Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2016 Dec;24(12):2475-2480.
doi: 10.1002/oby.21652. Epub 2016 Nov 2.

Baseline Gray- And White-Matter Volume Predict Successful Weight Loss in the Elderly

Affiliations
Free PMC article

Baseline Gray- And White-Matter Volume Predict Successful Weight Loss in the Elderly

Fatemeh Mokhtari et al. Obesity (Silver Spring). .
Free PMC article

Abstract

Objective: The purpose of this study was to investigate whether structural brain phenotypes could be used to predict weight loss success following behavioral interventions in older adults with overweight or obesity and cardiometabolic dysfunction.

Methods: A support vector machine with a repeated random subsampling validation approach was used to classify participants into the upper and lower halves of the weight loss distribution following 18 months of a weight loss intervention. Predictions were based on baseline brain gray matter and white matter volume from 52 individuals who completed the intervention and a magnetic resonance imaging session.

Results: The support vector machine resulted in an average classification accuracy of 72.62% based on gray matter and white matter volume. A receiver operating characteristic analysis indicated that classification performance was robust based on an area under the curve of 0.82.

Conclusions: Findings suggest that baseline brain structure was able to predict weight loss success following 18 months of treatment. The identification of brain structure as a predictor of successful weight loss was an innovative approach to identifying phenotypes for responsiveness to intensive lifestyle interventions. This phenotype could prove useful in future research focusing on the tailoring of treatment for weight loss.

Conflict of interest statement

The authors declare that they have no conflict of interest.

Figures

Figure 1
Figure 1
Average ROC curves for GM, WM, and combined classifiers. The curves each represent the average from 100 repetitions of the analysis. To make the figure legible, error bars have not been included.
Figure 2
Figure 2
The discriminatory map for (a) GM and (b) WM classifier. The red and blue color maps indicate voxels with a corresponding positive and negative value, respectively. According to MNI template (2mm), the z coordination of the axial slices is -50, -32, -12, 10, 26, 40, 62 and 74, respectively.

Similar articles

See all similar articles

Cited by 2 articles

Feedback