Personalized federated learning for predicting disability progression in multiple sclerosis using real-world routine clinical data.

To investigate disease progression and risk factors in a large geographically based population with multiple sclerosis (MS), using two different inception points--clinical onset and date of birth. The authors reviewed a database of subjects with definite MS and symptom onset prior to July 1988. The main outcome was sustained progression to Expanded Disability Status Scale (EDSS) 6 (requires a cane), using the date of birth and date of MS onset as inception points in separate analyses. Risk factors examined were sex, relapsing vs primary progressive course, onset age, and onset symptoms. The study included 2,837 patients, followed prospectively for 22,723 patient years. The median time to EDSS 6 was 27.9 years, 15 years after onset; only 21% reached EDSS 6, and by age 50, 28% required a cane. Men progressed 38% more quickly than women from onset (p < 0.0005), yet both required canes at similar ages: 58.8 years for men and 60.1 for women (p = 0.082). A younger onset age predicted a slower progression, but those older at onset were consistently older when reaching EDSS 6. A primary progressive course predicted a more rapid progression from both onset (p < 0.0005) and birth (hazard ratio = 2.7 [95% CI: 2.2 to 3.3]). No onset symptom consistently predicted progression. Disability progression in multiple sclerosis (MS) accrued more slowly than found in earlier longitudinal studies. The authors also challenged two fundamental concepts in MS, demonstrating that neither male sex nor older onset age was associated with worse disease outcome.

PurposeClinical validation of “BrainLossNet”, a deep learning-based method for fast and robust estimation of brain volume loss (BVL) from longitudinal T1-weighted MRI, for the detection of accelerated BVL in multiple sclerosis (MS) and for the discrimination between MS patients with versus without disability progression. Materials and methodsA longitudinal normative database of healthy controls (n = 563), two mono-scanner MS cohorts (n = 414, 156) and a mixed-scanner cohort acquired for various indications (n = 216) were included retrospectively. Mean observation period from the baseline (BL) to the last follow-up (FU) MRI scan was 2–3 years. Expanded Disability Status Scale (EDSS) at BL and FU was available in 149 MS patients. Annual BVL was computed using BrainLossNet and Siena and then adjusted for age. Repeated-measures ANOVA and Cohen's effect size were used to compare BrainLossNet and Siena regarding the detection of accelerated BVL and the differentiation between MS patients with versus without EDSS progression. ResultsCohen's effect size for the differentiation of patients from healthy controls based on the age-adjusted annual BVL was larger with BrainLossNet than with Siena (MS cohort 1: 0.927 versus 0.495, MS cohort 2: 0.671 versus 0.456, mixed-scanner cohort: 0.918 versus 0.730, all p < 0.001). Cohen's effect size for the discrimination between MS patients with (n = 51) versus without (n = 98) EDSS progression was larger with BrainLossNet (0.503 versus 0.400, p = 0.048). ConclusionBrainLossNet can provide added value in clinical routine and MS therapy trials regarding the detection of accelerated BVL in MS and the differentiation between MS patients with versus without disability progression.

BackgroundThere is a lack of understanding of the mechanisms by which the CNS is injured in multiple sclerosis (MS). Since Theiler’s murine encephalomyelitis virus (TMEV) infection in SJL/J mice is an established model of progressive disability in MS, and CNS atrophy correlates with progressive disability in MS, we used in vivo MRI to quantify total ventricular volume in TMEV infection. We then sought to identify immunological and virological biomarkers that correlated with increased ventricular size.MethodsMice, both infected and control, were followed for 6 months. Cerebral ventricular volumes were determined by MRI, and disability was assessed by Rotarod. A range of immunological and virological measures was obtained using standard techniques.ResultsDisability was present in infected mice with enlarged ventricles, while infected mice without enlarged ventricles had Rotarod performance similar to sham mice. Ventricular enlargement was detected as soon as 1 month after infection. None of the immunological and virological measures correlated with the development of ventricular enlargement.ConclusionsThese results support TMEV infection with brain MRI monitoring as a useful model for exploring the biology of disability progression in MS, but they did not identify an immunological or virological correlate with ventricular enlargement.

Disability progression in multiple sclerosis (MS) is strongly linked to central nervous system (CNS)-specific pathological processes that occur throughout all disease stages, but that become clinically evident in later phases of the disease. We here discuss current views and concepts for targeting progressive MS. Detailed clinical assessment of MS patients has identified an even closer entanglement of relapse-remitting and progressive disease, leading to novel concepts such as 'progression independent of relapse activity'. Evolving clinical concepts together with a focus on molecular (neurofilament light chain) and imaging (paramagnetic rim lesions) biomarkers might specifically identify patients at risk of developing progressive MS considerably earlier than before. A multitude of novel treatment approaches focus either on direct neuroaxonal protection or myelin regeneration or on beneficially modulating CNS-intrinsic or innate immune inflammation. Although some long-awaited trials have recently been unsuccessful, important lessons could still be drawn from novel trial designs providing frameworks for future clinical studies. Targeting progressive disease biology and repairing established damage is the current central challenge in the field of MS. Especially, the compartmentalized adaptive and innate CNS inflammation is an attractive target for novel approaches, probably as a combinatory approach together with neuroprotective or myelin regenerating strategies.

Short-term disability progression was predicted from a baseline evaluation in patients with multiple sclerosis (MS) using their three-dimensional T1-weighted (3DT1) magnetic resonance images (MRI). One-hundred-and-eighty-one subjects diagnosed with MS underwent 3T-MRI and were followed up for two to six years at two sites, with disability progression defined according to the expanded-disability-status-scale (EDSS) increment at the follow-up. The patients’ 3DT1 images were bias-corrected, brain-extracted, registered onto MNI space, and divided into slices along coronal, sagittal, and axial projections. Deep learning image classification models were applied on slices and devised as ResNet50 fine-tuned adaptations at first on a large independent dataset and secondly on the study sample. The final classifiers’ performance was evaluated via the area under the curve (AUC) of the false versus true positive diagram. Each model was also tested against its null model, obtained by reshuffling patients’ labels in the training set. Informative areas were found by intersecting slices corresponding to models fulfilling the disability progression prediction criteria. At follow-up, 34% of patients had disability progression. Five coronal and five sagittal slices had one classifier surviving the AUC evaluation and null test and predicted disability progression (AUC > 0.72 and AUC > 0.81, respectively). Likewise, fifteen combinations of classifiers and axial slices predicted disability progression in patients (AUC > 0.69). Informative areas were the frontal areas, mainly within the grey matter. Briefly, 3DT1 images may give hints on disability progression in MS patients, exploiting the information hidden in the MRI of specific areas of the brain.

BackgroundLow vitamin D levels, tobacco use and high body mass index (BMI) have been linked to adverse disease outcomes in multiple sclerosis (MS), but their influence on long-term disability progression remains unclear. Therefore, we explored whether these modifiable lifestyle factors were associated with 10-year clinical disability progression in patients with MS. MethodsIn this prospective study, a cohort of 88 patients with relapsing-remitting MS completed a randomized controlled study on ω-3 fatty acids between 2004 and 2008. During 24 months, serum 25-hydroxyvitamin D (25(OH)D), serum cotinine (nicotine metabolite), and BMI were repeatedly measured. In 2017, a follow-up study was conducted among 80 of the participants, including disability assessment by the Expanded Disability Status Scale (EDSS). Linear regression was used to explore associations between the lifestyle factors and the EDSS change over 10 years. ResultsHigher seasonally adjusted 25(OH)D levels were associated with lower 10-year EDSS progression (change in EDSS per 1 SD increase in 25(OH)D in a model adjusted for sex, age and baseline EDSS: -0.45 point, 95% CI: -0.75 to -0.16, p=0.003). Further adjustments for potential confounders related to lifestyle and disease status gave similar results. The association was mainly driven by low 25(OH)D levels during spring, as well as seasonally adjusted levels below 80 nmol/L. No clear association was found for BMI and cotinine. ConclusionLower 25(OH)D levels, but apparently not tobacco use or higher BMI, were significantly associated with worse long-term disability progression in MS.

Multiple sclerosis (MS) is an important cause of progressive neurological disability, typically commencing in early adulthood. There is a need for safe and effective therapy to prevent the progressive central nervous system (CNS) damage and resultant disability that characterize the disease course. Increasing evidence supports a chronic autoimmune basis for CNS damage in MS. In the present study, we review current concepts of autoimmune pathogenesis in MS, assess current therapies aimed at countering autoimmune attack and discuss potential therapeutic strategies. Among currently available therapies, beta-interferon and glatiramer acetate have a modest effect on reducing relapses and slowing the accumulation of disability in relapsing-remitting MS. Beta-interferon is of doubtful efficacy in secondary progressive MS and appears to aggravate primary progressive MS, possibly by increasing antibody-mediated CNS damage through inhibition of B-cell apoptosis. Mitoxantrone may reduce relapses and slow disability progression in relapsing-remitting and secondary progressive MS, but its use is limited by the risk of cardiomyopathy. There are currently no effective treatments for primary progressive MS. Many therapies that are effective in the animal model, experimental autoimmune encephalomyelitis (EAE), are either ineffective in MS or--in the case of gamma-interferon, lenercept and altered peptide ligands--actually make MS worse. This discrepancy may be explained by the occurrence in MS of defects in immunoregulatory mechanisms, the integrity of which is essential for the efficacy of these treatments in EAE. It is likely that the development of safe, effective therapy for MS will depend on a better understanding of immunoregulatory defects in MS.

Disability in progressive MS is associated with T2 lesion changes

Disability in multiple sclerosis is associated with vascular factors: An ultrasound study

To perform a meta-analysis of randomized, blinded, multiple sclerosis (MS) clinical trials, to test the hypothesis that efficacy of immunomodulatory disease-modifying therapies (DMTs) on MS disability progression is strongly dependent on age. We performed a literature search with pre-defined criteria and extracted relevant features from 38 clinical trials that assessed efficacy of DMTs on disability progression. We fit a linear regression, weighted for trial sample size, and duration, to examine the hypothesis that age has a defining effect on the therapeutic efficacy of immunomodulatory DMTs. More than 28,000 MS subjects participating in trials of 13 categories of immunomodulatory drugs are included in the meta-analysis. The efficacy of immunomodulatory DMTs on MS disability strongly decreased with advancing age (R2 = 0.6757, p = 6.39e-09). Inclusion of baseline EDSS did not significantly improve the model. The regression predicts zero efficacy beyond approximately age 53 years. The comparative efficacy rank derived from the regression residuals differentiates high- and low-efficacy drugs. High-efficacy drugs outperform low-efficacy drugs in inhibiting MS disability only for patients younger than 40.5 years. The meta-analysis supports the notion that progressive MS is simply a later stage of the MS disease process and that age is an essential modifier of a drug efficacy. Higher efficacy treatments exert their benefit over lower efficacy treatments only during early stages of MS, and, after age 53, the model suggests that there is no predicted benefit to receiving immunomodulatory DMTs for the average MS patient.

To assess whether biological aging as measured by leukocyte telomere length (LTL) is associated with clinical disability and brain volume loss in multiple sclerosis (MS). Adults with MS/clinically isolated syndrome in the University of California, San Francisco EPIC cohort study were included. LTL was measured on DNA samples by quantitative polymerase chain reaction and expressed as telomere to somatic DNA (T/S) ratio. Expanded Disability Status Scale (EDSS) and 3-dimensional T1-weighted brain magnetic resonance imaging were performed at baseline and follow-up. Associations of baseline LTL with cross-sectional and longitudinal outcomes were assessed using simple and mixed effects linear regression models. A subset (n = 46) had LTL measured over time, and we assessed the association of LTL change with EDSS change with mixed effects models. Included were 356 women and 160 men (mean age = 43 years, median disease duration = 6 years, median EDSS = 1.5 [range = 0-7], mean T/S ratio = 0.97 [standard deviation = 0.18]). In baseline analyses adjusted for age, disease duration, and sex, for every 0.2 lower LTL, EDSS was 0.27 higher (95% confidence interval [CI] = 0.13-0.42, p < 0.001) and brain volume was 7.4mm3 lower (95% CI = 0.10-14.7, p = 0.047). In longitudinal adjusted analyses, those with lower baseline LTL had higher EDSS and lower brain volumes over time. In adjusted analysis of the subset, LTL change was associated with EDSS change over 10 years; for every 0.2 LTL decrease, EDSS was 0.34 higher (95% CI = 0.08-0.61, p = 0.012). Shorter telomere length was associated with disability independent of chronological age, suggesting that biological aging may contribute to neurological injury in MS. Targeting aging-related mechanisms is a potential therapeutic strategy against MS progression. ANN NEUROL 2019;86:671-682.

Accelerometry-derived activity fragmentation reflects how frequently active periods are broken by sedentary periods. It has been associated with frailty, mortality, and reduced gait speed in the general population; however, its prognostic significance in multiple sclerosis (MS) remains unknown. People with MS (PwMS) wore wrist tri-axial accelerometers at three-month intervals, underwent disability assessments biannually and MRI brain approximately annually. We evaluated whether active-to-sedentary transition probability (ASTP) and sedentary-to-active transition probability (SATP) during the 10 most active hours of each 24-hour period (M10) were associated with confirmed disability progression and brain substructure atrophy, by modeling between- and within-person effects. Among 239 PwMS, 120 had confirmed Expanded Disability Status Scale(EDSS)-plus progression over a mean of 2.9±1.1 years. Within-person increase in ASTP slope during M10 (indicating increasing activity fragmentation throughout M10) was associated with higher risk of subsequent EDSS-plus progression (per 1 SD increase: HR 1.22 [95%CI 1.02,1.46],p=0.03) and lower deep gray matter and thalamic volumes over time (per 1 SD increase: -0.35 [95%CI - 0.58,-0.13],p=0.002, -0.42 [95%CI:-0.68,-0.15],p=0.002 respectively). There were no similar associations for SATP. Within-person worsening in activity fragmentation was associated with higher risk of neurologic decline. Activity fragmentation may represent an early compensatory strategy for reduced physiologic reserve and serve as an early indicator of MS progression.

ABSTRACTIntroduction: Multiple sclerosis (MS) is a chronic inflammatory, demyelinating disease of the central nervous system affecting both white matter and grey matter in the earliest phases of its course. The crucial role of neurodegeneration in disability progression in MS, regardless of white matter damage, has been confirmed by several imaging and neuropathological studies. Fingolimod is an effective immunomodulator of the sphingosine 1-phosphate receptor, approved in relapsing remitting MS and able to cross the blood–brain barrier and to slow disability progression and brain volume loss. However, it remains unclear whether this neuroprotective action is due to a peripheral anti-inflammatory effect and/or to a direct effect on neuronal cells.Areas covered: In this review, the authors summarize the published preclinical and clinical studies on the effect of Fingolimod in limiting the focal and diffuse grey matter damage in MS.Expert opinion: Fingolimod might have a significant neuroprotective effect on relapsing remitting MS based on its modulatory effect on oligodendroglial cells and astrocytes, and on its direct effect on cortical neurons. Future clinical studies including measures of grey matter damage are required to confirm in vivo such neuroprotective effect.

To investigate the association between serum levels of neurofilament light chain (sNfL) and atrophied T2 lesion volume (LV) and other MRI measures indicative of inflammation and neurodegeneration, and disability progression (DP) in multiple sclerosis (MS).

Smoking is associated with a more severe disease course in people with multiple sclerosis (MS). The magnitude of effect of smoking cessation on MS progression is unknown. The aim of this study was to quantify the impact of smoking cessation on reaching MS disability milestones. This is a cross-sectional study with retrospective reports. A comprehensive smoking questionnaire was sent to 1270 patients with MS registered between 1994 and 2013 in the Nottingham University Hospital MS Clinics database. Demographic and clinical data were extracted from the clinical database. Cox proportional hazard regression was used to estimate effects of smoke-free years on the time to Expanded Disability Status Scale (EDSS) scores 4.0 and 6.0. MS Impact Scale 29 and Patient Determined Disease Steps were used to assess the physical and psychological impact of smoking. Each "smoke-free year" was associated with 0.96 (95% confidence interval: 0.95 to 0.97) times decreased risk of reaching EDSS 4.0 and 0.97 (95% confidence interval: 0.95 to 0.98) times decreased risk of reaching EDSS 6.0. Nonsmokers showed a significantly lower level of disability in all the self-reported outcomes compared with current smokers. The reduction in the risk of disability progression after smoking cessation is significant and time dependent. The earlier the patients quit, the stronger the reduction in the risk of reaching disability milestones. The quantitative estimates of the impact of smoking cessation on reaching disability milestones in MS can be used in interventional trials. This study provides for the first time quantitative estimates of the effects of smoking cessation in MS, essential for informing smoking cessation trials. The clear effect of smoking cessation on MS progression suggests the need to consider adjusting for smoking cessation when assessing for treatment effects in clinical trials of treatments for MS. Smoking cessation should be an early intervention in people with MS.