Short-term MRI measurements as predictors of EDSS progression in relapsing-remitting multiple sclerosis: grey matter atrophy but not lesions are predictive in a real-life setting

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.

Prognosis in meningoencephalitis of unknown origin in dogs: Risk factors associated with survival, clinical relapse, and long-term disability

BACKGROUND

Meningoencephalitis of unknown origin (MUO) comprises a group of noninfectious inflammatory diseases affecting the central nervous system of dogs. Previous studies have reported individual risk factors for survival but prognostication for MUO remains challenging.

OBJECTIVES

Identify clinical prognostic variables in dogs with MUO.

ANIMALS

A retrospective study of 447 dogs presented to 2 UK referral hospitals and diagnosed with MUO.

METHODS

Medical records of dogs diagnosed with MUO were retrospectively reviewed. Multivariable logistic regression was used for the identification of risk factors for survival and Cox proportional hazards analysis for the identification of risk factors for clinical relapse.

RESULTS

Eighty-two percent (366/447) of dogs with presumptive MUO survived to discharge and 63.5% (284/447) were alive at 6 months; 36% of the latter (103/284) had persistent neurological deficits. Breed (pugs; P = .03), epileptic seizures (P < .001), paresis (P < .001), and higher neurodisability scale (NDS) score (P < .001) at presentation were negatively associated with survival to 6 months. Dogs with persistent deficits had higher NDS scores on presentation (P = .001). Median follow-up time was 11 months (interquartile range [IQR], 1-24) and 50.6% (160/316) relapsed during treatment (median time to relapse, 7 months; IQR, 2-15). Incomplete resolution of the clinical signs during the 6 months after diagnosis (P < .001), higher NDS score (P < .001), and longer duration of the clinical signs (P < .001) were associated with relapse.

CONCLUSIONS AND CLINICAL IMPORTANCE

Knowledge of risk factors associated with survival, incomplete recovery and clinical relapse in MUO can help guide monitoring and treatment and improve owner communications regarding prognosis for this debilitating disease.

Magnetic Resonance Imaging as a Prognostic Disability Marker in Clinically Isolated Syndrome and Multiple Sclerosis: A Systematic Review and Meta-Analysis

To date, there are no definite imaging predictors for long-term disability in multiple sclerosis (MS). Magnetic resonance imaging (MRI) is the key prognostic tool for MS, primarily at the early stage of the disease. Recent findings showed that white matter lesion (WML) counts and volumes could predict long-term disability for MS. However, the prognostic value of MRI in the early stage of the disease and its link to long-term physical disability have not been assessed systematically and quantitatively. A meta-analysis was conducted using studies from four databases to assess whether MS lesion counts and volumes at baseline MRI scans could predict long-term disability, assessed by the expanded disability status scale (EDSS). Fifteen studies were eligible for the qualitative analysis and three studies for meta-analysis. T2 brain lesion counts and volumes after the disease onset were associated with disability progression after 10 years. Four or more lesions at baseline showed a highly significant association with EDSS 3 and EDSS 6, with a pooled OR of 4.10 and 4.3, respectively. The risk increased when more than 10 lesions were present. This review and meta-analysis confirmed that lesion counts and volumes could be associated with disability and might offer additional valid guidance in treatment decision making. Future work is essential to determine whether these prognostic markers have high predictive potential.

Cortical fractal dimension predicts disability worsening in Multiple Sclerosis patients

BACKGROUND

Fractal geometry measures the morphology of the brain and detects CNS damage. We aimed to assess the longitudinal changes on brain's fractal geometry and its predictive value for disease worsening in patients with Multiple Sclerosis (MS).

METHODS

We prospectively analyzed 146 consecutive patients with relapsing-remitting MS with up to 5 years of clinical and brain MRI (3 T) assessments. The fractal dimension and lacunarity were calculated for brain regions using box-counting methods. Longitudinal changes were analyzed in mixed-effect models and the risk of disability accumulation were assessed using Cox Proportional Hazard regression analysis.

RESULTS

There was a significant decrease in the fractal dimension and increases of lacunarity in different brain regions over the 5-year follow-up. Lower cortical fractal dimension increased the risk of disability accumulation for the Expanded Disability Status Scale [HR 0.9734, CI 0.8420-0.9125; Harrell C 0.59; Wald p 0.038], 9-hole peg test [HR 0.9734, CI 0.8420-0.9125; Harrell C 0.59; Wald p 0.0083], 2.5% low contrast vision [HR 0.4311, CI 0.2035-0.9133; Harrell C 0.58; Wald p 0.0403], symbol digit modality test [HR 2.215, CI 1.043-4.705; Harrell C 0.65; Wald p 0.0384] and MS Functional Composite-4 [HR 0.55, CI 0.317-0.955; Harrell C 0.59; Wald p 0.0029].

CONCLUSIONS

Fractal geometry analysis of brain MRI identified patients at risk of increasing their disability in the next five years.

The feasibility of assessing cognitive and motor function in multiple sclerosis patients using robotics

Background

Multiple sclerosis (MS) causes pervasive motor, sensory and cognitive dysfunction. The Expanded Disability Status Scale (EDSS) is the gold standard for assessing MS disability. The EDSS is biased towards mobility and may not accurately measure MS-related disabilities in the upper limb or in cognitive functions (e.g. executive function).

Objective

Our objectives were to determine the feasibility of using the Kinarm robotic system to quantify neurological deficits related to arm function and cognition in MS patients, and examine relationships between traditional clinical assessments and Kinarm variables.

Methods

Individuals with MS performed 8 robotic tasks assessing motor, cognitive, and sensory ability. We additionally collected traditional clinical assessments and compared these to the results of the robotic assessment.

Results

Forty-three people with MS were assessed. Most participants could complete the robotic assessment. Twenty-six (60%) were impaired on at least one cognitive task and twenty-six (60%) were impaired on at least one upper-limb motor task. Cognitive domain task performance correlated most strongly with the EDSS.

Conclusions

Kinarm robotic assessment of people with MS is feasible, can identify a broad range of upper-limb motor and sensory, as well as cognitive, impairments, and complements current clinical rating scales in the assessment of MS-related disability.

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.

Does CSF pleocytosis have a predictive value for disease course in MS?

Objective

MS is a demyelinating CNS disorder with a spectrum of clinical patterns regarding course and prognosis. Although several prognostic factors are considered in the initial evaluation of patients, biological markers defining the disease course and guiding treatments are currently lacking. It is unknown whether patients with CSF pleocytosis differ in regard to symptoms, disease course, and prognosis from those without. The aim of this study was to evaluate whether CSF pleocytosis during the initial presentation has an impact on the clinical course and progression of MS.

Methods

We retrospectively evaluated patients attending the MS Clinic at Rabin Medical Center between January 1999 and January 2016 who underwent lumbar puncture (LP) at disease presentation, considering CSF cell count, clinical diagnosis (clinically isolated syndrome [CIS] and relapsing-remitting MS [RRMS]), annualized relapse rate (ARR), paraclinical findings (imaging, CSF oligoclonal bands, and evoked potentials), and disease progression, expressed by the Expanded Disability Status Scale (EDSS).

Results

One hundred fourteen patients (72 females) underwent LP at disease presentation (RRMS: n = 100, CIS: n = 14). Age at diagnosis was 32.4 ± 12.2 years, and the follow-up time was 9.4 ± 3.8 years. Forty-six patients showed a pleocytic CSF (≥5 cells per μL). Compared with patients with <4 cells per μL, patients with pleocytosis had a higher ARR (0.60 ± 0.09 vs 0.48 ± 0.04; p = 0.0267) and a steeper increase (slope) in the EDSS score throughout the follow-up period (correlation coefficient: r2 = 0.04; p = 0.0251).

Conclusions

CSF pleocytosis may be considered a biological unfavorable predictive factor regarding disease course and progression in MS.

Brazilian Consensus for the Treatment of Multiple Sclerosis: Brazilian Academy of Neurology and Brazilian Committee on Treatment and Research in Multiple Sclerosis

The expanding therapeutic arsenal in multiple sclerosis (MS) has allowed for more effective and personalized treatment, but the choice and management of disease-modifying therapies (DMTs) is becoming increasingly complex. In this context, experts from the Brazilian Committee on Treatment and Research in Multiple Sclerosis and the Neuroimmunology Scientific Department of the Brazilian Academy of Neurology have convened to establish this Brazilian Consensus for the Treatment of MS, based on their understanding that neurologists should be able to prescribe MS DMTs according to what is better for each patient, based on up-to-date evidence and practice. We herein propose practical recommendations for the treatment of MS, with the main focus on the choice and management of DMTs, as well as present a review of the scientific rationale supporting therapeutic strategies in MS.

MRI phenotypes in MS: Longitudinal changes and miRNA signatures

Objective

To classify and immunologically characterize persons with MS based on brain lesions and atrophy and their associated microRNA profiles.

Methods

Cerebral T2-hyperintense lesion volume (T2LV) and brain parenchymal fraction (BPF) were quantified and used to define MRI phenotypes as follows: type I: low T2LV, low atrophy; type II: high T2LV, low atrophy; type III: low T2LV, high atrophy; type IV: high T2LV, high atrophy, in a large cross-sectional cohort (n = 1,088) and a subset with 5-year lngitudinal follow-up (n = 153). Serum miRNAs were assessed on a third MS cohort with 2-year MRI phenotype stability (n = 98).

Results

One-third of the patients had lesion-atrophy dissociation (types II or III) in both the cross-sectional and longitudinal cohorts. At 5 years, all phenotypes had progressive atrophy (p < 0.001), disproportionally in type II (BPF -2.28%). Only type IV worsened in physical disability. Types I and II showed a 5-year MRI phenotype conversion rate of 33% and 46%, whereas III and IV had >90% stability. Type II switched primarily to IV (91%); type I switched primarily to II (47%) or III (37%). Baseline higher age (p = 0.006) and lower BPF (p < 0.001) predicted 5-year phenotype conversion. Each MRI phenotype demonstrated an miRNA signature whose underlying biology implicates blood-brain barrier pathology: hsa.miR.22.3p, hsa.miR.361.5p, and hsa.miR.345.5p were the most valid differentiators of MRI phenotypes.

Conclusions

MRI-defined MS phenotypes show high conversion rates characterized by the continuation of either predominant neurodegeneration or inflammation and support the partial independence of these 2 measures. MicroRNA signatures of these phenotypes suggest a role for blood-brain barrier integrity.

Magnetic resonance imaging as a prognostic disability marker in clinically isolated syndrome: A systematic review

Magnetic resonance imaging (MRI) is the key prognostic tool in people with a clinically isolated syndrome (CIS). There is increasing interest in treating people following a CIS in the hope that conversion to multiple sclerosis (MS) will be prevented and future disability reduced. So far, the prognostic value of MRI for disability following a CIS has not been evaluated systematically. We systematically searched MEDLINE and EMBASE. Cohort studies were selected if they reported associations of MRI and disability following a CIS, included at least 50 people with a CIS at baseline, had at least 5 years of follow-up and obtained at least one structural MRI measurement (T1 lesions, T2 lesions, T1 contrast-enhancing lesions or brain atrophy). We assessed the studies for quality and rated the completeness of MRI reporting. In total, 13 studies were identified reporting on the following: T2 lesion number and volume, T2 infratentorial lesion number and volume, T1 contrast-enhancing lesions and grey matter fraction. T2 brain lesion number determined soon after the occurrence of a CIS was associated with disability progression after 5-7 years, with an increased risk when 10 or more lesions were present. Infratentorial lesions were also associated with a higher risk of subsequent disability. The number and distribution of MRI-visible lesions soon after a CIS are associated with disability later on, and may offer additional useful information when making treatment decisions in people with early MS. Further work is required to determine whether other measures have a higher predictive potential.