimaging Network Initiative repository. A deep learning architecture based on convolutional neural networks was implemented to predict: (1) clinical worsening (Expanded Disability Status Scale [EDSS]–based model), (2) cognitive deterioration (Symbol Digit Modalities Test [SDMT]–based model), or (3) both (EDSS + SDMT–based model). The method was tested on an independent data set and compared with the performance of 2 expert physicians.ResultsFor the test set, the convolutional neural network model showed high predictive accuracy for clinical (83.3%) and cognitive (67.7%) worsening, although the highest accuracy was reached when training the algorithm using both EDSS and SDMT information (85.7%). Artificial intelligence classification performance exceeded that of 2 expert physicians (70% of accuracy for the human raters).ConclusionsWe developed a robust and accurate model for predicting clinical and cognitive worsening of MS patients after 2 years, based on conventional T2-weighted and T1-weighted brain MRI scans obtained at baseline. This algorithm may be valuable for supporting physicians in their clinical practice for the earlier identification of MS patients at risk of disease worsening.

No abstract