Detecting features of epileptogenesis in EEG after TBI using unsupervised diffusion component analysis

Dominique Duncan; Paul Vespa; Arthur W. Toga

doi:10.3934/dcdsb.2018010

Article Contents

2018, Volume 23, Issue 1: 161-172. Doi: 10.3934/dcdsb.2018010

This issue Previous Article Sensitivity of combined chemo-and antiangiogenic therapy results in different models describing cancer growth Next Article A global inversion theorem for functions with singular points

Detecting features of epileptogenesis in EEG after TBI using unsupervised diffusion component analysis

1.
USC Stevens Neuroimaging and Informatics Institute, University of Southern California, 2025 Zonal Ave, Los Angeles, CA, 90033, USA
2.
Division of Neurosurgery and Department of Neurology, University of California at Los Angeles School of Medicine, 10833 LeConte Avenue, CHS 18-218, Los Angeles, CA, 90024, USA

* Corresponding author: Dominique Duncan
* Corresponding author: Dominique Duncan

Received: December 31, 2016

Published: November 2017

Abstract Full Text(HTML) Figure(8) Related Papers Cited by

Abstract

Epilepsy is among the most common serious disabling disorders of the brain, and the global burden of epilepsy exerts a tremendous cost to society. Most people with epilepsy have acquired forms, and the development of antiepileptogenic interventions could potentially prevent or cure these epilepsies [3,13]. The discovery of potential antiepileptogenic treatments is currently a high research priority. Clinical validation would require a means to identify populations of patients at particular high risk for epilepsy after a potential epileptogenic insult to know when to treat and to document prevention or cure. We investigate the development of post-traumatic epilepsy (PTE) following traumatic brain injury (TBI), because this condition offers the best opportunity to know the time of onset of epileptogenesis in patients. Epileptogenesis is common after TBI, and because much is known about the physical history of PTE, it represents a near-ideal human model in which to study the process of developing seizures.

Using scalp and depth EEG recordings for six patients, the goal of our analysis is to find a way to quantitatively detect features in the EEG that could potentially help predict seizure onset post trauma. Unsupervised Diffusion Component Analysis [5], a novel approach based on the diffusion mapping framework [4], reduces data dimensionality and provides pattern recognition that can be used to distinguish different states of the patient, such as seizures and non-seizure spikes in the EEG. This method is also adapted to the data to enable the extraction of the underlying brain activity. Previous work has shown that such techniques can be useful for seizure prediction [6].

Some new results that demonstrate how this algorithm is used to detect spikes in the EEG data as well as other changes over time are shown. This nonlinear and local network approach has been used to determine if the early occurrences of specific electrical features of epileptogenesis, such as interictal epileptiform activity and morphologic changes in spikes and seizures, during the initial week after TBI predicts the development of PTE.

Keywords:

Mathematics Subject Classification: 68T10, 65F15, 92B99, 92C20, 92C55, 00A69.

Citation:

Full Text(HTML)

Figure 1. Raw EEG data showing epileptiform spike activity at two time points

Download: Full-size image PowerPoint slide

Figure 2. The corresponding embedding using Unsupervised Diffusion Component Analysis and eigenvectors 2, 3, and 5

Download: Full-size image PowerPoint slide

Figure 3. An example of raw EEG data from 4 electrode contacts from 1 patient with epileptiform activity at one time point

Download: Full-size image PowerPoint slide

Figure 4. The corresponding embedding using Unsupervised Diffusion Component Analysis (color represents time), and the yellow/orange points are separated from the other embedded points

Download: Full-size image PowerPoint slide

Figure 5. An example of EEG data from 3 electrode contacts from another patient with more subtle spikes that are not clear from examining the raw data

Download: Full-size image PowerPoint slide

Figure 6. The corresponding embedding using Unsupervised Diffusion Component Analysis

Download: Full-size image PowerPoint slide

Figure 7. An example of raw EEG data from 3 electrode contacts from 1 patient with no epileptiform activity

Download: Full-size image PowerPoint slide

Figure 8. The corresponding embedding using Unsupervised Diffusion Component Analysis

Download: Full-size image PowerPoint slide

Related Papers

Cited by

References

	J. F. Annegers , W. A. Hauser , S. P. Coan and W. A. Rocca , A population-based study of seizures after traumatic brain injuries, N Engl J Med, 338 (1998) , 20-24.
	J. L. Arango , C. P. Deibert , D. Brown , M. Bell , I. Dvorchik and P. D. Adelson , Posttraumatic seizures in children with severe traumatic brain injury, Childs Nerv Syst, 28 (2012) , 1925-1929.
	C. E. Begley , M. Famulari and J. F. Annegers , The cost of epilepsy in the United States: An estimate from population-based clinical and survey data, Epilepsia, 41 (2000) , 342-351.
	R. R. Coifman and S. Lafon , Diffusion maps, Appl. Comp. Harm. Anal., 21 (2006) , 5-30. doi: 10.1016/j.acha.2006.04.006.
	D. Duncan and T. Strohmer , Classification of Alzheimer's disease using unsupervised diffusion component analysis, Math Biosci Eng, 13 (2016) , 1119-1130. doi: 10.3934/mbe.2016033.
	D. Duncan , R. Talmon , H. P. Zaveri and R. R. Coifman , Identifying preseizure state in intracranial EEG data using diffusion kernels, Math Biosci Eng, 10 (2013) , 579-590. doi: 10.3934/mbe.2013.10.579.
	R. Immonen , I. Kharatishvili , O. Gröhn and A. Pitkänen , MRI biomarkers for post-traumatic epileptogenesis, Journal of neurotrauma, 30 (2013) , 1305-1309.
	C. D. Lamar , R. A. Hurley , J. A. Rowland and K. H. Taber , Post-traumatic epilepsy: review of risks, pathophysiology, and potential biomarkers, J Neuropsychiatry Clin Neurosci, 26 (2014) , ⅳ-113.
	J. J. Lin , M. Mula and B. P. Hermann , Uncovering the neurobehavioural comorbidities of epilepsy over the lifespan, Lancet, 380 (2012) , 1180-1192.
	W. Loscher and C. Brandt , Prevention or modification of epileptogenesis after brain insults: experimental approaches and translational research, Pharmacol Rev, 62 (2010) , 668-700.
	E. S. Lutkenhoff , D. L. McArthur , X. Hua , P. M. Thompson , P. M. Vespa and M. M. Monti , Thalamic atrophy in antero-medial and dorsal nuclei correlates with six-month outcome after severe brain injury, Neuroimage Clin, 3 (2013) , 396-404.
	A. M. Mishra, X. Bai, B. G. Sanganahalli, S. G. Waxman, O. Shatillo, O. Grohn, F. Hyder, A. Pitkänen and H. Blumenfeld, Decreased resting functional connectivity after traumatic brain injury in the rat, PloS one, 9 (2014), e95280.
	C. J. L. Murray and A. D. Lopez, Global Comparative Assessment in the Health Sector; Disease Burden, Expenditures, and Intervention Packages, Geneva: World Health Organization, 1994.
	T. Ostergard , J. Sweet , D. Kusyk , E. Herring and J. Miller , Animal models of post-traumatic epilepsy. Journal of neuroscience methods, Journal of neuroscience methods, 272 (2016) , 50-55.
	R. Ottman , C. Barker-Cummings , C. L. Leibson , V. M. Vasoli , W. A. Hauser and J. R. Buchhalter , Validation of a brief screening instrument for the ascertainment of epilepsy, Epilepsia, 51 (2010) , 191-197.
	A. Y. Reid , A. Bragin , C. C. Giza , R. J. Staba and J. Engel , The progression of electrophysiologic abnormalities during epileptogenesis after experimental traumatic brain injury, Epilepsia, 47 (2016) , 1558-1567.
	Y. Rubner , C. Tomasi and L. J. Guibas , A metric for distributions with applications to image databases, IEEE 6th International Conference on Computer Vision, (1998) , 59-66.
	A. M. Salazar , B. Jabbari , S. C. Vance , J. Grafman , D. Amin and J. D. Dillon , Epilepsy after penetrating head injury. 1. Clinical correlates: A report of the Vietnam Head Injury Study, Neurology, 35 (1985) , 1406-1414.
	C. Syms, Principal components analysis, Elsevier, (2008), 2940-2949.
	J. P. Szaflarski , Y. Nazzal and L. E. Dreer , Post-traumatic epilepsy: Current and emerging treatment options, Neuropsychiatr Dis Treat, 10 (2014) , 1469-1477.
	R. Talmon and R. R. Coifman , Differential stochastic sensing: Intrinsic modeling of random time series with applications to nonlinear tracking, PNAS, (2012) , 1-14.
	R. Talmon , D. Kushnir , R. R. Coifman , I. Cohen and S. Gannot , Parametrization of linear systems using diffusion kernels, IEEE Transactions on Signal Processing, 60 (2012) , 1159-1173. doi: 10.1109/TSP.2011.2177973.
	R. Talmon , D. Kushnir , R. R. Coifman , I. Cohen and S. Gannot , Parametrization of linear systems using diffusion kernels, IEEE Trans. Signal Process, 60 (2012) , 1159-1173. doi: 10.1109/TSP.2011.2177973.
	P. M. Vespa , M. R. Nuwer , V. Nenov , E. Ronne-Engstrom , D. A. Hovda , N. A. Martin and D. P. Becker , Increased incidence and impact of nonconvulsive and convulsive seizures after traumatic brain injury as detected by continuous EEG in the intensive care unit, J Neurosurg, 91 (1999) , 750-760.
	P. M. Vespa, M. Tubi, J. Claassen, M. Blanco, D. McArthur, A. G. Velazquez, B. Tu, M. Prins and M. Nuwer, Metabolic Crisis Occurs with Seizures and Periodic Discharges after Brain Trauma, Ann Neurol, 2016.
	P. M. Vespa , D. L. McArthur , Y. Xu , M. Eliseo , M. Etchepare , I. Dinov , J. Alger , T. P. Glenn and D. Hovda , Nonconvulsive seizures after traumatic brain injury are associated with hippocampal atrophy, Ann Neurol, 75 (2010) , 792-798.