Format

Send to

Choose Destination
PLoS One. 2013 Nov 25;8(11):e78824. doi: 10.1371/journal.pone.0078824. eCollection 2013.

A machine learning approach to automated structural network analysis: application to neonatal encephalopathy.

Author information

1
Department of Radiology & Biomedical Imaging, University of California San Francisco, San Francisco, California, United States of America.

Abstract

Neonatal encephalopathy represents a heterogeneous group of conditions associated with life-long developmental disabilities and neurological deficits. Clinical measures and current anatomic brain imaging remain inadequate predictors of outcome in children with neonatal encephalopathy. Some studies have suggested that brain development and, therefore, brain connectivity may be altered in the subgroup of patients who subsequently go on to develop clinically significant neurological abnormalities. Large-scale structural brain connectivity networks constructed using diffusion tractography have been posited to reflect organizational differences in white matter architecture at the mesoscale, and thus offer a unique tool for characterizing brain development in patients with neonatal encephalopathy. In this manuscript we use diffusion tractography to construct structural networks for a cohort of patients with neonatal encephalopathy. We systematically map these networks to a high-dimensional space and then apply standard machine learning algorithms to predict neurological outcome in the cohort. Using nested cross-validation we demonstrate high prediction accuracy that is both statistically significant and robust over a broad range of thresholds. Our algorithm offers a novel tool to evaluate neonates at risk for developing neurological deficit. The described approach can be applied to any brain pathology that affects structural connectivity.

PMID:
24282501
PMCID:
PMC3840059
DOI:
10.1371/journal.pone.0078824
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Public Library of Science Icon for PubMed Central
Loading ...
Support Center