Prediction of individual brain maturity using fMRI
Nico U F Dosenbach1, Binyam Nardos, Alexander L Cohen
1Department of Neurology, Washington University School of Medicine, St. Louis, MO 63110, USA. ndosenbach@wustl.edu
Science (New York, N.Y.)
|September 11, 2010
Summary
Functional connectivity magnetic resonance imaging (fcMRI) accurately predicts brain maturity in individuals aged 7-30. This brain development prediction relies on changes in short-range functional connections.
Area of Science:
- Neuroscience
- Developmental Neuroscience
- Brain Imaging
Background:
- Group functional connectivity magnetic resonance imaging (fcMRI) studies reveal developmental changes in brain maturity.
- Understanding individual brain maturation is crucial for developmental neuroscience.
Purpose of the Study:
- To investigate if multivariate pattern analysis of fcMRI data can accurately predict individual brain maturity across development.
- To identify key functional connectivity changes associated with brain maturation.
Main Methods:
- Utilized support vector machine-based multivariate pattern analysis on resting-state fcMRI data.
- Analyzed 238 scans from typically developing volunteers aged 7 to 30 years.
- Focused on 5-minute resting-state fcMRI data acquisition.
Main Results:
- Accurate predictions of individual brain maturity were achieved using fcMRI data.
- A functional connectivity maturation index was developed, explaining 55% of sample variance.
- The maturation curve followed a nonlinear asymptotic growth pattern.
- Weakening of short-range functional connections between major brain networks was the strongest predictor.
Conclusions:
- fcMRI data, analyzed with machine learning, can reliably predict individual brain maturity.
- This approach offers a sensitive measure of neurodevelopmental trajectories.
- Changes in functional connectivity, particularly short-range connections, are key indicators of brain maturation.
