Brain MRI Predicts Worsening Multiple Sclerosis Disability over 5 Years in the SUMMIT Study

Bakshi, Rohit; Healy, Brian C.; Dupuy, Sheena L.; Kirkish, Gina; Khalid, Fariha; Gundel, Tristan J; Asteggiano, Carlo; Yousuf, Fawad; Alexander, Amber; Weiner, Howard L.; Henry, Roland G.

doi:10.1111/jon.12688

Cited by 11 publications

(14 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cognitive batteries are usually complex and time consuming 11 . Similarly, imaging markers of axonal loss that use non-conventional sequences require expertise for their interpretation, which is not always available in most treatment centers 12,13 . The corpus callosum is the largest axonal interhemispheric brain connection.…”

Section: Discussionmentioning

confidence: 99%

“Stable” vs. “silent progressive multiple sclerosis”: a real-world retrospective clinical imaging Brazilian study

Figueira¹,

SOARES²,

Silveira³

et al. 2022

Arq. Neuro-Psiquiatr.

View full text Add to dashboard Cite

Background: Clinical and imaging are required to characterize activity and progression in MS. The parameters for activity are well defined but not those for progression. The ideal aim for long-term treatment is that neither clinical nor imaging signs of disease should be present, and also no brain atrophy. Objectives: To conduct a comparative clinical-imaging study focusing on MRI brain volumetry. Methods: 174 consecutive relapsing-remitting MS patients (McDonald 2001) were studied, focusing on activity and progression. Annual clinical evaluations (relapse rate and EDSS) and MRI data, along with the annualized evolution of the corpus callosum index (CCI), were compared. Results: Out of 174 patients, 148 were considered clinically “stable” based on EDSS. However, 33 (22.2%) out of this group showed annualized reductions in CCI of more than 0.5%, which was the cutoff for defining significant brain atrophy. Conclusions: Among apparently “stable” relapsing-remitting MS patients, 1/5 showed significant brain atrophy over a follow-up period of at least 7 years. We consider it reasonable to suggest that MRI volume sequences should be included in follow-up protocols, so as to provide information on the real treatment response status.

show abstract

Section: Discussionmentioning

confidence: 99%

“Stable” vs. “silent progressive multiple sclerosis”: a real-world retrospective clinical imaging Brazilian study

Figueira¹,

SOARES²,

Silveira³

et al. 2022

Arq. Neuro-Psiquiatr.

View full text Add to dashboard Cite

show abstract

“…This underlines how our result can help physicians in selecting those patients that can benefit from an early and more efficacy therapy. A recent study by Bakshi and colleagues found that baseline brain parenchymal fraction, but not T2LL, may be a good predictor of 5-year disability worsening [ 35 ]. A possible explanation to this discrepancy could be researched in the different clinical endpoint.…”

Section: Discussionmentioning

confidence: 99%

Machine learning classifier to identify clinical and radiological features relevant to disability progression in multiple sclerosis

et al. 2021

View full text Add to dashboard Cite

Objectives To evaluate the accuracy of a data-driven approach, such as machine learning classification, in predicting disability progression in MS. Methods We analyzed structural brain images of 163 subjects diagnosed with MS acquired at two different sites. Participants were followed up for 2–6 years, with disability progression defined according to the expanded disability status scale (EDSS) increment at follow-up. T2-weighted lesion load (T2LL), thalamic and cerebellar gray matter (GM) volumes, fractional anisotropy of the normal appearing white matter were calculated at baseline and included in supervised machine learning classifiers. Age, sex, phenotype, EDSS at baseline, therapy and time to follow-up period were also included. Classes were labeled as stable or progressed disability. Participants were randomly chosen from both sites to build a sample including 50% patients showing disability progression and 50% patients being stable. One-thousand machine learning classifiers were applied to the resulting sample, and after testing for overfitting, classifier confusion matrix, relative metrics and feature importance were evaluated. Results At follow-up, 36% of participants showed disability progression. The classifier with the highest resulting metrics had accuracy of 0.79, area under the true positive versus false positive rates curve of 0.81, sensitivity of 0.90 and specificity of 0.71. T2LL, thalamic volume, disability at baseline and administered therapy were identified as important features in predicting disability progression. Classifiers built on radiological features had higher accuracy than those built on clinical features. Conclusions Disability progression in MS may be predicted via machine learning classifiers, mostly evaluating neuroradiological features.

show abstract

“…33 Last, baseline whole-brain volume was the only predictor of disability progression in a recent study from the Serially Unified Multicenter MS Investigation consortium. 34 Because it was shown that the rate of brain atrophy is slower in patients with MS with benign disease 35 and to avoid a potential bias within the 3 disability status groups, we calculated the proportion of patients with benign MS according to the definition based on EDSS and disease duration (EDSS #3.0 and disease duration $15 years). 29 Surprisingly, we found that the disability progression group had a larger proportion of patients with MS with benign disease at baseline (18.7%) compared with 7.9% of patients with MS with benign disease in the disability improvement and 15.2% in the stable groups, respectively.…”

Section: Discussionmentioning

confidence: 99%

Disability Improvement Is Associated with Less Brain Atrophy Development in Multiple Sclerosis

Ghione¹,

Bergsland

Dwyer

et al. 2020

AJNR Am J Neuroradiol

View full text Add to dashboard Cite

BACKGROUND AND PURPOSE: It is unknown whether deceleration of brain atrophy is associated with disability improvement in patients with MS. Our aim was to investigate whether patients with MS with disability improvement develop less brain atrophy compared with those who progress in disability or remain stable. MATERIALS AND METHODS:We followed 980 patients with MS for a mean of 4.8 6 2.4 years. Subjects were divided into 3 groups: progress in disability (n ¼ 241, 24.6%), disability improvement (n ¼ 101, 10.3%), and stable (n ¼ 638, 65.1%) at follow-up. Disability improvement and progress in disability were defined on the basis of the Expanded Disability Status Scale score change using standardized guidelines. Stable was defined as nonoccurrence of progress in disability or disability improvement. Normalized whole-brain volume was calculated using SIENAX on 3D T1WI, whereas the lateral ventricle was measured using NeuroSTREAM on 2D-T2-FLAIR images. The percentage brain volume change and percentage lateral ventricle volume change were calculated using SIENA and NeuroSTREAM, respectively. Differences among groups were investigated using ANCOVA, adjusted for age at first MR imaging, race, T2 lesion volume, and corresponding baseline structural volume and the Expanded Disability Status Scale.RESULTS: At first MR imaging, there were no differences among progress in disability, disability improvement, and the stable groups in whole-brain volume (P ¼ .71) or lateral ventricle volume (P ¼ .74). During follow-up, patients with disability improvement had the lowest annualized percentage lateral ventricle volume change (1.6% 6 2.7%) followed by patients who were stable (2.1% 6 3.7%) and had progress in disability (4.1% 6 5.5%), respectively (P , .001). The annualized percentage brain volume change values were À0.7% 6 0.7% for disability improvement, À0.8% 6 0.7% for stable, and À1.1% 6 1.1% for progress in disability (P ¼ .001). CONCLUSIONS:Patients with MS who improve in their clinical disability develop less brain atrophy across time compared with those who progress. ABBREVIATIONS: DMT ¼ disease-modifying therapies; EDSS ¼ Expanded Disability Status Scale; LVV ¼ lateral ventricle volume; PBVC ¼ percentage brain volume change; PLVVC ¼ percentage lateral ventricle volume change; PP ¼ primary-progressive; RR ¼ relapsing-remitting; SP ¼ secondary-progressive; T2-LV ¼ T2 lesion volume M S is an autoimmune disease of the central nervous system characterized by focal and diffuse inflammation 1 and neurodegeneration that presents with central, peripheral, and regional brain atrophy. 2,3 Brain atrophy measurement is one of the key biomarkers in MS 4,5 because it can be assessed in vivo by MR imaging. Brain atrophy is accelerated in patients with MS,6 persists during the course of the disease, and is clinically meaningful since the earliest disease stages. 7 Brain atrophy is related to short-and long-term physical and cognitive clinical deterioration, more robust than other measures of disease burden and lesion activity. 5,8,9

show abstract

Brain MRI Predicts Worsening Multiple Sclerosis Disability over 5 Years in the SUMMIT Study

Cited by 11 publications

References 39 publications

“Stable” vs. “silent progressive multiple sclerosis”: a real-world retrospective clinical imaging Brazilian study

“Stable” vs. “silent progressive multiple sclerosis”: a real-world retrospective clinical imaging Brazilian study

Machine learning classifier to identify clinical and radiological features relevant to disability progression in multiple sclerosis

Disability Improvement Is Associated with Less Brain Atrophy Development in Multiple Sclerosis

Contact Info

Product

Resources

About