Improved prediction of early cognitive impairment in multiple sclerosis combining blood and imaging biomarkers

Artificial Intelligence and Multiple Sclerosis

In this paper, we analyse the different advances in artificial intelligence (AI) approaches in multiple sclerosis (MS). AI applications in MS range across investigation of disease pathogenesis, diagnosis, treatment, and prognosis. A subset of AI, Machine learning (ML) models analyse various data sources, including magnetic resonance imaging (MRI), genetic, and clinical data, to distinguish MS from other conditions, predict disease progression, and personalize treatment strategies. Additionally, AI models have been extensively applied to lesion segmentation, identification of biomarkers, and prediction of outcomes, disease monitoring, and management. Despite the big promises of AI solutions, model interpretability and transparency remain critical for gaining clinician and patient trust in these methods. The future of AI in MS holds potential for open data initiatives that could feed ML models and increasing generalizability, the implementation of federated learning solutions for training the models addressing data sharing issues, and generative AI approaches to address challenges in model interpretability, and transparency. In conclusion, AI presents an opportunity to advance our understanding and management of MS. AI promises to aid clinicians in MS diagnosis and prognosis improving patient outcomes and quality of life, however ensuring the interpretability and transparency of AI-generated results is going to be key for facilitating the integration of AI into clinical practice.

Matching proposed clinical and MRI criteria of aggressive multiple sclerosis to serum and cerebrospinal fluid markers of neuroaxonal and glial injury

BACKGROUND

Definitions of aggressive MS employ clinical and MR imaging criteria to identify highly active, rapidly progressing disease courses. However, the degree of overlap between clinical and radiological parameters and biochemical markers of CNS injury is not fully understood. Aim of this cross-sectional study was to match clinical and MR imaging hallmarks of aggressive MS to serum/CSF markers of neuroaxonal and astroglial injury (neurofilament light chain (sNfL, cNfL), and glial fibrillary acidic protein (sGFAP, cGFAP)).

METHODS

We recruited 77 patients with relapsing-remitting MS (RRMS) and 22 patients with clinically isolated syndrome. NfL and GFAP levels in serum and CSF were assessed using a single-molecule-array HD-1-analyzer. A general linear model with each biomarker as a dependent variable was computed. Clinical and imaging criteria of aggressive MS, as recently proposed by the ECTRIMS Consensus Group, were modeled as independent variables. Other demographic, clinical or laboratory parameters, were modeled as covariates. Analyses were repeated in a homogenous subgroup, consisting only of newly diagnosed, treatment-naïve RRMS patients presenting with an acute relapse.

RESULTS

After adjusting for covariates and multiplicity of testing, sNfL and cNfL concentrations were strongly associated with the presence of ≥2 gadolinium-enhancing lesions (psNfL = 0.00008; pcNfL = 0.004) as well as the presence of infratentorial lesions on MRI (psNfL = 0.0003; pcNfL < 0.004). No other clinical and imaging criteria of aggressive MS correlated significantly with NfL or GFAP in serum and CSF. In the more homogeneous subgroup, sNfL still was associated with the presence of ≥2 gadolinium-enhancing lesions (psNfL = 0.001), presence of more than 20 T2-lesions (psNfL = 0.049) as well as the presence of infratentorial lesions on MRI (psNfL = 0.034), while cNfL was associated with the presence of ≥2 gadolinium-enhancing lesions (psNfL = 0.011) and presence of more than 20 T2-lesions (psNfL = 0.029).

CONCLUSIONS

Among proposed risk factors for an aggressive disease course, MRI findings but not clinical characteristics correlated with sNfL and cNfL as a marker of neuroaxonal injury and should be given appropriate weight considering MS prognosis and therapy. No significant correlation was detected for GFAP alone.

Cognitive impairment in multiple sclerosis: from phenomenology to neurobiological mechanisms

Multiple sclerosis (MS) is an autoimmune-mediated disease of the central nervous system characterized by inflammation, demyelination and chronic progressive neurodegeneration. Among its broad and unpredictable range of clinical symptoms, cognitive impairment (CI) is a common and disabling feature greatly affecting the patients' quality of life. Its prevalence is 20% up to 88% with a wide variety depending on the phenotype of MS, with highest frequency and severity in primary progressive MS. Involving different cognitive domains, CI is often associated with depression and other neuropsychiatric symptoms, but usually not correlated with motor and other deficits, suggesting different pathophysiological mechanisms. While no specific neuropathological data for CI in MS are available, modern research has provided evidence that it arises from the disease-specific brain alterations. Multimodal neuroimaging, besides structural changes of cortical and deep subcortical gray and white matter, exhibited dysfunction of fronto-parietal, thalamo-hippocampal, default mode and cognition-related networks, disruption of inter-network connections and involvement of the γ-aminobutyric acid (GABA) system. This provided a conceptual framework to explain how aberrant pathophysiological processes, including oxidative stress, mitochondrial dysfunction, autoimmune reactions and disruption of essential signaling pathways predict/cause specific disorders of cognition. CI in MS is related to multi-regional patterns of cerebral disturbances, although its complex pathogenic mechanisms await further elucidation. This article, based on systematic analysis of PubMed, Google Scholar and Cochrane Library, reviews current epidemiological, clinical, neuroimaging and pathogenetic evidence that could aid early identification of CI in MS and inform about new therapeutic targets and strategies.

A Radiomic "Warning Sign" of Progression on Brain MRI in Individuals with MS

BACKGROUND AND PURPOSE

MS is a chronic progressive, idiopathic, demyelinating disorder whose diagnosis is contingent on the interpretation of MR imaging. New MR imaging lesions are an early biomarker of disease progression. We aimed to evaluate a machine learning model based on radiomics features in predicting progression on MR imaging of the brain in individuals with MS.

MATERIALS AND METHODS

This retrospective cohort study with external validation on open-access data obtained full ethics approval. Longitudinal MR imaging data for patients with MS were collected and processed for machine learning. Radiomics features were extracted at the future location of a new lesion in the patients' prior MR imaging ("prelesion"). Additionally, "control" samples were obtained from the normal-appearing white matter for each participant. Machine learning models for binary classification were trained and tested and then evaluated the external data of the model.

RESULTS

The total number of participants was 167. Of the 147 in the training/test set, 102 were women and 45 were men. The average age was 42 (range, 21-74 years). The best-performing radiomics-based model was XGBoost, with accuracy, precision, recall, and F1-score of 0.91, 0.91, 0.91, and 0.91 on the test set, and 0.74, 0.74, 0.74, and 0.70 on the external validation set. The 5 most important radiomics features to the XGBoost model were associated with the overall heterogeneity and low gray-level emphasis of the segmented regions. Probability maps were produced to illustrate potential future clinical applications.

CONCLUSIONS

Our machine learning model based on radiomics features successfully differentiated prelesions from normal-appearing white matter. This outcome suggests that radiomics features from normal-appearing white matter could serve as an imaging biomarker for progression of MS on MR imaging.

Toward identifying key mechanisms of progression in multiple sclerosis

A major therapeutic goal in the treatment of multiple sclerosis (MS) is to prevent the accumulation of disability over an often decades-long disease course. Disability progression can result from acute relapses as well as from CNS intrinsic parenchymal disintegration without de novo CNS lesion formation. Research focus has shifted to progression not associated with acute inflammation, as it is not sufficiently controlled by currently available treatments. This review outlines how recent advances in the understanding of the pathogenesis of progressive MS have been facilitated by the development of more precise, less static pathogenetic concepts of progressive MS, as well as by new techniques for the analysis of region-specific proteomic and transcriptomic signatures in the human CNS. We highlight key drivers of MS disease progression and potential targets in its treatment.

Multi-modal neuroimaging signatures predict cognitive decline in multiple sclerosis: A 5-year longitudinal study

BACKGROUND

Cognitive impairment is a hallmark of multiple sclerosis (MS) but is usually an under-recorded symptom of disease progression. Identifying the predictive signatures of cognitive decline in people with MS (pwMS) over time is important to ensure effective preventative treatment strategies. Structural and functional brain characteristics as measured by various magnetic resonance (MR) methods have been correlated with variation in cognitive function in MS, but typically these studies are limited to a single MR modality and/or are cross-sectional designs. Here we assess the predictive value of multiple different MR modalities in relation to cognitive decline in pwMS over 5 years.

METHODS

A cohort of 43 pwMS was assessed at baseline and 5 years follow-up. Baseline (input) data consisted of 70 multi-modal MRI measures for different brain regions including magnetic resonance spectroscopy (MRS), diffusion tensor imaging (DTI) and standard volumetrics. Age, sex, disease duration and treatment were included as clinical inputs. Cognitive function was assessed using the Audio Recorded Cognitive Screen (ARCS) and the Symbol Digit Modalities Test (SDMT). Prediction modelling was performed using the machine learning package - GLMnet, where a penalised regression was applied to identify multi-modal signatures with the most predictive value (and the least error) for each outcome.

RESULTS

The multi-modal approach to neuroimaging was able to accurately predict cognitive decline in pwMS. The best performing model for change in total ARCS (tARCS) included 16 features from across the various MR modalities and explained 54 % of the variation in change over time (R2=0.54, 95 % CI=0.48-0.51). The features included nine MRS, four volumetric and two DTI parameters. The model also selected disease duration, but not treatment, as a predictive feature. By comparison, the best model for SDMT included several of the same above features and explained 39 % of the change over time (R2=0.39, 95 % CI=0.48-0.51). Conventional volumetric measures were about half as good at predicting change in tARCS score compared to the best multi-modal model (R2=0.26 95 % CI:0.22-0.29). The clinical interpretation of the best predictive model for change in tARCS showed that cognitive decline could be predicted with >90 % accuracy in this cohort (AUC=0.92, SE=0.86 - 0.94).

CONCLUSION

Multi-modal MRI signatures can predict cognitive decline in a cohort of pwMS over 5 years with high accuracy. Future studies will benefit from the inclusion of even more MR modalities e.g., functional MRI, quantitative susceptibility mapping, magnetisation transfer imaging, as well as other potential predictors e.g., genetic and environmental factors. With further validation, this signature could be used in future trials with high-risk patients to personalise the management of cognitive decline in pwMS, even in the absence of relapses.

Neurofilament Light Chain in Adult and Pediatric Multiple Sclerosis: A Promising Biomarker to Better Characterize Disease Activity and Personalize MS Treatment

Many biological markers have been explored in multiple sclerosis (MS) to better quantify disease burden and better evaluate response to treatments, beyond clinical and MRI data. Among these, neurofilament light chain (Nf-L), although non-specific for this disease and found to be increased in other neurological conditions, has been shown to be the most promising biomarker for assessing axonal damage in MS, with a definite role in predicting the development of MS in patients at the first neurological episode suggestive of MS, and also in a preclinical phase. There is strong evidence that Nf-L levels are increased more in relapsing versus stable MS patients, and that they predict future disease evolution (relapses, progression, MRI measures of activity/progression) in MS patients, providing information on response to therapy, helping to anticipate clinical decisions in patients with an apparently stable evolution, and identifying patient non-responders to disease-modifying treatments. Moreover, Nf-L can contribute to the better understanding of the mechanisms of demyelination and axonal damage in adult and pediatric MS. A fundamental requirement for its clinical use is the accurate standardization of normal values, corrected for confounding factors, in particular age, sex, body mass index, and presence of comorbidities. In this review, a guide is provided to update clinicians on the use of Nf-L in clinical activity.

Spatial transcriptomics and neurofilament light chain reveal changes in lesion patterns in murine autoimmune neuroinflammation

OBJECTIVE

Ongoing neuroaxonal damage is a major contributor to disease progression and long-term disability in multiple sclerosis. However, spatio-temporal distribution and pathophysiological mechanisms of neuroaxonal damage during acute relapses and later chronic disease stages remain poorly understood.

METHODS

Here, we applied immunohistochemistry, single-molecule array, spatial transcriptomics, and microglia/axon co-cultures to gain insight into spatio-temporal neuroaxonal damage in experimental autoimmune encephalomyelitis (EAE).

RESULTS

Association of spinal cord white matter lesions and blood-based neurofilament light (sNfL) levels revealed a distinct, stage-dependent anatomical pattern of neuroaxonal damage: in chronic EAE, sNfL levels were predominately associated with anterolateral lumbar lesions, whereas in early EAE sNfL showed no correlation with lesions in any anatomical location. Furthermore, neuroaxonal damage in late EAE was largely confined to white matter lesions but showed a widespread distribution in early EAE. Following this pattern of neuroaxonal damage, spatial transcriptomics revealed a widespread cyto- and chemokine response at early disease stages, whereas late EAE was characterized by a prominent glial cell accumulation in white matter lesions. These findings were corroborated by immunohistochemistry and microglia/axon co-cultures, which further revealed a strong association between CNS myeloid cell activation and neuroaxonal damage both in vivo and in vitro.

INTERPRETATION

Our findings indicate that CNS myeloid cells may play a crucial role in driving neuroaxonal damage in EAE. Moreover, neuroaxonal damage can progress in a stage-dependent centripetal manner, transitioning from normal-appearing white matter to focal white matter lesions. These insights may contribute to a better understanding of neurodegeneration and elevated sNfL levels observed in multiple sclerosis patients at different disease stages.

Innovations in Multiple Sclerosis Care: The Impact of Artificial Intelligence via Machine Learning on Clinical Research and Decision-Making

Artificial intelligence (AI) and its specialized subcomponent machine learning are becoming increasingly popular analytic techniques. With this growth, clinicians and health care professionals should soon expect to see an increase in diagnostic, therapeutic, and rehabilitative technologies and processes that use elements of AI. The purpose of this review is twofold. First, we provide foundational knowledge that will help health care professionals understand these modern algorithmic techniques and their implementation for classification and clustering tasks. The phrases artificial intelligence and machine learning are defined and distinguished, as are the metrics by which they are assessed and delineated. Subsequently, 7 broad categories of algorithms are discussed, and their uses explained. Second, this review highlights several key studies that exemplify advances in diagnosis, treatment, and rehabilitation for individuals with multiple sclerosis using a variety of data sources-from wearable sensors to questionnaires and serology-and elements of AI. This review will help health care professionals and clinicians better understand AI-dependent diagnostic, therapeutic, and rehabilitative techniques, thereby facilitating a greater quality of care.

Neurofilaments - Small proteins of physiological significance and predictive power for future neurodegeneration and cognitive decline across the life span

Neurofilaments (NFs) are not only important for axonal integrity and nerve conduction in large myelinated axons but they are also thought to be crucial for receptor and synaptic functioning. Therefore, NFs may play a critical role in cognitive functions, as cognitive processes are known to depend on synaptic integrity and are modulated by dopaminergic signaling. Here, we present a theory-driven interdisciplinary approach that NFs may link inflammation, neurodegeneration, and cognitive functions. We base our hypothesis on a wealth of evidence suggesting a causal link between inflammation and neurodegeneration and between these two and cognitive decline (see Fig. 1), also taking dopaminergic signaling into account. We conclude that NFs may not only serve as biomarkers for inflammatory, neurodegenerative, and cognitive processes but also represent a potential mechanical hinge between them, moreover, they may even have predictive power regarding future cognitive decline. In addition, we advocate the use of both NFs and MRI parameters, as their synthesis offers the opportunity to individualize medical treatment by providing a comprehensive view of underlying disease activity in neurological diseases. Since our society will become significantly older in the upcoming years and decades, maintaining cognitive functions and healthy aging will play an important role. Thanks to technological advances in recent decades, NFs could serve as a rapid, noninvasive, and relatively inexpensive early warning system to identify individuals at increased risk for cognitive decline and could facilitate the management of cognitive dysfunctions across the lifespan.

[15th Post-ECTRIMS Meeting: a review of the latest developments presented at the 2022 ECTRIMS Congress (Part I)]

INTRODUCTION

On 4 and 5 November 2022, Madrid hosted the 15th edition of the Post-ECTRIMS Meeting, where neurologists specialised in multiple sclerosis (MS) outlined the most relevant novelties presented at the 2022 ECTRIMS Congress, held in Amsterdam from 26 to 28 October.

AIM

To synthesise the content presented at the 15th edition of the Post-ECTRIMS Meeting, in an article broken down into two parts.

DEVELOPMENT

In this first part, the initial events involved in the onset of MS, the role played by lymphocytes and the migration of immune system cells into the central nervous system are presented. It describes emerging biomarkers in body fluids and imaging findings that are predictive of disease progression and useful in the differential diagnosis of MS. It also discusses advances in imaging techniques which, together with a better understanding of the agents involved in demyelination and remyelination processes, provide a basis for dealing with remyelination in the clinical setting. Finally, the mechanisms triggering the inflammatory reaction and neurodegeneration involved in MS pathology are reviewed.

The Blood Concentration of Metallic Nanoparticles Is Related to Cognitive Performance in People with Multiple Sclerosis: An Exploratory Analysis

The imbalance in the concentration of metallic nanoparticles has been demonstrated to play an important role in multiple sclerosis (MS), which may impact cognition. Biomarkers are needed to provide insights into the pathogenesis and diagnosis of MS. They can be used to gain a better understanding of cognitive decline in people with MS (pwMS). In this study, we investigated the relationship between the blood concentration of metallic nanoparticles (blood nanoparticles) and cognitive performance in pwMS. First, four mL blood samples, clinical characteristics, and cognitive performance were obtained from 21 pwMS. All participants had relapse-remitting MS, with a score of ≤4.5 points in the expanded disability status scale. They were relapse-free in the three previous months from the day of collection and had no orthopedic, muscular, cardiac, and cerebellar diseases. We quantified the following metallic nanoparticles: aluminum, chromium, copper, iron, magnesium, nickel, zinc, and total concentration. Cognitive performance was measured by mini-mental state examination (MMSE) and the symbol digit modalities test (SDMT). Pearson's and Spearman's correlation coefficients and stepwise linear regression were calculated to assess the relationship between cognitive performance and blood nanoparticles. We found that better performance in SDMT and MMSE was related to higher total blood nanoparticles (r = 0.40; p < 0.05). Also, better performance in cognitive processing speed and attention (SDMT) and mental state (MMSE) were related to higher blood iron (r = 0.44; p < 0.03) and zinc concentrations (r = 0.41; p < 0.05), respectively. The other metallic nanoparticles (aluminum, chromium, copper, magnesium, and nickel) did not show a significant relationship with the cognitive parameters (p > 0.05). Linear regression estimated a significant association between blood iron concentration and SDMT performance. In conclusion, blood nanoparticles are related to cognitive performance in pwMS. Our findings suggest that the blood concentration of metallic nanoparticles, particularly the iron concentration, is a promising biomarker for monitoring cognitive impairment in pwMS.

Neuroimaging Technology in Exercise Neurorehabilitation Research in Persons with MS: A Scoping Review

There is increasing interest in the application of neuroimaging technology in exercise neurorehabilitation research among persons with multiple sclerosis (MS). The inclusion and focus on neuroimaging outcomes in MS exercise training research is critical for establishing a biological basis for improvements in functioning and elevating exercise within the neurologist's clinical armamentarium alongside disease modifying therapies as an approach for treating the disease and its consequences. Indeed, the inclusion of selective neuroimaging approaches and sensor-based technology among physical activity, mobility, and balance outcomes in such MS research might further allow for detecting specific links between the brain and real-world behavior. This paper provided a scoping review on the application of neuroimaging in exercise training research among persons with MS based on searches conducted in PubMed, Web of Science, and Scopus. We identified 60 studies on neuroimaging-technology-based (primarily MRI, which involved a variety of sequences and approaches) correlates of functions, based on multiple sensor-based measures, which are typically targets for exercise training trials in MS. We further identified 12 randomized controlled trials of exercise training effects on neuroimaging outcomes in MS. Overall, there was a large degree of heterogeneity whereby we could not identify definitive conclusions regarding a consistent neuroimaging biomarker of MS-related dysfunction or singular sensor-based measure, or consistent neural adaptation for exercise training in MS. Nevertheless, the present review provides a first step for better linking correlational and randomized controlled trial research for the development of high-quality exercise training studies on the brain in persons with MS, and this is timely given the substantial interest in exercise as a potential disease-modifying and/or neuroplasticity-inducing behavior in this population.

A multimodal marker for cognitive functioning in multiple sclerosis: the role of NfL, GFAP and conventional MRI in predicting cognitive functioning in a prospective clinical cohort

BACKGROUND

Cognitive impairment in people with MS (PwMS) has primarily been investigated using conventional imaging markers or fluid biomarkers of neurodegeneration separately. However, the single use of these markers do only partially explain the large heterogeneity found in PwMS.

OBJECTIVE

To investigate the use of multimodal (bio)markers: i.e., serum and cerebrospinal fluid (CSF) levels of neurofilament light chain (NfL) and glial fibrillary acidic protein (GFAP) and conventional imaging markers in predicting cognitive functioning in PwMS.

METHODS

Eighty-two PwMS (56 females, disease duration = 14 ± 9 years) underwent neuropsychological and neurological examination, structural magnetic resonance imaging, blood sampling and lumbar puncture. PwMS were classified as cognitively impaired (CI) if scoring ≥ 1.5SD below normative scores on ≥ 20% of test scores. Otherwise, PwMS were defined as cognitively preserved (CP). Association between fluid and imaging (bio)markers were investigated, as well as binary logistics regression to predict cognitive status. Finally, a multimodal marker was calculated using statistically important predictors of cognitive status.

RESULTS

Only higher NfL levels (in serum and CSF) correlated with worse processing speed (r = - 0.286, p = 0.012 and r = - 0.364, p = 0.007, respectively). sNfL added unique variance in the prediction of cognitive status on top of grey matter volume (NGMV), p = 0.002). A multimodal marker of NGMV and sNfL yielded most promising results in predicting cognitive status (sensitivity = 85%, specificity = 58%).

CONCLUSION

Fluid and imaging (bio)markers reflect different aspects of neurodegeneration and cannot be used interchangeably as markers for cognitive functioning in PwMS. The use of a multimodal marker, i.e., the combination of grey matter volume and sNfL, seems most promising for detecting cognitive deficits in MS.

Validity of serum neurofilament light chain as a prognostic biomarker of disease activity in multiple sclerosis

Multiple sclerosis (MS) is a chronic demyelinating and neuroinflammatory disease of the human central nervous system with complex pathoetiology, heterogeneous presentations and an unpredictable course of disease progression. There remains an urgent need to identify and validate a biomarker that can reliably predict the initiation and progression of MS as well as identify patient responses to disease-modifying treatments/therapies (DMTs). Studies exploring biomarkers in MS and other neurodegenerative diseases currently focus mainly on cerebrospinal fluid (CSF) analyses, which are invasive and impractical to perform on a repeated basis. Recent studies, replacing CSF with peripheral blood samples, have revealed that the elevation of serum neurofilament light chain (sNfL) in the clinical stages of MS is, potentially, an ideal prognostic biomarker for predicting disease progression and for possibly guiding treatment decisions. However, there are unresolved factors (the definition of abnormal values of sNfL concentration, the standardisation of measurement and the amount of change in sNfL concentration that is significant) that are preventing its use as a biomarker in routine clinical practice for MS. This updated review critiques these recent findings and highlights areas for focussed work to facilitate the use of sNfL as a prognostic biomarker in MS management.

The Brave New World of Early Treatment of Multiple Sclerosis: Using the Molecular Biomarkers CXCL13 and Neurofilament Light to Optimize Immunotherapy

Multiple sclerosis (MS) is a highly heterogeneous disease involving a combination of inflammation, demyelination, and CNS injury. It is the leading cause of non-traumatic neurological disability in younger people. There is no cure, but treatments in the form of immunomodulatory drugs (IMDs) are available. Experience over the last 30 years has shown that IMDs, also sometimes called disease-modifying therapies, are effective in downregulating neuroinflammatory activity. However, there are a number of negatives in IMD therapy, including potential for significant side-effects and adverse events, uncertainty about long-term benefits regarding disability outcomes, and very high and increasing financial costs. The two dozen currently available FDA-approved IMDs also are heterogeneous with respect to efficacy and safety, especially long-term safety, and determining an IMD treatment strategy is therefore challenging for the clinician. Decisions about optimal therapy have been particularly difficult in early MS, at the time of the initial clinical demyelinating event (ICDE), at a time when early, aggressive treatment would best be initiated on patients destined to have a highly inflammatory course. However, given the fact that the majority of ICDE patients have a more benign course, aggressive immunosuppression, with its attendant risks, should not be administered to this group, and should only be reserved for patients with a more neuroinflammatory course, a decision that can only be made in retrospect, months to years after the ICDE. This quandary of moderate vs. aggressive therapy facing clinicians would best be resolved by the use of biomarkers that are predictive of future neuroinflammation. Unfortunately, biomarkers, especially molecular biomarkers, have not thus far been particularly useful in assisting clinicians in predicting the likelihood of future neuroinflammation, and thus guiding therapy. However, the last decade has seen the emergence of two highly promising molecular biomarkers to guide therapy in early MS: the CXCL13 index and neurofilament light. This paper will review the immunological and neuroscientific underpinnings of these biomarkers and the data supporting their use in early MS and will propose how they will likely be used to maximize benefit and minimize risk of IMDs in MS patients.