The clinico-radiological paradox of cognitive function and MRI burden of white matter lesions in people with multiple sclerosis: A systematic review and meta-analysis

Abstract

Background: Moderate correlation exists between the imaging quantification of brain white matter lesions and cognitive performance in people with multiple sclerosis (MS). This may reflect the greater importance of other features, including subvisible pathology, or methodological limitations of the primary literature.

Objectives: To summarise the cognitive clinico-radiological paradox and explore the potential methodological factors that could influence the assessment of this relationship.

Methods: Systematic review and meta-analysis of primary research relating cognitive function to white matter lesion burden.

Results: Fifty papers met eligibility criteria for review, and meta-analysis of overall results was possible in thirty-two (2050 participants). Aggregate correlation between cognition and T2 lesion burden was r = -0.30 (95% confidence interval: -0.34, -0.26). Wide methodological variability was seen, particularly related to key factors in the cognitive data capture and image analysis techniques.

Conclusions: Resolving the persistent clinico-radiological paradox will likely require simultaneous evaluation of multiple components of the complex pathology using optimum measurement techniques for both cognitive and MRI feature quantification. We recommend a consensus initiative to support common standards for image analysis in MS, enabling benchmarking while also supporting ongoing innovation.

Fig 1. Flowchart showing articles retrieved and considered at each stage of the review process.

Fig 2. Showing factors relevant to study quality including histograms of a) numbers of participants with MS in individual studies and b) overall quality scores, and c) the reporting of individual factors contributing to the overall quality score.

Fig 3. Forest plot of the individual studies showing their effect sizes as correlation coefficients.

Box sizes are inversely proportional to study variance. Manuscripts reporting “non-significant” results without a point estimate are represented by circles. Aggregate effect size: r = -0.30; 95% confidence interval: -0.34, -0.26.