Machine-learning-based prediction of disability progression in multiple sclerosis: An observational, international, multi-center study.

BACKGROUND: Disability progression is a key milestone in the disease evolution of people with multiple sclerosis (PwMS). Prediction models of the probability of disability progression have not yet reached the level of trust needed to be adopted in the clinic. A common benchmark to assess model development in multiple sclerosis is also currently lacking. METHODS: Data of adult PwMS with a follow-up of at least three years from 146 MS centers, spread over 40 countries and collected by the MSBase consortium was used. With basic inclusion criteria for quality requirements, it represents a total of 15, 240 PwMS. External validation was performed and repeated five times to assess the significance of the results. Transparent Reporting for Individual Prognosis Or Diagnosis (TRIPOD) guidelines were followed. Confirmed disability progression after two years was predicted, with a confirmation window of six months. Only routinely collected variables were used such as the expanded disability status scale, treatment, relapse information, and MS course. To learn the probability of disability progression, state-of-the-art machine learning models were investigated. The discrimination performance of the models is evaluated with the area under the receiver operator curve (ROC-AUC) and under the precision recall curve (AUC-PR), and their calibration via the Brier score and the expected calibration error. All our preprocessing and model code are available at https://gitlab.com/edebrouwer/ms_benchmark, making this task an ideal benchmark for predicting disability progression in MS. FINDINGS: Machine learning models achieved a ROC-AUC of 0⋅71 ± 0⋅01, an AUC-PR of 0⋅26 ± 0⋅02, a Brier score of 0⋅1 ± 0⋅01 and an expected calibration error of 0⋅07 ± 0⋅04. The history of disability progression was identified as being more predictive for future disability progression than the treatment or relapses history. CONCLUSIONS: Good discrimination and calibration performance on an external validation set is achieved, using only routinely collected variables. This suggests machine-learning models can reliably inform clinicians about the future occurrence of progression and are mature for a clinical impact study.

Microstructural characterization of multiple sclerosis lesion phenotypes using multiparametric longitudinal analysis.

BACKGROUND AND OBJECTIVES: In multiple sclerosis (MS), slowly expanding lesions were shown to be associated with worse disability and prognosis. Their timely detection from cross-sectional data at early disease stages could be clinically relevant to inform treatment planning. Here, we propose to use multiparametric, quantitative MRI to allow a better cross-sectional characterization of lesions with different longitudinal phenotypes. METHODS: We analysed T1 and T2 relaxometry maps from a longitudinal cohort of MS patients. Lesions were classified as enlarging, shrinking, new or stable based on their longitudinal volumetric change using a newly developed automated technique. Voxelwise deviations were computed as z-scores by comparing individual patient data to T1, T2 and T2/T1 normative values from healthy subjects. We studied the distribution of microstructural properties inside lesions and within perilesional tissue. RESULTS AND CONCLUSIONS: Stable lesions exhibited the highest T1 and T2 z-scores in lesion tissue, while the lowest values were observed for new lesions. Shrinking lesions presented the highest T1 z-scores in the first perilesional ring while enlarging lesions showed the highest T2 z-scores in the same region. Finally, a classification model was trained to predict the longitudinal lesion type based on microstructural metrics and feature importance was assessed. Z-scores estimated in lesion and perilesional tissue from T1, T2 and T2/T1 quantitative maps carry discriminative and complementary information to classify longitudinal lesion phenotypes, hence suggesting that multiparametric MRI approaches are essential for a better understanding of the pathophysiological mechanisms underlying disease activity in MS lesions.

Real-world effectiveness of cladribine as an escalation strategy for MS: Insights from the Czech nationwide ReMuS registry.

Background: Cladribine, a selective immune reconstitution therapy, is approved for the treatment of adult patients with highly active multiple sclerosis (MS). Objectives: Provide experience with cladribine therapy in a real-world setting. Methods: This is a registry-based retrospective observational cohort study. First, using data from the Czech nationwide registry ReMuS, we analysed patients who initiated cladribine from September 1, 2018 to December 31, 2021. Second, we analysed a subgroup of patients who initiated cladribine between September 1, 2018 to June 30, 2020, thus possessing a follow-up period of at least 2 years. We evaluated demographic and MS characteristics including disease-modifying therapies (DMTs) before and after cladribine administration, relapses, Expanded Disability Status Scale (EDSS), and adherence. Results: In total, 617 patients (335 with follow-up of at least 2 years) started cladribine therapy in the study period (mean age 37.0, mean disease duration 8.4 years, 74.1% females). In most cases, cladribine was administered as a second-line drug, a total of 80.7% had been escalated from a platform DMT. During 2 years before cladribine initiation, the average annualised relapse rate (ARR) was .67. Following cladribine initiation, the ARR decreased to .28 in the first year and .22 in the second year. Overall, across the entire two-year treatment period, 69.0% of patients were relapse-free and the average ARR was .25. As for EDSS development, the median baseline EDSS was 2.5 and remained stable even after 24 months. The adherence to treatment ranged of around 90%. Conclusion: This nationwide study confirms the efficacy of cladribine in real-world settings, especially in patients who are not treatment-naïve. In addition, the study shows an exceptionally high adherence rate, a finding that underscores the invaluable role of cladribine, but also the value of registry-based studies in capturing real-world clinical practice.

Big Multiple Sclerosis Data network: an international registry research network.

BACKGROUND: The Big Multiple Sclerosis Data (BMSD) network ( https://bigmsdata.org ) was initiated in 2014 and includes the national multiple sclerosis (MS) registries of the Czech Republic, Denmark, France, Italy, and Sweden as well as the international MSBase registry. BMSD has addressed the ethical, legal, technical, and governance-related challenges for data sharing and so far, published three scientific papers on pooled datasets as proof of concept for its collaborative design. DATA COLLECTION: Although BMSD registries operate independently on different platforms, similarities in variables, definitions and data structure allow joint analysis of data. Certain coordinated modifications in how the registries collect adverse event data have been implemented after BMSD consensus decisions, showing the ability to develop together. DATA MANAGEMENT: Scientific projects can be proposed by external sponsors via the coordinating centre and each registry decides independently on participation, respecting its governance structure. Research datasets are established in a project-to-project fashion and a project-specific data model is developed, based on a unifying core data model. To overcome challenges in data sharing, BMSD has developed procedures for federated data analysis. FUTURE PERSPECTIVES: Presently, BMSD is seeking a qualification opinion from the European Medicines Agency (EMA) to conduct post-authorization safety studies (PASS) and aims to pursue a qualification opinion also for post-authorization effectiveness studies (PAES). BMSD aspires to promote the advancement of real-world evidence research in the MS field.

No evidence for association between rs10191329 severity locus and longitudinal disease severity in 1813 relapse-onset multiple sclerosis patients from the MSBase registry.

BACKGROUND: The International Multiple Sclerosis Genetics Consortium and MultipleMS Consortium recently reported a genetic variant associated with multiple sclerosis (MS) severity. However, it remains unclear if these variants remain associated with more robust, longitudinal measures of disease severity. METHODS: We examined the top variant, rs10191329, from Harroud et al.'s study in 1813 relapse-onset MS patients from the MSBase Registry to assess association with longitudinal disease severity. RESULTS: Our analysis revealed no significant association between rs10191329 genotype and longitudinal binary disease severity (p > 0.05). CONCLUSION: These findings highlight the complexity of genetic factors mediating long-term MS outcomes and the need for further research.

Comparing ocrelizumab to interferon/glatiramer acetate in people with multiple sclerosis over age 60.

BACKGROUND: Ongoing controversy exists regarding optimal management of disease modifying therapy (DMT) in older people with multiple sclerosis (pwMS). There is concern that the lower relapse rate, combined with a higher risk of DMT-related infections and side effects, may alter the risk-benefit balance in older pwMS. Given the lack of pwMS above age 60 in randomised controlled trials, the comparative efficacy of high-efficacy DMTs such as ocrelizumab has not been shown in older pwMS. We aimed to evaluate the comparative effectiveness of ocrelizumab, a high-efficacy DMT, versus interferon/glatiramer acetate (IFN/GA) in pwMS over the age of 60. METHODS: Using data from MSBase registry, this multicentre cohort study included pwMS above 60 who switched to or started on ocrelizumab or IFN/GA. We analysed relapse and disability outcomes after balancing covariates using an inverse probability treatment weighting (IPTW) method. Propensity scores were obtained based on age, country, disease duration, sex, baseline Expanded Disability Status Scale, prior relapses (all-time, 12 months and 24 months) and prior DMT exposure (overall number and high-efficacy DMTs). After weighting, all covariates were balanced. Primary outcomes were time to first relapse and annualised relapse rate (ARR). Secondary outcomes were 6-month confirmed disability progression (CDP) and confirmed disability improvement (CDI). RESULTS: A total of 248 participants received ocrelizumab, while 427 received IFN/GA. The IPTW-weighted ARR for ocrelizumab was 0.01 and 0.08 for IFN/GA. The IPTW-weighted ARR ratio was 0.15 (95% CI 0.06 to 0.33, p<0.001) for ocrelizumab compared with IFN/GA. On IPTW-weighted Cox regression models, HR for time to first relapse was 0.13 (95% CI 0.05 to 0.26, p<0.001). The hazard of first relapse was significantly reduced in ocrelizumab users after 5 months compared with IFN/GA users. However, the two groups did not differ in CDP or CDI over 3.57 years. CONCLUSION: In older pwMS, ocrelizumab effectively reduced relapses compared with IFN/GA. Overall relapse activity was low. This study adds valuable real-world data for informed DMT decision making with older pwMS. Our study also confirms that there is a treatment benefit in older people with MS, given the existence of a clear differential treatment effect between ocrelizumab and IFN/GA in the over 60 age group.

Comparative Effectiveness of Natalizumab, Fingolimod, and Injectable Therapies in Pediatric-Onset Multiple Sclerosis: A Registry-Based Study.

BACKGROUND AND OBJECTIVES: Patients with pediatric-onset multiple sclerosis (POMS) typically experience higher levels of inflammation with more frequent relapses, and though patients with POMS usually recover from relapses better than adults, patients with POMS reach irreversible disability at a younger age than adult-onset patients. There have been few randomized, placebo-controlled clinical trials of multiple sclerosis (MS) disease-modifying therapies (DMTs) in patients with POMS, and most available data are based on observational studies of off-label use of DMTs approved for adults. We assessed the effectiveness of natalizumab compared with fingolimod using injectable platform therapies as a reference in pediatric patients in the global MSBase registry. METHODS: This retrospective study included patients with POMS who initiated treatment with an injectable DMT, natalizumab, or fingolimod between January 1, 2006, and May 3, 2021. Patients were matched using inverse probability treatment weighting. The primary outcome was time to first relapse from index therapy initiation. Secondary study outcomes included annualized relapse rate; proportions of relapse-free patients at 1, 2, and 5 years; time to treatment discontinuation; and times to 24-week confirmed disability worsening and confirmed disability improvement. RESULTS: A total of 1,218 patients with POMS were included in this analysis. Patients treated with fingolimod had a significantly lower risk of relapse than patients treated with injectable DMTs (hazard ratio [HR], 0.49; 95% confidence interval [CI], 0.29-0.83; p = 0.008). After adjustment for prior DMT experience in the unmatched sample, patients treated with natalizumab had a significantly lower risk of relapse than patients treated either with injectable DMTs (HR, 0.15; 95% CI 0.07-0.31; p < 0.001) or fingolimod (HR, 0.37; 95% CI 0.14-1.00; p = 0.049). The adjusted secondary study outcomes were generally consistent with the primary outcome or with previous observations. The findings in the inverse probability treatment weighting-adjusted patient populations were confirmed in multiple sensitivity analyses. DISCUSSION: Our analyses of relapse risk suggest that natalizumab is more effective than fingolimod in the control of relapses in this population with high rates of new inflammatory activity, consistent with previous studies of natalizumab and fingolimod in adult-onset patients and POMS. In addition, both fingolimod and natalizumab were more effective than first-line injectable therapies. CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that patients with POMS treated with natalizumab had a lower risk of relapse than those with fingolimod.

Long-term clinical outcomes in patients with multiple sclerosis who are initiating disease-modifying therapy with natalizumab compared with BRACETD first-line therapies.

Background: Aggressive disease control soon after multiple sclerosis (MS) diagnosis may prevent irreversible neurological damage, and therefore early initiation of a high-efficacy disease-modifying therapy (DMT) is of clinical relevance. Objectives: Evaluate long-term clinical outcomes in patients with MS who initiated treatment with either natalizumab or a BRACETD therapy (interferon beta, glatiramer acetate, teriflunomide, or dimethyl fumarate). Design: This retrospective analysis utilized data from MSBase to create a matched population allowing comparison of first-line natalizumab to first-line BRACETD. Methods: This study included patients who initiated treatment either with natalizumab or a BRACETD DMT within 1 year of MS diagnosis and continued treatment for ⩾6 months, after which patients could switch DMTs or discontinue treatment. Patients had a minimum follow-up time of ⩾60 months from initiation. A subgroup analysis compared the natalizumab group to patients in the BRACETD group who escalated therapy after 6 months. Outcomes included unadjusted annualized relapse rates (ARRs), time-to-first relapse, time-to-first confirmed disability improvement (CDI), and time-to-first confirmed disability worsening (CDW). Results: After 1:1 propensity score matching, 355 BRACETD patients were matched to 355 natalizumab patients. Patients initiating natalizumab were less likely to experience a relapse over the duration of follow-up, with ARRs [95% confidence interval (CI)] of 0.080 (0.070-0.092) for natalizumab patients and 0.191 (0.178-0.205) for BRACETD patients (p < 0.0001). A Cox regression model of time-to-first relapse showed a reduced risk of relapse for natalizumab patients [hazard ratio (95% CI) of 0.52 (0.42-0.65); p < 0.001] and a more favorable time-to-first CDI. The risk of CDW was similar between groups. The subgroup analysis showed an increased relapse risk as well as a significantly higher risk of CDW for BRACETD patients. Conclusion: Early initiation of natalizumab produced long-term benefits in relapse outcomes in comparison with BRACETD, regardless of a subsequent escalation in therapy.

Emulating randomised clinical trials in relapsing-remitting multiple sclerosis with non-randomised real-world evidence: an application using data from the MSBase Registry.

BACKGROUND: To mimic as closely as possible a randomised controlled trial (RCT) and calibrate the real-world evidence (RWE) studies against a known treatment effect would be helpful to understand if RWE can support causal conclusions in selected circumstances. The aim was to emulate the TRANSFORMS trial comparing Fingolimod (FTY) versus intramuscular interferon ß-1a (IFN) using observational data. METHODS: We extracted from the MSBase registry all the patients with relapsing-remitting multiple sclerosis (RRMS) collected in the period 2011-2021 who received IFN or FTY (0.5 mg) and with the same inclusion and exclusion criteria of the TRANSFORMS RCT. The primary endpoint was the annualised relapse rate (ARR) over 12 months. Patients were 1:1 propensity-score (PS) matched. Relapse-rate ratio (RR) was calculated by mean of a negative binomial regression. RESULTS: A total of 4376 patients with RRMS (1140 in IFN and 3236 in FTY) were selected. After PS, 856 patients in each group were matched. The ARR was 0.45 in IFN and 0.25 in FTY with a significant difference between the two groups (RR: 0.55, 95% CI: 0.45 to 0.68; p<0.001). The result of the emulation was very similar and fell within the 95% CI of that observed in the RCT (RR: 0.49, 95% CI: 0.37 to 0.64; p<0.001) with a standardised difference of 0.66 (p=0.51). CONCLUSIONS: By applying the same inclusion and exclusion criteria used in the RCT and employing appropriate methodology, we successfully replicated the RCT results with only minor discrepancies. Also, even if the confounding bias cannot be fully eliminated, conducting a rigorous target trial emulation could still yield valuable insights for comparative effectiveness research.

Quantitative brain morphometry identifies cerebellar, cortical, and subcortical gray and white matter atrophy in late-onset Tay-Sachs disease.

Cerebellar atrophy is a characteristic sign of late-onset Tay-Sachs disease (LOTS). Other structural neuroimaging abnormalities are inconsistently reported. Our study aimed to perform a detailed whole-brain analysis and quantitatively characterize morphometric changes in LOTS patients. Fourteen patients (8 M/6F) with LOTS from three centers were included in this retrospective study. For morphometric brain analyses, we used deformation-based morphometry, voxel-based morphometry, surface-based morphometry, and spatially unbiased cerebellar atlas template. The quantitative whole-brain morphometric analysis confirmed the finding of profound pontocerebellar atrophy with most affected cerebellar lobules V and VI in LOTS patients. Additionally, the atrophy of structures mainly involved in motor control, including bilateral ventral and lateral thalamic nuclei, primary motor and sensory cortex, supplementary motor area, and white matter regions containing corticospinal tract, was present. The atrophy of the right amygdala, hippocampus, and regions of occipital, parietal and temporal white matter was also observed in LOTS patients in contrast with controls (p < 0.05, FWE corrected). Patients with dysarthria and those initially presenting with ataxia had more severe cerebellar atrophy. Our results show predominant impairment of cerebellar regions responsible for speech and hand motor function in LOTS patients. Widespread morphological changes of motor cortical and subcortical regions and tracts in white matter indicate abnormalities in central motor circuits likely coresponsible for impaired speech and motor function.

Predictors of treatment switching in the Big Multiple Sclerosis Data Network.

Background: Treatment switching is a common challenge and opportunity in real-world clinical practice. Increasing diversity in disease-modifying treatments (DMTs) has generated interest in the identification of reliable and robust predictors of treatment switching across different countries, DMTs, and time periods. Objective: The objective of this retrospective, observational study was to identify independent predictors of treatment switching in a population of relapsing-remitting MS (RRMS) patients in the Big Multiple Sclerosis Data Network of national clinical registries, including the Italian MS registry, the OFSEP of France, the Danish MS registry, the Swedish national MS registry, and the international MSBase Registry. Methods: In this cohort study, we merged information on 269,822 treatment episodes in 110,326 patients from 1997 to 2018 from five clinical registries. Patients were included in the final pooled analysis set if they had initiated at least one DMT during the relapsing-remitting MS (RRMS) stage. Patients not diagnosed with RRMS or RRMS patients not initiating DMT therapy during the RRMS phase were excluded from the analysis. The primary study outcome was treatment switching. A multilevel mixed-effects shared frailty time-to-event model was used to identify independent predictors of treatment switching. The contributing MS registry was included in the pooled analysis as a random effect. Results: Every one-point increase in the Expanded Disability Status Scale (EDSS) score at treatment start was associated with 1.08 times the rate of subsequent switching, adjusting for age, sex, and calendar year (adjusted hazard ratio [aHR] 1.08; 95% CI 1.07-1.08). Women were associated with 1.11 times the rate of switching relative to men (95% CI 1.08-1.14), whilst older age was also associated with an increased rate of treatment switching. DMTs started between 2007 and 2012 were associated with 2.48 times the rate of switching relative to DMTs that began between 1996 and 2006 (aHR 2.48; 95% CI 2.48-2.56). DMTs started from 2013 onwards were more likely to switch relative to the earlier treatment epoch (aHR 8.09; 95% CI 7.79-8.41; reference = 1996-2006). Conclusion: Switching between DMTs is associated with female sex, age, and disability at baseline and has increased in frequency considerably in recent years as more treatment options have become available. Consideration of a patient's individual risk and tolerance profile needs to be taken into account when selecting the most appropriate switch therapy from an expanding array of treatment choices.