Predicting clinical progression in multiple sclerosis after 6 and 12 years

Long-term disability trajectories in multiple sclerosis: a group-based trajectory analysis of the AusLong cohort

BACKGROUND

Previous natural history studies highlighted a consistent heterogeneity of disability trajectories among individuals with primary or secondary progressive multiple sclerosis (MS). However, evidence on disability progression in relapsing onset MS is scarce.The aim of this study was to investigate heterogeneity in disability accumulation over 10 years following a first clinical diagnosis of central nervous system demyelination (FCD) and identify genetic, demographic, environmental and clinical factors associated with these trajectories.

METHODS

We used group-based trajectory models to measure heterogeneity in disability trajectories based on the Expanded Disability Status Scale (EDSS) in a prospectively assessed cohort of 263 participants. To capture sustained neurological impairments and avoid issues related to significant changes in EDSS associated with relapse, we did not consider EDSS points recorded within 3 months of a relapse.

RESULTS

We identified three distinct and clinically meaningful disability trajectories: No/minimal, moderate and severe. Those in the no/minimal disability trajectory showed no appreciable progression of disability (median EDSS∼1 at 10-year review) while those in the moderate and severe disability trajectories experienced disability worsening (median time to reach EDSS 4 was 9 and 7 years, respectively). Compared with the no/minimal disability trajectory, those with older age, a higher number of relapses within the first 5 years post-FCD, and a higher number of comorbidities at baseline were more likely to be in the worse disability trajectory. Surprisingly, baseline MRI and anatomical site of initial symptoms did not influence long-term outcomes.

CONCLUSIONS

Those at higher risk of faster MS disability progression can be identified based on their early clinical characteristics with potential therapeutic implications for early intervention and treatment escalation.

Evaluation of machine learning-based classification of clinical impairment and prediction of clinical worsening in multiple sclerosis

BACKGROUND

Robust predictive models of clinical impairment and worsening in multiple sclerosis (MS) are needed to identify patients at risk and optimize treatment strategies.

OBJECTIVE

To evaluate whether machine learning (ML) methods can classify clinical impairment and predict worsening in people with MS (pwMS) and, if so, which combination of clinical and magnetic resonance imaging (MRI) features and ML algorithm is optimal.

METHODS

We used baseline clinical and structural MRI data from two MS cohorts (Berlin: n = 125, Amsterdam: n = 330) to evaluate the capability of five ML models in classifying clinical impairment at baseline and predicting future clinical worsening over a follow-up of 2 and 5 years. Clinical worsening was defined by increases in the Expanded Disability Status Scale (EDSS), Timed 25-Foot Walk Test (T25FW), 9-Hole Peg Test (9HPT), or Symbol Digit Modalities Test (SDMT). Different combinations of clinical and volumetric MRI measures were systematically assessed in predicting clinical outcomes. ML models were evaluated using Monte Carlo cross-validation, area under the curve (AUC), and permutation testing to assess significance.

RESULTS

The ML models significantly determined clinical impairment at baseline for the Amsterdam cohort, but did not reach significance for predicting clinical worsening over a follow-up of 2 and 5 years. High disability (EDSS ≥ 4) was best determined by a support vector machine (SVM) classifier using clinical and global MRI volumes (AUC = 0.83 ± 0.07, p = 0.015). Impaired cognition (SDMT Z-score ≤ -1.5) was best determined by a SVM using regional MRI volumes (thalamus, ventricles, lesions, and hippocampus), reaching an AUC of 0.73 ± 0.04 (p = 0.008).

CONCLUSION

ML models could aid in classifying pwMS with clinical impairment and identify relevant biomarkers, but prediction of clinical worsening is an unmet need.

The macular retinal ganglion cell layer as a biomarker for diagnosis and prognosis in multiple sclerosis: A deep learning approach

PURPOSE

The macular ganglion cell layer (mGCL) is a strong potential biomarker of axonal degeneration in multiple sclerosis (MS). For this reason, this study aims to develop a computer-aided method to facilitate diagnosis and prognosis in MS.

METHODS

This paper combines a cross-sectional study of 72 MS patients and 30 healthy control subjects for diagnosis and a 10-year longitudinal study of the same MS patients for the prediction of disability progression, during which the mGCL was measured using optical coherence tomography (OCT). Deep neural networks were used as an automatic classifier.

RESULTS

For MS diagnosis, greatest accuracy (90.3%) was achieved using 17 features as inputs. The neural network architecture comprised the input layer, two hidden layers and the output layer with softmax activation. For the prediction of disability progression 8 years later, accuracy of 81.9% was achieved with a neural network comprising two hidden layers and 400 epochs.

CONCLUSION

We present evidence that by applying deep learning techniques to clinical and mGCL thickness data it is possible to identify MS and predict the course of the disease. This approach potentially constitutes a non-invasive, low-cost, easy-to-implement and effective method.

Brain and cognitive reserve mitigate balance dysfunction in multiple sclerosis

BACKGROUND

Approximately two-thirds of patients with multiple sclerosis (MS) complain different degrees of balance dysfunction, but some of them are able to withstand considerable disease burden without an overt balance impairment. Here, we tested the hypothesis that brain and cognitive reserve lessen the effect of MS-related tissue damage on balance control.

METHODS

We measured the postural sway of 148 patients and 74 sex- and age-matched healthy controls by force platform under different conditions reflecting diverse neuro-pathological substrates of balance dysfunction: eyes opened (EO), eyes closed (EC), and while performing the Stroop test, i.e., dual-task (DT). Lesion volumes on T2-hyperintense and T1-hypointense sequences, and normalized brain volume provided estimations of MS-related tissue damage in patients with MS. Hierarchical linear regressions explored the protective effect against the MS-related tissue damage of intracranial volume and educational attainment (proxies for brain and cognitive reserve, respectively) on balance.

RESULTS

Larger intracranial volume and high educational attainment mitigated the detrimental effect of MS-related tissue damage on postural sway under EO (adjusted-R2=0.20 and 0.27, respectively, p<0.01) and DT (adjusted-R2=0.22 and 0.30, respectively, p<0.06) conditions. Neither educational level nor brain size was associated with postural sway under EC condition.

CONCLUSION

Our findings suggest a protective role of brain and cognitive reserve even on balance, an outcome that relies on both motor control and higher order processing resources. The lack of a protective effect on postural sway under EC condition confirms that this latter outcome is closer associated with spinal cord rather than brain damage.

Predicting multiple sclerosis severity with multimodal deep neural networks

Multiple Sclerosis (MS) is a chronic disease developed in the human brain and spinal cord, which can cause permanent damage or deterioration of the nerves. The severity of MS disease is monitored by the Expanded Disability Status Scale, composed of several functional sub-scores. Early and accurate classification of MS disease severity is critical for slowing down or preventing disease progression via applying early therapeutic intervention strategies. Recent advances in deep learning and the wide use of Electronic Health Records (EHR) create opportunities to apply data-driven and predictive modeling tools for this goal. Previous studies focusing on using single-modal machine learning and deep learning algorithms were limited in terms of prediction accuracy due to data insufficiency or model simplicity. In this paper, we proposed the idea of using patients' multimodal longitudinal and longitudinal EHR data to predict multiple sclerosis disease severity in the future. Our contribution has two main facets. First, we describe a pioneering effort to integrate structured EHR data, neuroimaging data and clinical notes to build a multi-modal deep learning framework to predict patient's MS severity. The proposed pipeline demonstrates up to 19% increase in terms of the area under the Area Under the Receiver Operating Characteristic curve (AUROC) compared to models using single-modal data. Second, the study also provides valuable insights regarding the amount useful signal embedded in each data modality with respect to MS disease prediction, which may improve data collection processes.

Systematic review of cognitive reserve in multiple sclerosis: Accounting for physical disability, fatigue, depression, and anxiety

BACKGROUND

Cognitive reserve (CR) describes an individual's ability to adapt cognitive processes in response to brain atrophy, and has been reported to explain some of the discrepancy between brain atrophy and cognitive functioning outcomes in multiple sclerosis (MS). CR in MS is typically investigated by assessing an individual's pre- and/or post-diagnosis enrichment, which includes premorbid intellectual abilities, educational level, occupational attainment, and engagement in cognitively enriching leisure activities. Common MS symptoms (e.g., physical disability, fatigue, depression, anxiety) may impact an individual's ability to engage in various CR-enhancing activities post-diagnosis. It is unknown to what extent these MS symptoms have been taken into account in MS research on CR. As such, we identified whether studies assessed CR using measures of premorbid or continuous (including post-diagnosis) enrichment. For studies investigating continuous enrichment, we identified whether studies accounted for MS-impact, which MS symptoms were accounted for, and how, and whether studies acknowledged MS symptoms as potential CR-confounds.

METHODS

Three electronic databases (PsycINFO, PubMed, Scopus) were searched. Eligible studies investigated CR proxies (e.g., estimated premorbid intellectual abilities, vocabulary knowledge, educational level, occupational attainment, cognitively enriching leisure activities, or a combination thereof) in relation to cognitive, brain atrophy or connectivity, or daily functioning outcomes in adult participants with MS. We extracted data on methods and measures used, including any MS symptoms taken into account. Objectives were addressed using frequency analyses and narrative synthesis.

RESULTS

115 studies were included in this review. 47.8% of all studies investigated continuous enrichment. Approximately half of the studies investigating continuous enrichment accounted for potential MS-impact in their analyses, with only 31.0% clearly identifying that they treated MS symptoms as potential confounds for CR-enhancement. A narrative synthesis of studies which investigated CR with and without controlling statistically for MS-impact indicated that accounting for MS symptoms may impact findings concerning the protective nature of CR.

CONCLUSION

Fewer than half of the studies investigating CR proxies in MS involved continuous enrichment. Just over half of these studies accounted for potential MS-impact in their analyses. To achieve a more complete and accurate understanding of CR in MS, future research should investigate both pre-MS and continuous enrichment. In doing so, MS symptoms and their potential impact should be considered. Establishing greater consistency and rigour across CR research in MS will be crucial to produce an evidence base for the development of interventions aimed at improving quality of care and life for pwMS.

Prognostic models for predicting clinical disease progression, worsening and activity in people with multiple sclerosis

BACKGROUND

Multiple sclerosis (MS) is a chronic inflammatory disease of the central nervous system that affects millions of people worldwide. The disease course varies greatly across individuals and many disease-modifying treatments with different safety and efficacy profiles have been developed recently. Prognostic models evaluated and shown to be valid in different settings have the potential to support people with MS and their physicians during the decision-making process for treatment or disease/life management, allow stratified and more precise interpretation of interventional trials, and provide insights into disease mechanisms. Many researchers have turned to prognostic models to help predict clinical outcomes in people with MS; however, to our knowledge, no widely accepted prognostic model for MS is being used in clinical practice yet.

OBJECTIVES

To identify and summarise multivariable prognostic models, and their validation studies for quantifying the risk of clinical disease progression, worsening, and activity in adults with MS.

SEARCH METHODS

We searched MEDLINE, Embase, and the Cochrane Database of Systematic Reviews from January 1996 until July 2021. We also screened the reference lists of included studies and relevant reviews, and references citing the included studies.

SELECTION CRITERIA

We included all statistically developed multivariable prognostic models aiming to predict clinical disease progression, worsening, and activity, as measured by disability, relapse, conversion to definite MS, conversion to progressive MS, or a composite of these in adult individuals with MS. We also included any studies evaluating the performance of (i.e. validating) these models. There were no restrictions based on language, data source, timing of prognostication, or timing of outcome.

DATA COLLECTION AND ANALYSIS

Pairs of review authors independently screened titles/abstracts and full texts, extracted data using a piloted form based on the Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS), assessed risk of bias using the Prediction Model Risk Of Bias Assessment Tool (PROBAST), and assessed reporting deficiencies based on the checklist items in Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD). The characteristics of the included models and their validations are described narratively. We planned to meta-analyse the discrimination and calibration of models with at least three external validations outside the model development study but no model met this criterion. We summarised between-study heterogeneity narratively but again could not perform the planned meta-regression.

MAIN RESULTS

We included 57 studies, from which we identified 75 model developments, 15 external validations corresponding to only 12 (16%) of the models, and six author-reported validations. Only two models were externally validated multiple times. None of the identified external validations were performed by researchers independent of those that developed the model. The outcome was related to disease progression in 39 (41%), relapses in 8 (8%), conversion to definite MS in 17 (18%), and conversion to progressive MS in 27 (28%) of the 96 models or validations. The disease and treatment-related characteristics of included participants, and definitions of considered predictors and outcome, were highly heterogeneous amongst the studies. Based on the publication year, we observed an increase in the percent of participants on treatment, diversification of the diagnostic criteria used, an increase in consideration of biomarkers or treatment as predictors, and increased use of machine learning methods over time. Usability and reproducibility All identified models contained at least one predictor requiring the skills of a medical specialist for measurement or assessment. Most of the models (44; 59%) contained predictors that require specialist equipment likely to be absent from primary care or standard hospital settings. Over half (52%) of the developed models were not accompanied by model coefficients, tools, or instructions, which hinders their application, independent validation or reproduction. The data used in model developments were made publicly available or reported to be available on request only in a few studies (two and six, respectively). Risk of bias We rated all but one of the model developments or validations as having high overall risk of bias. The main reason for this was the statistical methods used for the development or evaluation of prognostic models; we rated all but two of the included model developments or validations as having high risk of bias in the analysis domain. None of the model developments that were externally validated or these models' external validations had low risk of bias. There were concerns related to applicability of the models to our research question in over one-third (38%) of the models or their validations. Reporting deficiencies Reporting was poor overall and there was no observable increase in the quality of reporting over time. The items that were unclearly reported or not reported at all for most of the included models or validations were related to sample size justification, blinding of outcome assessors, details of the full model or how to obtain predictions from it, amount of missing data, and treatments received by the participants. Reporting of preferred model performance measures of discrimination and calibration was suboptimal.

AUTHORS' CONCLUSIONS

The current evidence is not sufficient for recommending the use of any of the published prognostic prediction models for people with MS in clinical routine today due to lack of independent external validations. The MS prognostic research community should adhere to the current reporting and methodological guidelines and conduct many more state-of-the-art external validation studies for the existing or newly developed models.

The association between brain volume loss and disability in multiple sclerosis: A systematic review

BACKGROUND

Multiple sclerosis (MS) is a chronic, inflammatory, demyelinating, degenerative disease of the central nervous system that affects approximately 2.8 million people worldwide. Compelling evidence from observational studies and clinical trials indicates a strong association between brain volume loss (BVL) and the accumulation of disability in MS. However, the considerable heterogeneity in study designs and methods of assessment of BVL invites questions concerning the generalizability of the reported findings. Therefore, we conducted this systematic review to characterize the relationship between BVL and physical disability in patients with MS.

METHODS

A systematic literature search of MEDLINE and EMBASE databases was performed supplemented by gray literature searches. The following study designs were included: prospective/retrospective cohort, cross-sectional and case-control. Only English language articles published from 2010 onwards were eligible for final inclusion. There were no restrictions on MS subtype, age, or ethnicity. Of the 1620 citations retrieved by the structured searches, 50 publications met our screening criteria and were included in the final data set.

RESULTS

Across all BVL measures, there was considerable heterogeneity in studies regarding the underlying study population, the definitions of BVL and image analysis methodologies, the physical disability measure used, the measures of association reported and whether the analysis conducted was univariable or multivariable. A total of 36 primary studies providing data on the association between whole BVL and physical disability in MS collectively suggest that whole brain atrophy is associated with greater physical disability progression in MS patients. Similarly, a total of 15 primary studies providing data on the association between ventricular atrophy and physical disability in MS suggest that ventricular atrophy is associated with greater physical disability progression in MS patients. Along similar lines, the existing evidence based on a total of 13 primary studies suggests that gray matter atrophy is associated with greater physical disability progression in MS patients. Four primary studies suggest that corpus callosum atrophy is associated with greater physical disability progression in MS patients. The majority of the existing evidence (6 primary studies) suggests no association between white matter atrophy and physical disability in MS. It is difficult to assign a relationship between basal ganglia volume loss and physical disability as well as medulla oblongata width and physical disability in MS due to very limited data.

CONCLUSION

The evidence gathered from this systematic review, although very heterogeneous, suggests that whole brain atrophy is associated with greater physical disability progression in MS patients. Our review can help define future imaging biomarkers for physical disability progression and treatment monitoring in MS.

Relationship between paramagnetic rim lesions and slowly expanding lesions in multiple sclerosis

BACKGROUND

Magnetic resonance imaging (MRI) markers for chronic active lesions in MS include slowly expanding lesions (SELs) and paramagnetic rim lesions (PRLs).

OBJECTIVES

To identify the relationship between SELs and PRLs in MS, and their association with disability.

METHODS

61 people with MS (pwMS) followed retrospectively with MRI including baseline susceptibility-weighted imaging, and longitudinal T1 and T2-weighted scans. SELs were computed using deformation field maps; PRLs were visually identified. Mixed-effects models assessed differences in Expanded Disability Status Scale (EDSS) score changes between the group defined by the presence of SELs and or PRLs.

RESULTS

The median follow-up time was 3.2 years. At baseline, out of 1492 lesions, 616 were classified as SELs, and 80 as PRLs. 92% of patients had ⩾ 1 SEL, 56% had ⩾ 1 PRL, while both were found in 51%. SELs compared to non-SELs were more likely to also be PRLs (7% vs. 4%, p = 0.027). PRL counts positively correlated with SEL counts (ρ= 0.28, p = 0.03). SEL + PRL + patients had greater increases in EDSS over time (beta = 0.15/year, 95% confidence interval (0.04, 0.27), p = 0.009) than SEL+PRL-patients.

CONCLUSION

SELs are more numerous than PRLs in pwMS. Compared with either SELs or PRLs found in isolation, their joint occurrence was associated with greater clinical progression.

Recent Progress in the Identification of Early Transition Biomarkers from Relapsing-Remitting to Progressive Multiple Sclerosis

Despite extensive research into the pathophysiology of multiple sclerosis (MS) and recent developments in potent disease-modifying therapies (DMTs), two-thirds of relapsing-remitting MS patients transition to progressive MS (PMS). The main pathogenic mechanism in PMS is represented not by inflammation but by neurodegeneration, which leads to irreversible neurological disability. For this reason, this transition represents a critical factor for the long-term prognosis. Currently, the diagnosis of PMS can only be established retrospectively based on the progressive worsening of the disability over a period of at least 6 months. In some cases, the diagnosis of PMS is delayed for up to 3 years. With the approval of highly effective DMTs, some with proven effects on neurodegeneration, there is an urgent need for reliable biomarkers to identify this transition phase early and to select patients at a high risk of conversion to PMS. The purpose of this review is to discuss the progress made in the last decade in an attempt to find such a biomarker in the molecular field (serum and cerebrospinal fluid) between the magnetic resonance imaging parameters and optical coherence tomography measures.

Association of volumetric MRI measures and disability in MS patients of the same age: Descriptions from a birth year cohort

BACKGROUND AND OBJECTIVES

Although MRI-based markers of neuroinflammation have proven crucial for the diagnosis of multiple sclerosis (MS), predicting clinical progression with inflammation remains difficult. Neurodegenerative markers such as brain volume loss show stronger clinical (predictive) correlations, but also harbor age-related variation that must be disentangled from disease duration. In this study we investigated how clinical disability is related to volumetric MRI measures in a cohort of MS patients and healthy controls (HC) of the same age: Project Y.

METHODS

This study included 234 MS patients born in 1966 and 112 HC born between 1965 and 1967 in the Netherlands. Disability was quantified using the expanded disability status scale (EDSS), nine hole peg test (9HPT), and timed 25 foot walking test (T25FWT). Volumes were quantified on 3T MRI as normalized whole brain (NBV) and regional gray matter (GM) volumes using the same scanner and MRI protocol: cortical (normalized cortical gray matter volume; NCGMV), deep (NDGMV), thalamic (NThalV), and cerebellar (NCbV) GM volumes. In addition, mean upper cervical cord area (MUCCA), white matter lesion volume (LV), and spinal cord lesions were assessed. These measures were compared between patients and HC, and related to disability measures using linear regression.

RESULTS

Mean age of people with MS (PwMS) was 52.8 years (SD 0.9) and median disease duration 15.8 years (IQR 8.7-24.8). All global and regional brain measures were lower in MS patients compared to HC. Univariate regression models showed that NDGMV (β = -0.20) and MUCCA (β = -0.38) were most strongly related to the EDSS in all PwMS. After subtype stratification, MUCCA was most strongly related to the EDSS (β = -0.60) and 9HPT (β = -0.55) in secondary progressive PwMS. Multivariate regression models demonstrated that in all PwMS, the EDSS was best explained by lower MUCCA, longer disease durations and a progressive disease course (adjusted-R (Sastre-Garriga et al., 2017) = 0.26, p < 0.001). MUCCA was a consistent correlate in separate models of the EDSS for all PwMS, relapsing and progressive onset PwMS. The 9HPT (adjusted-R (Sastre-Garriga et al., 2017) = 0.20, p < 0.001) was best explained by lower MUCCA, higher LV and pack years, while lower limb disability (adjusted-R (Sastre-Garriga et al., 2017) = 0.11, p < 0.001) was best explained by lower MUCCA, progressive onset MS and female sex.

DISCUSSION

Our results indicate that in a cohort unbiased by age differences, spinal cord and deep gray matter volumes best related to physical disability. Our results support the use of these measures in clinical practice and trials.

Large-scale cross-sectional online survey on patient-neurologist communication, burden of disease assessment and disease monitoring in people with multiple sclerosis

Background

Management of multiple sclerosis (MS) requires a high level of communication between health care professionals (HCPs) and people with MS (pwMS) including profound investigation and discussion of symptoms to identify therapeutic needs. For treatment decisions, monitoring of disease activity is important, in this respect self-monitoring devices and apps, as well as magnetic resonance imaging are important tools.

Methods

MS Perspectives is a cross-sectional online survey conducted in Germany which was designed to collect data, among others, on the communication between pwMS and HCPs regarding treatment goals, symptom assessment, usage of devices and apps to self-monitor health functions, as well as to identify patients' attitude toward the role of magnetic resonance imaging (MRI). Between December 2021 and February 2022, 4,555 pwMS completed the survey.

Results

In total, 63.7% of participants reported that treatment goals have been discussed with their HCPs. Symptoms worsening in the past 12 months independent of relapses was more often reported by pwMS than inquired by HCPs, according to patients' report. Devices or apps for health monitoring were used by less than half of participants. Frequency of MRI controls was much lower in participants with longer compared to shorter disease duration (47.5 vs. 86.3%). The proportion of patients with annual or semiannual scans was highest among pwMS receiving infusion therapy (93.5%), followed by oral medication (82.5%) and injectables (73.4%), and lowest for pwMS without immunotherapy (58.2%).

Conclusion

MS Perspectives identified a rather low patient involvement regarding treatment goals and symptom assessment in clinical practice. Regarding this and our findings for health self-monitoring and MRI usage, strategies for improving patient-HCP communication and disease monitoring may be considered.

Rapid, non-contact multifocal visual assessment in multiple sclerosis

OBJECTIVE

Previous work on temporally sparse multifocal methods suggests that the results are correlated with disability and progression in people with multiple sclerosis (PwMS). Here, we assess the diagnostic power of three cortically mediated sparse multifocal pupillographic objective perimetry (mfPOP) methods that quantified response-delay and light-sensitivity at up to 44 regions of both visual fields concurrently.

METHODS

One high-spatial-resolution mfPOP method, P129, and two rapid medium-resolution methods, W12 and W20, were tested on 44 PwMS and controls. W12 and W20 took 82 s to test both visual fields concurrently, providing response delay and sensitivity at each field location, while P129 took 7 min. Diagnostic power was assessed using areas under the receiver operating characteristic (AUROC) curves and effect-size (Hedges' g). Linear models examined significance. Concurrent testing of both eyes permitted assessment of between-eye asymmetries.

RESULTS

Per-region response delays and asymmetries achieved AUROCs of 86.6% ± 4.72% (mean ± SE) in relapsing-remitting MS, and 96.5% ± 2.30% in progressive MS. Performance increased with increasing disability scores, with even moderate EDSS 2 to 4.5 PwMS producing AUROCs of 82.1 to 89.8%, Hedge's g values up to 2.06, and p = 4.0e - 13. All tests performed well regardless of any history of optic neuritis. W12 and W20 performed as well or better than P129.

CONCLUSION

Overall, the 82-s tests (W12 and W20) performed better than P129. The results suggest that mfPOP assesses a correlate of disease severity rather than a history of inflammation, and that it may be useful in the clinical management of PwMS.

Spinal cord lesions and brain grey matter atrophy independently predict clinical worsening in definite multiple sclerosis: a 5-year, multicentre study

OBJECTIVES

To evaluate the combined contribution of brain and cervical cord damage in predicting 5-year clinical worsening in a multicentre cohort of definite multiple sclerosis (MS) patients.

METHODS

Baseline 3.0T brain and cervical cord T2-weighted and three-dimensional T1-weighted MRI was acquired in 367 patients with MS (326 relapse-onset and 41 progressive-onset) and 179 healthy controls. Expanded Disability Status Scale (EDSS) score was obtained at baseline and after a median follow-up of 5.1 years (IQR=4.8-5.2). At follow-up, patients were classified as clinically stable/worsened according to EDSS changes. Generalised linear mixed models identified predictors of clinical worsening, evolution to secondary progressive (SP) MS and reaching EDSS=3.0, 4.0 and 6.0 milestones at 5 years.

RESULTS

At follow-up, 120/367 (33%) patients with MS worsened clinically; 36/256 (14%) patients with relapsing-remitting evolved to SPMS. Baseline predictors of EDSS worsening were progressive-onset versus relapse-onset MS (standardised beta (β)=0.97), higher EDSS (β=0.41), higher cord lesion number (β=0.41), lower normalised cortical volume (β=-0.15) and lower cord area (β=-0.28) (C-index=0.81). Older age (β=0.86), higher EDSS (β=1.40) and cord lesion number (β=0.87) independently predicted SPMS conversion (C-index=0.91). Predictors of reaching EDSS=3.0 after 5 years were higher baseline EDSS (β=1.49), cord lesion number (β=1.02) and lower normalised cortical volume (β=-0.56) (C-index=0.88). Baseline age (β=0.30), higher EDSS (β=2.03), higher cord lesion number (β=0.66) and lower cord area (β=-0.41) predicted EDSS=4.0 (C-index=0.92). Finally, higher baseline EDSS (β=1.87) and cord lesion number (β=0.54) predicted EDSS=6.0 (C-index=0.91).

CONCLUSIONS

Spinal cord damage and, to a lesser extent, cortical volume loss helped predicting worse 5-year clinical outcomes in MS.

Potential biological contributers to the sex difference in multiple sclerosis progression

Multiple sclerosis (MS) is an immune-mediated disease that targets the myelin sheath of central nervous system (CNS) neurons leading to axon injury, neuronal death, and neurological progression. Though women are more highly susceptible to developing MS, men that develop this disease exhibit greater cognitive impairment and accumulate disability more rapidly than women. Magnetic resonance imaging and pathology studies have revealed that the greater neurological progression seen in males correlates with chronic immune activation and increased iron accumulation at the rims of chronic white matter lesions as well as more intensive whole brain and grey matter atrophy and axon loss. Studies in humans and in animal models of MS suggest that male aged microglia do not have a higher propensity for inflammation, but may become more re-active at the rim of white matter lesions as a result of the presence of pro-inflammatory T cells, greater astrocyte activation or iron release from oligodendrocytes in the males. There is also evidence that remyelination is more efficient in aged female than aged male rodents and that male neurons are more susceptible to oxidative and nitrosative stress. Both sex chromosome complement and sex hormones contribute to these sex differences in biology.

Objective perimetry and progression of multiple sclerosis

Introduction

We re-examined the per-region response amplitudes and delays obtained from multifocal pupillographic objective perimetry (mfPOP) after 10 years in 44 persons living with multiple sclerosis (PwMS), both to examine which parts of the visual field had progressed in terms of response properties and to examine if the baseline data could predict the overall progression of disease.

Methods

Expanded Disability Status Scale (EDSS) scores were assessed in 2009 and 2019. Both eyes of each participant were concurrently tested at 44 locations/eye on both occasions. Several measures of clinical progression were examined, using logistic regression to determine the odds of progression.

Results

At the second examination the 44 PwMS (31 females) were aged 61.0 ± 12.2 y. Mean EDSS had not changed significantly (3.69 ± 1.23 in 2009, 3.81 ± 2.00 in 2019). mfPOP delay increased progressively from inferior to superior regions of the visual fields while amplitudes demonstrated a temporal to nasal gradient. The mean of the 3 most delayed visual field regions was correlated with progression of MS by 2019 (p = 0.023). Logistic regression indicated a significant association between delay and odds of progression (p = 0.045): an individual with 3 regions at least 1 SD (40 ms) slower than the mean in 2009 had 2.05× (±SE: 1.43× to 2.95×) the odds of progression by 2019. A 1 SD shorter delay was associated with 2.05× lower odds of progression. Amplitude changes were not predictive of progression.

Significance

mfPOP may provide a rapid, convenient method of monitoring and predicting MS progression.

Information processing speed as a prognostic marker of physical impairment and progression in patients with multiple sclerosis

BACKGROUND

Prediction of disability progression in patients with MS (pwMS) is challenging. So far, scarce evidence exists suggesting knowledge about how cognitive performance may potentially improve prediction of physical impairment and disability progression in MS. Therefore, we wanted to assess the prognostic value of cognitive performance regarding physical impairment and disability progression in pwMS.

METHODS

85 patients (64% female; 60% relapse-remitting MS; mean age=36.78 ± 9.63 years) underwent clinical, neuropsychological (Brief Repeatable Battery for Neuropsychological Test (BRB-N)) and brain MRI (T1-weighted and T2-weighted FLAIR images) assessment at baseline and after an average of 7 years (SD=3.75) at follow-up. We assessed physical impairment and annualized disability progression (disability progression divided by follow-up duration) using the Expanded Disability Status Scale (EDSS). To compare patients with no or mild physical impairment (EDSS≤2.5) and patients with moderate to severe physical impairment (EDSS≥3.0), we used an EDSS score ≥3.0 as cut-off. Silent progression was defined by an EDSS worsening of at least 0.5 in the absence of relapses and inflammation in relapsing-remitting MS.

RESULTS

In hierarchical regression models (method "STEPWISE", forward) performance in information processing speed was a significant and independent predictor of physical impairment (EDSS≥3.0) at follow-up (model R²=0.671, b=-1.46, OR=0.23, p=0.001) and annualized disability progression (adjusted model R²=0.257, β=-0.26, 95% CI: -0.066, -0.008, p=0.012), in addition to demographics (age, education, individual follow-up time), clinical (EDSS, disease duration, clinical phenotype, annualized-relapse-rate) and MRI measures (brain volumes and T2-lesion load). In a MANCOVA controlled for age, disease duration and individual follow-up time, worse baseline performance in information processing speed was found in patients with higher EDSS at follow-up (m=-1.91, SD=1.18, p<0.001) and silent progression (m=-2.19, SD=1.01, p=0.038).

CONCLUSION

Performance in information processing speed might help to identify patients at risk for physical impairment. Therefore, neuropsychological assessment should be integrated in clinical standard care to support disease management in pwMS.

Myelin imaging measures as predictors of cognitive impairment in MS patients: A hybrid PET-MRI study

BACKGROUND

Cognitive impairment is one of the concerns of Multiple Sclerosis (MS) and has been related to myelin loss. Different neuroimaging methods have been used to quantify myelin and relate it to cognitive dysfunctions, among them Magnetization Transfer Ratio (MTR), Diffusion Tensor Imaging (DTI), and, more recently, Positron Emission Tomography (PET) with ¹¹C-PIB.

OBJECTIVE

To investigate different myelin imaging modalities as predictors of cognitive dysfunction.

METHODS

Fifty-one MS patients and 24 healthy controls underwent clinical and neuropsychological assessment and MTR, DTI (Axial Diffusion-AD and Fractional Anisotropy-FA maps), and ¹¹C-PIB PET images in a PET/MR hybrid system.

RESULTS

MTR and DTI(FA) differed in patients with or without cognitive impairment. There was an association of DTI(FA) and DTI(AD) with cognition and psychomotor speed for progressive MS, and of ¹¹C-PIB uptake and MTR for relapsing-remitting MS. MTR in the Thalamus (β= -0.51, p = 0.021) and Corpus Callosum (β= -0.24, p = 0.033) were predictive of cognitive impairment. DTI-FA in the Caudate (β= -26.93, p = 0.006) presented abnormal predictive result.

CONCLUSION

Lower myelin content by ¹¹C-PIB uptake was associated with worse cognitive status. MTR was predictive of cognitive impairment in MS.

Towards Multimodal Machine Learning Prediction of Individual Cognitive Evolution in Multiple Sclerosis

Multiple sclerosis (MS) manifests heterogeneously among persons suffering from it, making its disease course highly challenging to predict. At present, prognosis mostly relies on biomarkers that are unable to predict disease course on an individual level. Machine learning is a promising technique, both in terms of its ability to combine multimodal data and through the capability of making personalized predictions. However, most investigations on machine learning for prognosis in MS were geared towards predicting physical deterioration, while cognitive deterioration, although prevalent and burdensome, remained largely overlooked. This review aims to boost the field of machine learning for cognitive prognosis in MS by means of an introduction to machine learning and its pitfalls, an overview of important elements for study design, and an overview of the current literature on cognitive prognosis in MS using machine learning. Furthermore, the review discusses new trends in the field of machine learning that might be adopted for future studies in the field.

Design and Validation of an Expanded Disability Status Scale Model in Multiple Sclerosis

INTRODUCTION

We aimed to develop and validate an Expanded Disability Status Scale (EDSS) model through clinical, optical coherence tomography (OCT), and magnetic resonance imaging (MRI) measures.

METHODS

Sixty-four multiple sclerosis (MS) patients underwent peripapillary retinal nerve fiber layer and segmented macular layers evaluation through OCT (Spectralis, Heidelberg Engineering). Brain parenchymal fraction was quantified through Freesurfer, while cervical spinal cord (SC) volume was assessed manually guided by Spinal Cord Toolbox software analysis. EDSS, neuroradiological, and OCT assessment were carried out within 3 months. OCT parameters were calculated as the average of both nonoptic neuritis (ON) eyes, and in case the patient had previous ON, the value of the fellow non-ON eye was taken. Brain lesion volume, sex, age, disease duration, and history of disease-modifying treatment (1st or 2nd line disease-modifying treatments) were tested as covariables of the EDSS score.

RESULTS

EDSS values correlated with patient's age (r = 0.543, p = 0.001), SC volume (r = -0.301, p = 0.034), and ganglion cell layer (GCL, r = -0.354, p = 0.012). Using these correlations, an ordinal regression model to express probability of diverse EDSS scores were designed, the highest of which was the most probable (Nagelkerke R2 = 43.3%). Using EDSS cutoff point of 4.0 in a dichotomous model, compared to a cutoff of 2.0, permits the inclusion of GCL as a disability predictor, in addition to age and SC.

CONCLUSIONS

MS disability measured through EDSS is an age-dependent magnitude that is partly conditioned by SC and GCL. Further studies assessing paraclinical disability predictors are needed.

Machine Learning for Predicting Motor Improvement After Acute Subcortical Infarction Using Baseline Whole Brain Volumes

Background. Neuroimaging biomarkers are valuable predictors of motor improvement after stroke, but there is a gap between published evidence and clinical usage. Objective. In this work, we aimed to investigate whether machine learning techniques, when applied to a combination of baseline whole brain volumes and clinical data, can accurately predict individual motor outcome after stroke. Methods. Upper extremity Fugl-Meyer Assessments (FMA-UE) were conducted 1 week and 12 weeks, and structural MRI was performed 1 week, after onset in 56 patients with subcortical infarction. Proportional recovery model residuals were employed to assign patients to proportional and poor recovery groups (34 vs 22). A sophisticated machine learning scheme, consisting of conditional infomax feature extraction, synthetic minority over-sampling technique for nominal and continuous, and bagging classification, was employed to predict motor outcomes, with the input features being a combination of baseline whole brain volumes and clinical data (FMA-UE scores). Results. The proposed machine learning scheme yielded an overall balanced accuracy of 87.71% in predicting proportional vs poor recovery outcomes, a sensitivity of 93.77% in correctly identifying poor recovery outcomes, and a ROC AUC of 89.74%. Compared with only using clinical data, adding whole brain volumes can significantly improve the classification performance, especially in terms of the overall balanced accuracy (from 80.88% to 87.71%) and the sensitivity (from 92.23% to 93.77%). Conclusions. Experimental results suggest that a combination of baseline whole brain volumes and clinical data, when equipped with appropriate machine learning techniques, may provide valuable information for personalized rehabilitation planning after subcortical infarction.

Predicting disability progression and cognitive worsening in multiple sclerosis using patterns of grey matter volumes

OBJECTIVE

In multiple sclerosis (MS), MRI measures at the whole brain or regional level are only modestly associated with disability, while network-based measures are emerging as promising prognostic markers. We sought to demonstrate whether data-driven patterns of covarying regional grey matter (GM) volumes predict future disability in secondary progressive MS (SPMS).

METHODS

We used cross-sectional structural MRI, and baseline and longitudinal data of Expanded Disability Status Scale, Nine-Hole Peg Test (9HPT) and Symbol Digit Modalities Test (SDMT), from a clinical trial in 988 people with SPMS. We processed T1-weighted scans to obtain GM probability maps and applied spatial independent component analysis (ICA). We repeated ICA on 400 healthy controls. We used survival models to determine whether baseline patterns of covarying GM volume measures predict cognitive and motor worsening.

RESULTS

We identified 15 patterns of regionally covarying GM features. Compared with whole brain GM, deep GM and lesion volumes, some ICA components correlated more closely with clinical outcomes. A mainly basal ganglia component had the highest correlations at baseline with the SDMT and was associated with cognitive worsening (HR=1.29, 95% CI 1.09 to 1.52, p<0.005). Two ICA components were associated with 9HPT worsening (HR=1.30, 95% CI 1.06 to 1.60, p<0.01 and HR=1.21, 95% CI 1.01 to 1.45, p<0.05). ICA measures could better predict SDMT and 9HPT worsening (C-index=0.69-0.71) compared with models including only whole and regional MRI measures (C-index=0.65-0.69, p value for all comparison <0.05).

CONCLUSIONS

The disability progression was better predicted by some of the covarying GM regions patterns, than by single regional or whole-brain measures. ICA, which may represent structural brain networks, can be applied to clinical trials and may play a role in stratifying participants who have the most potential to show a treatment effect.

Spectral-Domain Optical Coherence Tomography Assessment in Treatment-Naïve Patients with Clinically Isolated Syndrome and Different Multiple Sclerosis Types: Findings and Relationship with the Disability Status

This study evaluates the peripapillary retinal nerve fiber layer (pRNFL) thickness and total macular volume (TMV) using spectral-domain optical coherence tomography in treatment naïve patients with the clinically isolated syndrome (CIS) and different multiple sclerosis (MS) types. A total of 126 patients (15 CIS, 65 relapsing-remitting MS, 14 secondary progressive MS, 11 primary progressive MS, 21 benign MS) with or without optic neuritis (ON) history and 63 healthy age-similar controls were assessed. Concerning controls' eyes, pRNFL thickness was significantly reduced in CIS-ON eyes (p < 0.01), while both TMV and pRNFL thickness was decreased in all MS eyes regardless of ON history (p < 0.01). Significant differences in pRNFL thickness and TMV between MS variants were observed for non-ON eyes (p < 0.01), with the lowest values in benign and secondary progressive disease type, respectively. The pRNFL thickness was inversely correlated with Expanded Disability Status Scale (EDSS) score in non-ON subgroups (p < 0.01), whereas TMV was inversely correlated with EDSS score in both ON and non-ON subgroups (p < 0.01). Concluding, pRNFL thinning confirms optic nerve damage in CIS-ON eyes and appears to be disproportionately high with respect to the disability status of benign MS patients. The values of TMV and pRNFL in non-ON eyes significantly correspond to MS course heterogeneity and patients' disability than in ON eyes.

Quantifying disease pathology and predicting disease progression in multiple sclerosis with only clinical routine T2-FLAIR MRI

•

We explored five brain pathology measures from clinical-quality T2-FLAIR MRI in MS.

•

These included LVV, thalamus volume, MOV, SCLV and network efficiency.

•

T2-FLAIR measures predicted a majority of the variance in research-quality MRI.

•

T2-FLAIR measures correlated with neurologic disability and cognitive function.

•

T2-FLAIR measures predicted disability progression over five-years.

•

T2-FLAIR measures can be used in legacy clinical datasets.

Background

Although quantitative measures from research-quality MRI provide a means to study multiple sclerosis (MS) pathology in vivo, these metrics are often unavailable in legacy clinical datasets.

Objective

To determine how well an automatically-generated quantitative snapshot of brain pathology, measured only on clinical routine T2-FLAIR MRI, can substitute for more conventional measures on research MRI in terms of capturing multi-factorial disease pathology and providing similar clinical relevance.

Methods

MRI with both research-quality sequences and conventional clinical T2-FLAIR was acquired for 172 MS patients at baseline, and neurologic disability was assessed at baseline and five-years later. Five measures (thalamus volume, lateral ventricle volume, medulla oblongata volume, lesion volume, and network efficiency) for quantifying disparate aspects of neuropathology from low-resolution T2-FLAIR were applied to predict standard research-quality MRI measures. They were compared in regard to association with future neurologic disability and disease progression over five years.

Results

The combination of the five T2-FLAIR measures explained most of the variance in standard research-quality MRI. T2-FLAIR measures were associated with neurologic disability and cognitive function five-years later (R² = 0.279, p < 0.001; R² = 0.382, p < 0.001), similar to standard research-quality MRI (R² = 0.279, p < 0.001; R² = 0.366, p < 0.001). They also similarly predicted disability progression over five years (%-correctly-classified = 69.8, p = 0.034), compared to standard research-quality MRI (%-correctly-classified = 72.4%, p = 0.022) in relapsing-remitting MS.

Conclusion

A set of five T2-FLAIR-only measures can substitute for standard research-quality MRI, especially in relapsing-remitting MS. When only clinical T2-FLAIR is available, it can be used to obtain substantially more quantitative information about brain pathology and disability than is currently standard practice.

Network Damage Predicts Clinical Worsening in Multiple Sclerosis: A 6.4-Year Study

OBJECTIVE

In multiple sclerosis (MS), clinical impairment is likely due to both structural damage and abnormal brain function. We assessed the added value of integrating structural and functional network MRI measures to predict 6.4-year MS clinical disability deterioration.

METHODS

Baseline 3D T1-weighted and resting-state functional MRI scans were obtained from 233 patients with MS and 77 healthy controls. Patients underwent a neurologic evaluation at baseline and at 6.4-year median follow-up (interquartile range = 5.06-7.51 years). At follow-up, patients were classified as clinically stable/worsened according to disability changes. In relapsing-remitting (RR) MS, secondary progressive (SP) MS conversion was evaluated. Global brain volumetry was obtained. Furthermore, independent component analysis identified the main functional connectivity (FC) and gray matter (GM) network patterns.

RESULTS

At follow-up, 105/233 (45%) patients were clinically worsened; 26/157 (16%) patients with RRMS evolved to SPMS. The treatment-adjusted random forest model identified normalized GM and brain volumes, decreased FC between default-mode networks, increased FC of the left precentral gyrus in the sensorimotor network (SMN), and GM atrophy in the fronto-parietal network (false discovery rate [FDR]-corrected p = range 0.01-0.09) as predictors of clinical worsening (out-of-bag [OOB] accuracy = 0.74). An expected contribution of baseline disability was also present (FDR-p = 0.01). Baseline disability, normalized GM volume, and GM atrophy in the SMN (FDR-p = range 0.01-0.09) were independently associated with SPMS conversion (OOB accuracy = 0.84). At receiver operating characteristic analysis, including network MRI variables improved disability worsening (p = 0.05) and SPMS conversion (p = 0.02) prediction.

CONCLUSIONS

Integration of MRI network measures helped determining the relative contributions of global/local GM damage and functional reorganization to clinical deterioration in MS.

Deciphering Multiple Sclerosis Progression

Multiple sclerosis (MS) is primarily an inflammatory and degenerative disease of the central nervous system, triggered by unknown environmental factors in patients with predisposing genetic risk profiles. The prevention of neurological disability is one of the essential goals to be achieved in a patient with MS. However, the pathogenic mechanisms driving the progressive phase of the disease remain unknown. It was described that the pathophysiological mechanisms associated with disease progression are present from disease onset. In daily practice, there is a lack of clinical, radiological, or biological markers that favor an early detection of the disease's progression. Different definitions of disability progression were used in clinical trials. According to the most descriptive, progression was defined as a minimum increase in the Expanded Disability Status Scale (EDSS) of 1.5, 1.0, or 0.5 from a baseline level of 0, 1.0–5.0, and 5.5, respectively. Nevertheless, the EDSS is not the most sensitive scale to assess progression, and there is no consensus regarding any specific diagnostic criteria for disability progression. This review document discusses the current pathophysiological concepts associated with MS progression, the different measurement strategies, the biomarkers associated with disability progression, and the available pharmacologic therapeutic approaches.

Short-term data on disease activity, cognition, mood, stigma and employment outcomes in a cohort of patients with primary progressive multiple sclerosis (UPPMS study)

BACKGROUND

Primary progressive multiple sclerosis (PPMS) has long been defined by progressive disability accrual in the absence of initial relapses. However, its underlying neurodegenerative process seems to be accompanied by central nervous system inflammation. A new classification defined multiple sclerosis courses according to clinical/radiological activity and progression. We provide further insight into PPMS activity according to this classification and other daily living aspects.

METHODS

This was a multicentre, prospective, cohort study including 55 adult patients with PPMS according to 2010 McDonald criteria, within ten years from neurologic symptom onset and not receiving disease-modifying therapies during the past six months, who were followed up for 12 months. The primary study endpoint was the percentage of patients with active disease based on clinical relapses and/or magnetic resonance activity. Disability progression, cognitive function, physical/psychological impact, depression symptoms, stigma and employment were secondary endpoints.

RESULTS

Eleven (25.6%) patients exhibited multiple sclerosis activity throughout the 12-month study follow-up. Fourteen showed non-active multiple sclerosis without progression, 11 non-active multiple sclerosis with progression, 6 active multiple sclerosis without progression and 4 active multiple sclerosis with progression; one patient with disease activity was not assessable for progression. Cognitive function scores remained unchanged or increased, disease physical impact was maintained and disease psychological impact significantly decreased. The proportion of patients with depression symptoms or stigma remained without significant changes as well as employment outcomes.

CONCLUSION

This study shows that one-fourth of PPMS patients may exhibit disease activity over one year, with disability progression in approximately one-third but without worsening of cognitive function, disease impact, depression, stigma or employment outcomes.

Histopathology-validated recommendations for cortical lesion imaging in multiple sclerosis

Cortical demyelinating lesions are clinically important in multiple sclerosis, but notoriously difficult to visualize with MRI. At clinical field strengths, double inversion recovery MRI is most sensitive, but still only detects 18% of all histopathologically validated cortical lesions. More recently, phase-sensitive inversion recovery was suggested to have a higher sensitivity than double inversion recovery, although this claim was not histopathologically validated. Therefore, this retrospective study aimed to provide clarity on this matter by identifying which MRI sequence best detects histopathologically-validated cortical lesions at clinical field strength, by comparing sensitivity and specificity of the thus far most commonly used MRI sequences, which are T₂, fluid-attenuated inversion recovery (FLAIR), double inversion recovery and phase-sensitive inversion recovery. Post-mortem MRI was performed on non-fixed coronal hemispheric brain slices of 23 patients with progressive multiple sclerosis directly after autopsy, at 3 T, using T₁ and proton-density/T₂-weighted, as well as FLAIR, double inversion recovery and phase-sensitive inversion recovery sequences. A total of 93 cortical tissue blocks were sampled from these slices. Blinded to histopathology, all MRI sequences were consensus scored for cortical lesions. Subsequently, tissue samples were stained for proteolipid protein (myelin) and scored for cortical lesion types I–IV (mixed grey matter/white matter, intracortical, subpial and cortex-spanning lesions, respectively). MRI scores were compared to histopathological scores to calculate sensitivity and specificity per sequence. Next, a retrospective (unblinded) scoring was performed to explore maximum scoring potential per sequence. Histopathologically, 224 cortical lesions were detected, of which the majority were subpial. In a mixed model, sensitivity of T₁, proton-density/T₂, FLAIR, double inversion recovery and phase-sensitive inversion recovery was 8.9%, 5.4%, 5.4%, 22.8% and 23.7%, respectively (20, 12, 12, 51 and 53 cortical lesions). Specificity of the prospective scoring was 80.0%, 75.0%, 80.0%, 91.1% and 88.3%. Sensitivity and specificity did not significantly differ between double inversion recovery and phase-sensitive inversion recovery, while phase-sensitive inversion recovery identified more lesions than double inversion recovery upon retrospective analysis (126 versus 95; P < 0.001). We conclude that, at 3 T, double inversion recovery and phase-sensitive inversion recovery sequences outperform conventional sequences T₁, proton-density/T₂ and FLAIR. While their overall sensitivity does not exceed 25%, double inversion recovery and phase-sensitive inversion recovery are highly pathologically specific when using existing scoring criteria and their use is recommended for optimal cortical lesion assessment in multiple sclerosis.

Deep Learning Corpus Callosum Segmentation as a Neurodegenerative Marker in Multiple Sclerosis

BACKGROUND AND PURPOSE

Corpus callosum atrophy is a sensitive biomarker of multiple sclerosis (MS) neurodegeneration but typically requires manual 2D or volumetric 3D-based segmentations. We developed a supervised machine learning algorithm, DeepnCCA, for corpus callosum segmentation and relate callosal morphology to clinical disability using conventional MRI scans collected in clinical routine.

METHODS

In a prospective study of 553 MS patients with 704 acquisitions, 200 unique 2D T₂ -weighted MRI scans were delineated to develop, train, and validate DeepnCCA. Comparative FreeSurfer segmentations were obtained in 504 3D T₁ -weighted scans. Both FreeSurfer and DeepnCCA outputs were correlated with clinical disability. Using principal component analysis of the DeepnCCA output, the morphological changes were explored in relation to clinical disease burden.

RESULTS

DeepnCCA and manual segmentations had high similarity (Dice coefficients 98.1 ± .11%, 89.3 ± .76%, for intracranial and corpus callosum area, respectively through 10-fold cross-validation). DeepnCCA had numerically stronger correlations with cognitive and physical disability as compared to FreeSurfer: Expanded disability status scale (EDSS) ±6 months (r = -.22 P = .002; r = -.17, P = .013), future EDSS (r = -.26, P<.001; r = -.17, P = .012), and future symbol digit modalities test (r = .26, P = .001; r = .24, P = .003). The corpus callosum became thinner with increasing cognitive and physical disability. Increasing physical disability, additionally, significantly correlated with a more angled corpus callosum.

CONCLUSIONS

DeepnCCA (https://github.com/plattenmichael/DeepnCCA/) is an openly available tool that can provide fast and accurate corpus callosum measurements applicable to large MS cohorts, potentially suitable for monitoring disease progression and therapy response.

Identifying Early Neuropsychological Indicators of Cognitive Involvement in Multiple Sclerosis

Multiple sclerosis (MS) is a debilitating disease of the central nervous system that is most commonly seen in early to middle adulthood, although it can be diagnosed during childhood or later in life. While cognitive impairment can become more prevalent and severe as the disease progresses, signs of cognitive involvement can be apparent in the early stages of the disease. In this review, we discuss the prevalence and types of cognitive impairment seen in early MS, including the specific measures used to identify them, as well as the challenges in characterizing their frequency and progression. In addition to examining the progression of early cognitive involvement over time, we explore the clinical factors associated with early cognitive involvement, including demographics, level of physical disability, disease modifying therapy use, vocational status, and psychological and physical symptoms. Given the prevalence and functional impact these impairments can have for persons with MS, considerations for clinicians are provided, such as the role of early cognitive screenings and the importance of comprehensive neuropsychological assessments.

Long-term course and morphological MRI correlates of cognitive function in multiple sclerosis

BACKGROUND

Cognitive impairment frequently occurs in patients with MS (pwMS). Magnetic resonance imaging (MRI) markers could help to identify patients at risk for decline.

OBJECTIVE

To characterize the long-term course and morphological MRI correlates of cognitive function in pwMS.

METHODS

We invited 116 pwMS who had undergone clinical, cognitive, and MRI evaluations between 2006 and 2012 (baseline, BL) to attend follow-up (FU) testing between 2016 and 2018. Disability (expanded disability status scale (EDSS)), cognition (brief repeatable battery of neuropsychological test (BRB-N)), global and regional T2-lesion load (T2-LL), brain volumes, and cortical thickness were assessed.

RESULTS

Sixty-three pwMS were willing to attend the FU (54%; median EDSS = 2, interquartile range (IQR) = 2) and did not differ from non-participating pwMS regarding BL characteristics. At BL, half of the participants showed cognitive deficits in at least one domain. Across the entire group, we observed no relevant changes in physical disability and cognition over 10 years. BL thalamic volume best predicted cognitive function at FU, in addition to age and BL cognition, explaining 67% of variance. Cognitive decliners (23.8%) were older, had longer disease duration, and a tendency for lower thalamic volume at BL.

CONCLUSION

Thalamic volume predicted FU cognitive function and distinguished declining from stable pwMS, underlining the potential of MRI to define risk groups.

Knowledge Is Power, but Is Ignorance Bliss? Optimising Conversations About Disease Progression in Multiple Sclerosis

Communication about multiple sclerosis (MS) disease progression between healthcare professionals (HCPs) and people with MS (PwMS) has historically been considered difficult, and attention to improving it has been neglected. However, a growing number of studies have shown that this is a key area to get right, since negative experiences can affect patient satisfaction, treatment adherence, and clinical outcomes. This article reports on a symposium at the European Charcot Foundation, 2018, led by a panel of leading clinicians and patient experts from MS in the 21st Century, who debated the benefits, drawbacks, and challenges of communicating about disease progression, for both HCPs and PwMS, and potential ways to optimise these discussions. PwMS' preferences and priorities regarding conversations about disease progression vary widely. While the majority want to have these conversations, some will be reluctant and/or emotionally unready. Communication therefore needs to be personalised, and HCPs should always be prepared to have such conversations in an appropriate and sensitive manner. Clinical information can be opaque for PwMS, so HCPs also need to use language that is clear, easily understandable, and patient-friendly. MS in the 21st Century is in the process of developing several resources and programmes to help improve disease progression communication between HCPs and PwMS. FUNDING: Merck KGaA, Darmstadt, Germany. Plain language summary available for this article.

Systematic review of prediction models in relapsing remitting multiple sclerosis

The natural history of relapsing remitting multiple sclerosis (RRMS) is variable and prediction of individual prognosis challenging. The inability to reliably predict prognosis at diagnosis has important implications for informed decision making especially in relation to disease modifying therapies. We conducted a systematic review in order to collate, describe and assess the methodological quality of published prediction models in RRMS. We searched Medline, Embase and Web of Science. Two reviewers independently screened abstracts and full text for eligibility and assessed risk of bias. Studies reporting development or validation of prediction models for RRMS in adults were included. Data collection was guided by the checklist for critical appraisal and data extraction for systematic reviews (CHARMS) and applicability and methodological quality assessment by the prediction model risk of bias assessment tool (PROBAST). 30 studies were included in the review. Applicability was assessed as high risk of concern in 27 studies. Risk of bias was assessed as high for all studies. The single most frequently included predictor was baseline EDSS (n = 11). T2 Lesion volume or number and brain atrophy were each retained in seven studies. Five studies included external validation and none included impact analysis. Although a number of prediction models for RRMS have been reported, most are at high risk of bias and lack external validation and impact analysis, restricting their application to routine clinical practice.

MRI biomarkers of disease progression and conversion to secondary-progressive multiple sclerosis

INTRODUCTION

Conventional imaging measures remain a key clinical tool for the diagnosis multiple sclerosis (MS) and monitoring of patients. However, most measures used in the clinic show unsatisfactory performance in predicting disease progression and conversion to secondary progressive MS.

AREAS COVERED

Sophisticated imaging techniques have facilitated the identification of imaging biomarkers associated with disease progression, such as global and regional brain volume measures, and with conversion to secondary progressive MS, such as leptomeningeal contrast enhancement and chronic inflammation. The relevance of emerging imaging approaches partially overcoming intrinsic limitations of traditional techniques is also discussed.

EXPERT OPINION

Imaging biomarkers capable of detecting tissue damage early on in the disease, with the potential to be applied in multicenter trials and at an individual level in clinical settings, are strongly needed. Several measures have been proposed, which exploit advanced imaging acquisitions and/or incorporate sophisticated post-processing, can quantify irreversible tissue damage. The progressively wider use of high-strength field MRI and the development of more advanced imaging techniques will help capture the missing pieces of the MS puzzle. The ability to more reliably identify those at risk for disability progression will allow for earlier intervention with the aim to favorably alter the disease course.

Conversion of diffusely abnormal white matter to focal lesions is linked to progression in secondary progressive multiple sclerosis

Background:

Diffusely abnormal white matter (DAWM) regions are observed in magnetic resonance images of secondary progressive multiple sclerosis (SPMS) patients. However, their role in clinical progression is still not established.

Objectives:

To characterize the longitudinal volumetric and intensity evolution of DAWM and focal white matter lesions (FWML) and assess their associations with clinical outcomes and progression in SPMS.

Methods:

Data include 589 SPMS participants followed up for 3 years (3951 time points). FWML and DAWM were automatically segmented. Screening DAWM volumes that transformed into FWML at the last visit (DAWM-to-FWML) and normalized T1-weighted intensities (indicating severity of damage) in those voxels were calculated.

Results:

FWML volume increased and DAWM volume decreased with an increase in disease duration ( p < 0.001). The Expanded Disability Status Scale (EDSS) was positively associated with FWML volumes ( p = 0.002), but not with DAWM. DAWM-to-FWML volume was higher in patients who progressed (2.75 cm3 vs. 1.70 cm3; p < 0.0001). Normalized T1-weighted intensity of DAWM-to-FWML was negatively associated with progression ( p < 0.00001).

Conclusion:

DAWM transformed into FWML over time, and this transformation was associated with clinical progression. DAWM-to-FWML voxels had greater normalized T1-weighted intensity decrease over time, in keeping with relatively greater tissue damage. Evaluation of DAWM in progressive multiple sclerosis provides a useful measure for therapies aiming to protect this at-risk tissue with the potential to slow progression.

MRI-Based Manual versus Automated Corpus Callosum Volumetric Measurements in Multiple Sclerosis

BACKGROUND AND PURPOSE

Corpus callosum atrophy is a neurodegenerative biomarker in multiple sclerosis (MS). Manual delineations are gold standard but subjective and labor intensive. Novel automated methods are promising but require validation. We aimed to compare the robustness of manual versus automatic corpus callosum segmentations based on FreeSurfer.

METHODS

Nine MS patients (6 females, age 38 ± 13 years, disease duration 7.3 ± 5.2 years) were scanned twice with repositioning using 3-dimensional T₁ -weighted magnetic resonance imaging on three scanners (two 1.5 T and one 3.0 T), that is, six scans/patient, on the same day. Normalized corpus callosum areas were measured independently by a junior doctor and neuroradiologist. The cross-sectional and longitudinal streams of FreeSurfer were used to segment the corpus callosum volume.

RESULTS

Manual measurements had high intrarater (junior doctor .96 and neuroradiologist .96) and interrater agreement (.94), by intraclass correlation coefficient (P < .001). The coefficient of variation was lowest for longitudinal FreeSurfer (.96% within scanners; 2.0% between scanners) compared to cross-sectional FreeSurfer (3.7%, P = .001; 3.8%, P = .058) and the neuroradiologist (2.3%, P = .005; 2.4%, P = .33). Longitudinal FreeSurfer was also more accurate than cross-sectional (Dice scores 83.9 ± 7.5% vs. 78.9 ± 8.4%, P < .01 relative to manual segmentations). The corpus callosum measures correlated with physical disability (longitudinal FreeSurfer r = -.36, P < .01; neuroradiologist r = -.32, P < .01) and cognitive disability (longitudinal FreeSurfer r = .68, P < .001; neuroradiologist r = .64, P < .001).

CONCLUSIONS

FreeSurfer's longitudinal stream provides corpus callosum measures with better repeatability than current manual methods and with similar clinical correlations. However, due to some limitations in accuracy, caution is warranted when using FreeSurfer with clinical data.

Advances in brain imaging in multiple sclerosis

Brain imaging is increasingly used to support clinicians in diagnosing multiple sclerosis (MS) and monitoring its progression. However, the role of magnetic resonance imaging (MRI) in MS goes far beyond its clinical application. Indeed, advanced imaging techniques have helped to detect different components of MS pathogenesis in vivo, which is now considered a heterogeneous process characterized by widespread damage of the central nervous system, rather than multifocal demyelination of white matter. Recently, MRI biomarkers more sensitive to disease activity than clinical disability outcome measures, have been used to monitor response to anti-inflammatory agents in patients with relapsing-remitting MS. Similarly, MRI markers of neurodegeneration exhibit the potential as primary and secondary outcomes in clinical trials for progressive phenotypes. This review will summarize recent advances in brain neuroimaging in MS from the research setting to clinical applications.