Functional clinical outcomes in multiple sclerosis: Current status and future prospects

The role of machine learning in developing non-magnetic resonance imaging based biomarkers for multiple sclerosis: a systematic review

Background

Multiple sclerosis (MS) is a neurological condition whose symptoms, severity, and progression over time vary enormously among individuals. Ideally, each person living with MS should be provided with an accurate prognosis at the time of diagnosis, precision in initial and subsequent treatment decisions, and improved timeliness in detecting the need to reassess treatment regimens. To manage these three components, discovering an accurate, objective measure of overall disease severity is essential. Machine learning (ML) algorithms can contribute to finding such a clinically useful biomarker of MS through their ability to search and analyze datasets about potential biomarkers at scale. Our aim was to conduct a systematic review to determine how, and in what way, ML has been applied to the study of MS biomarkers on data from sources other than magnetic resonance imaging.

Methods

Systematic searches through eight databases were conducted for literature published in 2014–2020 on MS and specified ML algorithms.

Results

Of the 1, 052 returned papers, 66 met the inclusion criteria. All included papers addressed developing classifiers for MS identification or measuring its progression, typically, using hold-out evaluation on subsets of fewer than 200 participants with MS. These classifiers focused on biomarkers of MS, ranging from those derived from omics and phenotypical data (34.5% clinical, 33.3% biological, 23.0% physiological, and 9.2% drug response). Algorithmic choices were dependent on both the amount of data available for supervised ML (91.5%; 49.2% classification and 42.3% regression) and the requirement to be able to justify the resulting decision-making principles in healthcare settings. Therefore, algorithms based on decision trees and support vector machines were commonly used, and the maximum average performance of 89.9% AUC was found in random forests comparing with other ML algorithms.

Conclusions

ML is applicable to determining how candidate biomarkers perform in the assessment of disease severity. However, applying ML research to develop decision aids to help clinicians optimize treatment strategies and analyze treatment responses in individual patients calls for creating appropriate data resources and shared experimental protocols. They should target proceeding from segregated classification of signals or natural language to both holistic analyses across data modalities and clinically-meaningful differentiation of disease.

Immunotherapy for people with clinically isolated syndrome or relapsing-remitting multiple sclerosis: treatment response by demographic, clinical, and biomarker subgroups (PROMISE)-a systematic review protocol

BACKGROUND

Multiple sclerosis (MS) is an inflammatory and degenerative disease of the central nervous system with an increasing worldwide prevalence. Since 1993, more than 15 disease-modifying immunotherapies (DMTs) have been licenced and have shown moderate efficacy in clinical trials. Based on the heterogeneity of the disease and the partial effectiveness of therapies, a personalised medicine approach would be valuable taking individual prognosis and suitability of a chosen therapy into account to gain the best possible treatment effect. The primary objective of this review is to assess the differential treatment effects of all approved DMTs in subgroups of adults with clinically isolated syndrome or relapsing forms of MS. We will analyse possible treatment effect modifiers (TEM) defined by baseline demographic characteristics (gender, age), and diagnostic (i.e. MRI measures) and clinical (i.e. relapses, disability level) measures of MS disease activity.

METHODS

We will include all published and accessible unpublished primary and secondary analyses of randomised controlled trials (RCTs) with a follow-up of at least 12 months investigating the efficacy of at least one approved DMT, with placebo or other approved DMTs as control intervention(s) in subgroups of trial participants. As the primary outcome, we will address disability as defined by the Expanded Disability Status Scale or multiple sclerosis functional composite scores followed by relapse frequency, quality of life measures, and side effects. MRI data will be analysed as secondary outcomes. MEDLINE, EMBASE, CINAHL, LILACS, CENTRAL and major trial registers will be searched for suitable studies. Titles and abstracts and full texts will be screened by two persons independently using Covidence. The risk of bias will be analysed based on the Cochrane "Risk of Bias 2" tool, and the certainty of evidence will be assessed using GRADE. Treatment effects will be reported as rate ratio or odds ratio. Primary analyses will follow the intention-to-treat principle. Meta-analyses will be carried out using random-effects models.

DISCUSSION

Given that individual patient data from clinical studies are often not available, the review will allow to analyse the evidence on TEM in MS immunotherapy and thus support clinical decision making in individual cases.

SYSTEMATIC REVIEW REGISTRATION

PROSPERO CRD42021279665 .

A higher burden of multiple sclerosis genetic risk confers an earlier onset

BACKGROUND

Age at onset of multiple sclerosis (MS) is an objective, influential predictor of the evolution of MS independent of disease duration.

OBJECTIVES

Determine the influence of MS genetic predisposition on age of onset.

METHODS

We conducted a comprehensive investigation of MS risk variants and age at onset in 3495 non-Latinx white individuals, including for combinations of HLA-DRB1*15:01 alleles and quintiles of an unweighted genetic risk score (GRS) for 198 of 200 autosomal MS risk variants that reside outside the major histocompatibility complex.

RESULTS

The mean age at onset was 32 years, 29% were male, and 46% were HLA-DRB1*15:01 carriers. For those with the greatest genetic risk burden (the highest GRS quintile with two HLA-DRB1*15:01 alleles) were on average 5 years younger at onset (p = 0.002) than those with the lowest genetic risk burden (the lowest GRS quintile with no HLA-DRB1*15:01 alleles). There was a strong inverse relationship between the MS genetic risk burden and age at onset of MS (p < 5 × 10^-8).

CONCLUSION

We demonstrate a significant gradient between elevated MS genetic risk burden and an earlier onset of MS, suggesting that a higher MS genetic risk burden accelerates onset of the disease.

Outcome measures assisting treatment optimization in multiple sclerosis

Objective

To review instruments used to assess disease stability or progression in persons with multiple sclerosis (pwMS) that can guide clinicians in optimizing therapy.

Methods

A non-systematic review of scientific literature was undertaken to explore modalities of monitoring symptoms and the disease evolution of MS.

Results

Multiple outcome measures, or tools, have been developed for use in MS research as well as for the clinical management of pwMS. Beginning with the Expanded Disability Status Scale, introduced in 1983, clinicians and researchers have developed monitoring modalities to assess all aspects of MS and the neurological impairment it causes.

Conclusions

Much progress has been made in recent decades for the management of MS and for the evaluation of disease progression. New technology, such as wearable sensors, will provide new opportunities to better understand changes in function, dexterity, and cognition. Essential work over the decades since EDSS was introduced continues to improve our ability to treat this debilitating disease.

Cognitive impairment in multiple sclerosis: diagnosis and monitoring

INTRODUCTION

Cognitive impairment (CI) has a prevalence of 45-70% in people with multiple sclerosis (MS), producing a negative impact on their quality of life, personal life, and work. Early detection of CI has become an important aspect to be considered for an adequate follow-up, to optimize social adaptation and to implement specific cognitive rehabilitation strategies. The aim of this work is to propose a suitable cognitive evaluation of patients with MS based on available and efficient tools for diagnosis and monitoring purposes well supported by literature review and clinical experience.

METHODS

A multidisciplinary panel of professionals from the field of neurology, neuropsychology, and neuroimaging performed a literature review of the topic of cognitive impairment assessment. This was combined and completed with their clinical experience to produce a set of recommendations.

RESULTS

Some limitations to cognitive evaluation are described: shortage of time and resources during the neurology consultation, scarceness or absence of specialized professionals' availability, importance of tests adaptation, and doubts about its use to define therapeutic efficiency. We recommend a baseline and annual screening evaluation, and we suggest a baseline and periodic neuropsychological assessment. The latter ought to change to a recommendation with the presence of either positive screening test, or subjective to cognitive complaints, screening-test results and patient or family report mismatch, or in specific social/work situations.

CONCLUSIONS

Cognitive evaluation should be performed on all patients diagnosed with MS and throughout follow-up. It is necessary to support the creation of multidisciplinary MS teams to optimize the evaluation and follow-up of MS patients.

Increased Within-Network Functional Connectivity May Predict NEDA Status in Fingolimod-Treated MS Patients

Only a few studies have evaluated the brain functional changes associated with disease-modifying therapies (DMTs) in multiple sclerosis (MS), though none used a composite measure of clinical and MRI outcomes to evaluate DMT-related brain functional connectivity (FC) measures predictive of short-term outcome. Therefore, we investigated the following: (1) baseline FC differences between patients who showed evidence of disease activity after a specific DMT and those who did not; (2) DMT-related effects on FC, and; (3) possible relationships between DMT-related FC changes and changes in performance. We used a previously analyzed dataset of 30 relapsing MS patients who underwent fingolimod treatment for 6 months and applied the “no evidence of disease activity” (NEDA-3) status as a clinical response indicator of treatment efficacy. Resting-state fMRI data were analyzed to obtain within- and between-network FC measures. After therapy, 14 patients achieved NEDA-3 status (hereinafter NEDA), while 16 did not (EDA). The two groups significantly differed at baseline, with the NEDA group having higher within-network FC in the anterior and posterior default mode, auditory, orbitofrontal, and right frontoparietal networks than the EDA. After therapy, NEDA showed significantly reduced within-network FC in the posterior default mode and left frontoparietal networks and increased between-network FC in the posterior default mode/orbitofrontal networks; they also showed PASAT improvement, which was correlated with greater within-network FC decrease in the posterior default mode network and with greater between-network FC increase. No significant longitudinal FC changes were found in the EDA. Taken together, these findings suggest that NEDA status after fingolimod is related to higher within-network FC at baseline and to a consistent functional reorganization after therapy.

Predicting onset of secondary-progressive multiple sclerosis using genetic and non-genetic factors

BACKGROUND

Predicting the transition from relapsing-remitting (RR) to secondary-progressive (SP) multiple sclerosis (MS) from early in the disease course is challenging.

OBJECTIVE

To construct prediction models for SPMS using sociodemographic and self-reported clinical measures that would be available at/near MS onset, with specific considerations for MS genetic risk factors.

METHODS

We conducted a retrospective cross-sectional study based on 1295 white, non-Hispanic individuals. Cox proportional hazard prediction models were generated for three censored SPMS outcomes (ever transitioning, transitioning within 10 years, and transitioning within 20 years) using sociodemographic, comorbid health information, symptomatology, and other measures of early disease activity. HLADRB1*15:01 and HLA-A*02:01, as well as a genetic risk score, were iteratively considered in each model. We also explored the relationships for all 200 MS risk variants located outside the major histocompatibility complex. Nomograms were generated for the final prediction models.

RESULTS

An older age of MS onset and being male predicted a short latency to SPMS, while a longer interval between the first two relapses predicted a much longer latency. Comorbid conditions and onset symptomatology variably predicted the risk for transitioning to SPMS for each censored outcome. The most notable observation was that HLA-A*02:01, which confers decreased risk for MS, also contributed to decreased hazards for SPMS.

CONCLUSIONS

These results have the potential to advance prognostication for a person with MS using information available at or near onset, potentially improving care and quality of life for those who live with MS.

Multiple Sclerosis Performance Test: Technical Development and Usability

Introduction

In the clinic, the assessment of patients with multiple sclerosis (MS) is typically qualitative and non-standardized.

Objectives

To describe the MS Performance Test (MSPT), an iPad Air^® 2 (Apple, Cupertino, CA, USA)-based neurological assessment platform allowing patients to input relevant information without the aid of a medical technician, creating a longitudinal, clinically meaningful, digital medical record. To report results from human factor (HF) and usability studies, and the initial large-scale implementation in a practice setting.

Methods

The HF study examined use-error patterns in small groups of MS patients and healthy controls (n = 14), the usability study assessed the effectiveness of patient interaction with the tool by patients with a range of MS disability (n = 60) in a clinical setting, and the implementation study deployed the MSPT across a diverse population of patients (n = 1000) in a large MS center for routine clinical care.

Results

MSPT assessments were completed by all users in the HF study; minor changes to design were recommended. In the usability study, 73% of patients with MS completed the MSPT, with an average administration time of 32 min; 85% described their experience with the tool as satisfactory. In the initial implementation for routine care, 84% of patients with MS completed the MSPT, with an average administration time of 28 min.

Conclusion

Patients with MS with varying disability levels completed the MSPT with minimal or no supervision, resulting in comprehensive, efficient, standardized, quantitative, clinically meaningful data collection as part of routine medical care, thus allowing for large-scale, real-world evidence generation.

Funding

Biogen.

Trial Registration

NCT02664324.

Electronic supplementary material

The online version of this article (10.1007/s12325-019-00958-x) contains supplementary material, which is available to authorized users.

Functional Connectivity Changes After Initial Treatment With Fingolimod in Multiple Sclerosis

On the basis of recent functional MRI studies, Multiple Sclerosis (MS) has been interpreted as a multisystem disconnection syndrome. Compared to normal subjects, MS patients show alterations in functional connectivity (FC). However, the mechanisms underlying these alterations are still debated. The aim of the study is to investigate resting state (RS) FC changes after initial treatment with fingolimod, a proven anti-inflammatory and immunomodulating agent for MS. We studied 32 right-handed relapsing-remitting MS patients (median Expanded Disability Status Scale: 2.0, mean disease duration: 8.8 years) who underwent both functional and conventional MRI with a 3 Tesla magnet. All assessments were performed 3 weeks before starting fingolimod, then, at therapy-initiation stage and at month 6. Each imaging session included scans at baseline (run1) and after (run2) a 25-min, within-session, motor-practice task, consisting of a paced right-thumb flexion. FC was assessed using a seed on the left primary motor cortex to obtain parametric maps at run1 and task-induced FC change (run2-run1). Comparison between 3-week before- and fingolimod start sessions accounted for a test-retest effect. The main outcome was the changes in both baseline and task-induced changes in FC, between initiation and 6 months. MRI contrast enhancement was detected in 14 patients at initiation and only in 3 at month 6. There was a significant improvement (p < 0.05) in cognitive function, as measured by the Paced Auditory Serial Addition Task, at month 6 compared to initiation. After accounting for test-retest effect, baseline FC significantly decreased at month 6, with respect to initiation (p < 0.05, family-wise error corrected) in bilateral occipito-parietal areas and cerebellum. A task-induced change in FC at month 6 showed a significant increment in all examined sessions, involving not only areas of the sensorimotor network, but also posterior cortical areas (cuneus and precuneus) and areas of the prefrontal and temporal cortices (p < 0.05, family-wise error corrected). Cognitive improvement at month 6 was significantly (p < 0.05) related to baseline FC reduction in posterior cortical areas. This study shows significant changes in functional connectivity, both at baseline and after the execution of a simple motor task following 6 months of fingolimod therapy.

Neuroprotective effect of l-serine against white matter demyelination by harnessing and modulating inflammation in mice

Demyelination in white matter is the end product of numerous pathological processes. This study was designed to evaluate the neuroprotective effect of l-serine and the underlying mechanisms against the demyelinating injury of white matter. A model of focal demyelinating lesions (FDL) was established using the two-point stereotactic injection of 0.25% lysophosphatidylcholine (LPC, 10 μg per point) into the corpus callosum of mice. Mice were then intraperitoneally injected with one of three doses of l-serine (114, 342, or 1026 mg/kg) 2 h after FDL, and then twice daily for the next five days. Behavior tests and histological analysis were assessed for up to twenty-eight days post-FDL induction. Electron microscopy was used for ultrastructural investigation. In vitro, we applied primary co-cultures of microglia and oligodendrocytes for oxygen glucose deprivation (OGD). After establishing FDL, l-serine treatment: 1) improved spatial learning, memory and cognitive ability in mice, and relieved anxiety for 4 weeks post-FDL induction; 2) reduced abnormally dephosphorylated neurofilament proteins, increased myelin basic protein, and preserved anatomic myelinated axons; 3) inhibited microglia activation and reduced the release of inflammatory factors; 4) promoted recruitment and proliferation of oligodendrocyte progenitor cells, and the efficiency of subsequent remyelination on day twenty-eight post-FDL induction. In vitro experiments, showed that l-serine not only directly protected against oligodendrocytes from OGD damage, but also provided an indirect protective effect by regulating microglia. In our study, l-serine offered long-lasting behavioral and oligodendrocyte protection and promoted remyelination. Therefore, l-serine may be an effective clinical treatment aganist white matter injury.

The Use of Cannabis and Cannabinoids in Treating Symptoms of Multiple Sclerosis: a Systematic Review of Reviews

PURPOSE OF REVIEW

Pharmaceutical cannabinoids such as nabiximols, nabilone and dronabinol, and plant-based cannabinoids have been investigated for their therapeutic potential in treating multiple sclerosis (MS) symptoms. This review of reviews aimed to synthesise findings from high quality systematic reviews that examined the safety and effectiveness of cannabinoids in multiple sclerosis. We examined the outcomes of disability and disability progression, pain, spasticity, bladder function, tremor/ataxia, quality of life and adverse effects.

RECENT FINDINGS

We identified 11 eligible systematic reviews providing data from 32 studies, including 10 moderate to high quality RCTs. Five reviews concluded that there was sufficient evidence that cannabinoids may be effective for symptoms of pain and/or spasticity in MS. Few reviews reported conclusions for other symptoms. Recent high quality reviews find cannabinoids may have modest effects in MS for pain or spasticity. Future research should include studies with non-cannabinoid comparators; this is an important gap in the evidence.

Efficacy of fingolimod and interferon beta-1b on cognitive, MRI, and clinical outcomes in relapsing-remitting multiple sclerosis: an 18-month, open-label, rater-blinded, randomised, multicentre study (the GOLDEN study)

Cognitive impairment (CI) affects 40-65% of multiple sclerosis (MS) patients. This study attempted evaluating the effects of fingolimod and interferon beta-1b (IFN β-1b) on CI progression, magnetic resonance imaging (MRI) and clinical outcomes in relapsing-remitting MS (RRMS) patients over 18 months. The GOLDEN study was a pilot study including RRMS patients with CI randomised (2:1) to fingolimod (0.5 mg daily)/IFN β-1b (250 µg every other day). CI was assessed via Rao's Brief Repeatable Battery and Delis-Kaplan Executive Function System test. MRI parameters, Expanded Disability Status Scale scores and relapses were measured. Overall, 157 patients were randomised, of whom 30 discontinued the study (fingolimod, 8.49%; IFN β-1b, 41.18%; p ≤ 0.0001). Patients randomised to fingolimod had more severe clinical and MRI disease characteristics at baseline compared with IFN β-1b. At Month (M) 18, both treatment groups showed improvements in all cognitive parameters. At M18, relapse rate, total number and volume of T2/T1 gadolinium-enhancing lesions were higher with IFN β-1b, as well as the percentage brain volume change during the study. Safety and tolerability of both treatments were similar to previous studies. Both treatments showed improvements in cognitive parameters. Fingolimod demonstrated significantly better effects on MRI parameters and relapse rate. Imbalance in baseline characteristics and the drop-out pattern may have favoured IFN β-1b. A longer duration trial may be needed to observe the complete expression of differential effects on CI scales reflecting the between-groups differences on MRI. Although limited in size, the GOLDEN study confirms the favourable benefit-risk profile of fingolimod reported in previous studies.

Efficacy of daclizumab beta versus intramuscular interferon beta-1a on disability progression across patient demographic and disease activity subgroups in DECIDE

Background:

Demonstration of clinical benefits on disability progression measures is an important attribute of effective multiple sclerosis (MS) treatments.

Objective:

Examine efficacy of daclizumab beta versus intramuscular (IM) interferon beta-1a on measures of disability progression in patient subgroups from DECIDE.

Methods:

Twenty-four-week confirmed disability progression (CDP), 24-week sustained worsening on a modified Multiple Sclerosis Functional Composite (MSFCS) where 3-Second Paced Auditory Serial Addition Test was replaced by Symbol Digit Modalities Test, and proportion of patients with clinically meaningful worsening in 29-Item Multiple Sclerosis Impact Scale physical impact subscale (MSIS-29 PHYS) score from baseline to week 96 were examined in the overall population and subgroups defined by baseline demographic/disease characteristics.

Results:

Daclizumab beta significantly reduced risk of 24-week CDP (hazard ratio (HR), 0.73; 95% confidence interval (95% CI), 0.55–0.98), risk of 24-week sustained MSFCS progression (HR, 0.80; 95% CI, 0.67–0.95), and odds of clinically meaningful worsening in MSIS-29 PHYS (odds ratio, 0.76; 95% CI, 0.60–0.95) versus IM interferon beta-1a. Point estimates showed trends favoring daclizumab beta over IM interferon beta-1a across several patient subgroups for all three outcome measures.

Conclusion:

Daclizumab beta showed consistent benefit versus IM interferon beta-1a across measures assessing patient disability/function and across a range of clinical baseline characteristics in patients with relapsing-remitting MS.

Intervening to reduce the risk of future disability from multiple sclerosis: are we there yet?

Disease-modifying therapies (DMTs) delay or may prevent the progression of patients with high-risk clinically isolated syndrome (CIS) to clinically definite multiple sclerosis (MS), and from relapsing-remitting MS to secondary progressive MS. Current evidence on the effects of DMT on disability in MS is supported by the use of the Expanded Disability Status Scale (EDSS), which is dominated by ambulation, and usually used as a secondary outcome measure. Less is known about the long-term effects of DMTs on other aspects of functional status, particularly cognition, which is a key determinant of ability to work. The time scale for measurements of disability is at most a few years, with scant data from more than 10 years of observation. Longer prospective follow-up of large numbers of patients with CIS is needed to determine whether early intervention with a DMT influences long-term disease progression. Finally, the emergence of the radiologically isolated syndrome (RIS) as a clinical entity has shifted the debate about when to intervene to an even earlier time frame. Balancing the significant side-effects associated with DMT in general and the expected outcome of pharmacologic intervention is increasingly problematic for managing patients with uncertain prognosis, as many patients may have low-risk CIS, benign MS or patients with RIS only. Preventing long-term disability in MS should be recognised more clearly as an important outcome in its own right, with disability measured more consistently with more sensitive instruments beyond the use of the EDSS.