Abstract #4757
Predicting stroke severity with structural connectivity network disruption as measured with the Network Modification (NeMo) Tool
Amy Kuceyeski 1 , Mark Villanueva 2 , Ashish Raj 1 , Michael O'Dell 2 , and Joan Toglia 3
1
Radiology, Weill Cornell Medical College,
New York, NY, United States,
2
Rehabilitation
Medicine, Weill Cornell Medical College, New York, NY,
United States,
3
Occupational
Therapy, Mercy College, NY, United States
The Network Modification (NeMo) Tool quantifies losses
in the brain connectivity network by mapping areas of
damage onto a large collection of healthy tractograms.
This allows for a clinically feasible method for
identifying areas that are most affected by loss of
connectivity due to stroke, which can provide insight as
to type and severity of functional loss. Here we
hypothesized the NeMo Tools measure of connectivity
disruption could better predict stroke severity,
measured with NIHSS, than lesion volume. Our partial
least squares regression model predicted NIHSS from
baseline disconnection with accuracy of R
2
=0.75,
while correlation with lesion volume was R
2
=0.28.
This abstract and the presentation materials are available to members only;
a login is required.
Join Here
