Single-subject level inference for volumetry features in mild traumatic brain injury using machine learning methods
Venkata Veerendranadh Chebrolu1, Tianhao Zhang2, Hariharan Ravishankar1, Sumit Niogi3, John A Tsiouris3, and Luca Marinelli4
1GE Global Research, Bangalore, India, 2GE Healthcare, Waukesha, WI, United States, 3Weill Cornell Medical Center, New York, NY, United States, 4GE Global Research, Niskayuna, NY, United States
The purpose of this work is to derive single-subject level
inferences for volumetry features in mild traumatic brain injury (mTBI) at
multiple time points after initial trauma using machine learning methods. 78
uncomplicated mTBI subjects were scanned three days (32 subjects), seven days
(61 subjects), one month (56) and three months (42 subjects) post injury to
derive volumetery features. 23 controls were also scanned. Logistic-regression
models were used to identify important volumetry features that jointly describe
the mTBI effects at single-subject level. Pallidus, supratentorial and whole-brain
volumetry features together provide single-subject level signature for mTBI at
multiple time-points after injury.
This abstract and the presentation materials are available to members only;
a login is required.
