Meeting Banner
Abstract #2836

Cohort Stratification by Clinical Symptoms through Unsupervised Learning Reveals Metabolic and Microstructural Brain Alterations in Former American Football Players

Molly Faith Charney1, Janna Kochsiek2,3, Tyler C. Starr1, Michael Alosco4, Brett Martin4, Huijun Liao1, David Kaufmann2,3, Lauren J. O'Donnell5, Sylvain Bouix2, Fan Zhang5, Nikos Makris6, Martha Shenton2,7, Robert Stern4, Inga Koerte2,3, and Alexander P. Lin1

1Radiology, Brigham and Women's Hospital, Boston, MA, United States, 2Psychiatry Neuroimaging Laboratory, Brigham and Women's Hospital, Boston, MA, United States, 3Child and Adolescent Psychiatry, Ludwig-Maximilians-Universit├Ąt, Munich, Germany, 4Boston University, Boston, MA, United States, 5Laboratory of Mathematics in Imaging, Brigham and Women's Hospital, Boston, MA, United States, 6Massachusetts General Hospital, Boston, MA, United States, 7VA Boston Healthcare System, Brockton, MA, United States

Chronic Traumatic Encephalopathy (CTE) is a neurodegenerative disease associated with exposure to repetitive head impacts. This study aims to characterize the differing clinical presentations of CTE using MR Spectroscopy and Diffusion Tensor Imaging. Unsupervised Learning was first used to divide a cohort of former NFL players into sub-groups based on the degree of mood/behavior symptoms and cognitive impairment relative to controls. The neurometabolite concentrations and measures of diffusivity were then compared between the sub-groups. Athletes with increased mood/behavior symptoms showed alterations reflective of neuroinflammation, whereas the cognitive impairment sub-group showed more neuronal and structural alterations.

This abstract and the presentation materials are available to members only; a login is required.

Join Here