Abstract Details

Title Relationship of Superficial White Matter Integrity and Cognition in Early MS: A Machine Learning Study

Topic Multiple Sclerosis

Presentation(s) P18 - Poster Session 18 (5:30 PM-6:30 PM)

Poster/Presentation
Number 12-010

Background

SWM is a brain compartment located between cortex and deep white matter (DWM) primarily comprised of short association/U-fibers. These fibers constitute the vast majority of cortico-cortical connections in the human brain. Contribution of SWM integrity to cognition in MS has not been studied using diffusion tensor imaging.

Objective

To investigate the relationship between superficial white matter (SWM) integrity and cognitive performance in early multiple sclerosis (MS).

Design/Methods Fractional anisotropy (FA) and mean diffusivity (MD) values from 100 SWM bundles across the cortex and major DWM tracts were extracted from 28 patients early in disease course (mean disease duration=2.1 years) and 31 age- and sex-matched healthy controls (HC). In addition, thickness of 68 cortical regions (CT) and resting-state-functional-connectivity (RSFC) among them were calculated. Using linear regression with elastic-net regularization, latent cognitive variables (Nonverbal Memory, Verbal Memory, Language, and Speed) were predicted in 5 models based on: 1-SWM, 2-DWM, 3-SWM and DWM, 4-CT, and 5-RSFC measures for MS and HC groups separately. In a final model, all features from previous models were concatenated. Pearson’s correlation (r) was calculated to assess the prediction performance of each model.

Results In all models, language scores were predicted with higher accuracy compared to other cognitive domains in the MS group (r>0.5 for all models). In HC, highest performance was observed in CT model predicting non-verbal memory (r=0.51). In MS patients, the SWM and DWM models predicted language scores with the highest accuracy (r=0.61 and 0.58 respectively). RSFC and CT models provided lower r values compared to SWM (r=0.56 and 0.53 respectively, p<0.05 for all comparisons).

Conclusions

SWM integrity was the best single neuroimaging metric predicting language performance in early MS. Consideration of SWM integrity as a sensitive and specific marker of language function in early MS may inform mechanistic models. Larger samples are warranted to replicate and extend these findings.

Authors/Disclosures
Korhan Buyukturkoglu, PhD (Columbia University) PRESENTER	Dr. Buyukturkoglu has nothing to disclose.
Ceren Tozlu	No disclosure on file
	No disclosure on file
	No disclosure on file
	No disclosure on file
Amy Kuceyeski, PhD (Weill Cornell Medical College, Radiology)	An immediate family member of Dr. Kuceyeski has received personal compensation for serving as an employee of Heyer Physical Therapy. The institution of Dr. Kuceyeski has received research support from National Institutes of Health. Dr. Kuceyeski has received personal compensation in the range of $500-$4,999 for serving as a Grant Panel Member with Department of Defense.
James F. Sumowski (Icahn School of Medicine At Mount Sinai)	Mr. Sumowski has nothing to disclose.
Carlos Guevara Oliva, MD (Chile University)	Dr. Guevara Oliva has nothing to disclose.
	No disclosure on file
Claire Riley, MD, FAAN (Columbia University Medical Center)	Dr. Riley has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Genentech. Dr. Riley has received personal compensation in the range of $10,000-$49,999 for serving on a Scientific Advisory or Data Safety Monitoring board for EMD Serono. Dr. Riley has received personal compensation in the range of $10,000-$49,999 for serving on a Scientific Advisory or Data Safety Monitoring board for TG Therapeutics. Dr. Riley has received personal compensation in the range of $10,000-$49,999 for serving on a Scientific Advisory or Data Safety Monitoring board for Horizon. Dr. Riley has received personal compensation in the range of $500-$4,999 for serving on a Scientific Advisory or Data Safety Monitoring board for Novartis. Dr. Riley has received personal compensation in the range of $500-$4,999 for serving on a Scientific Advisory or Data Safety Monitoring board for Viracta. Dr. Riley has received personal compensation in the range of $500-$4,999 for serving on a Scientific Advisory or Data Safety Monitoring board for TG Therapeutics.
	No disclosure on file
Victoria Leavitt, PhD, FAAN (Columbia University Irving Medical Center)	Dr. Leavitt has received personal compensation in the range of $500-$4,999 for serving on a Scientific Advisory or Data Safety Monitoring board for Biogen. Dr. Leavitt has received personal compensation in the range of $500-$4,999 for serving on a Speakers Bureau for Novartis. The institution of Dr. Leavitt has received research support from National Institutes of Health. The institution of Dr. Leavitt has received research support from National Multiple Sclerosis Society. The institution of Dr. Leavitt has received research support from Department of Defense. Dr. Leavitt has received intellectual property interests from a discovery or technology relating to health care.