Seizure Control

Model-Based Seizure Detection in Epilepsy


Epilepsy is a chronic neurological disorder that affects 60 million people worldwide with recurring abrupt and often severe seizures. About 40% of patients are medically refractory (i.e., do not respond to drug therapy) and this has raised great interest in closed-loop neural stimulation to suppress approaching seizures. The efficacy of this therapy critically depends on whether the electrical stimulus is administered close to the seizure origin (epileptogenic zone) and immediately prior to or at seizure onset. This requires algorithms to precisely localize the EZ and detect the seizure onset from intracranial EEG measurements.
Our program aims to develop computational tools for epileptogenic zone localization and seizure detection. In particular, we develop model-based tools and use multivariate variables estimated from intracranial EEG channels to clearly separate seizure and non-seizure states. Stochastic models capture the evolution of these statistics in each state and determine the probability of an incumbent seizure by identifying epileptogenic-specific signatures from the EEG measurements.  We also investigate optimization methods and feedback control approaches to detect the transition into a seizure state (seizure onset) from sequential EEG measurements.


NSF-EECS AWARDS 1346888 AND 1518672

“EAGER: Modeling Network Dynamics in the Epileptic Brain to Develop Translational Tools for Seizure Localization and Detection”








Publications produced as a result of this research

  1. Yaffe RB, Borger P, Megevand P, Groppe DM, Kramer MA, Chu CJ, Santaniello S, Meisel C, Mehta AD, Sarma SV (2015) “Physiology of Functional and Effective Networks in Epilepsy,” Clin. Neurophysiol., vol. 126(2):227-36. DOI: 10.1016/j.clinph.2014.09.009
  2. Burns SP, Santaniello S, Yaffe RB, Jouny CC, Crone NE, Bergey GK, Anderson WS, Sarma SV (2014) “Network Dynamics of the Epileptic Brain and the Influence of Seizure Focus,” Proc. Nat. Acad. Sci. USA, vol. 111(49):E5321-30. DOI: 10.1073/pnas.1401752111
  3. Santaniello S, Burns SP, Anderson WS, Sarma SV (2014) “An Optimal Control Approach to Seizure Detection in Drug-Resistant Epilepsy” in A Systems Theoretic Approach to Systems and Synthetic Biology I: Models and System Characterization (Kulkarni VV, Stan G-B, Raman K Eds.)., chapter 6, pp. 153-178. New York, NY: Springer. DOI: 10.1007/978-94-017-9041-3_6
  4. Hao S, Subramanian S, Jordan A, Santaniello S, Yaffe RB, Jouny CC, Bergey GK, Anderson WS, Sarma SV (2014) “Computing Network-based Features from Intracranial EEG Time Series Data: Application to Seizure Focus Localization,” 36th IEEE Annual Conference of the EMBS (EMBC). Chicago, IL, pp. 5821-5. DOI: 10.1109/EMBC.2014.6944949
  5. Burns SP, Santaniello S, Anderson WS, Sarma SV (2013) “State Dynamics of the Epileptic Brain,” 6th ASME Annual Dynamic Systems and Control Conference (DSCC). Palo Alto, CA, pp. V002T22A001 (7 pages). DOI: 10.1115/DSCC2013-3708
  6. Santaniello S, Sherman DL, Thakor NV, Eskandar EN, Sarma SV (2012) “Optimal Control-based Bayesian Detection of Clinical and Behavioral State Transitions,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 20(5):708-19. DOI: 10.1109/TNSRE.2012.2210246
  7. Santaniello S, Burns SP, Sarma SV (2012) “Automatic Seizure Onset Detection in Drug-Resistant Epilepsy: A Bayesian Optimal Solution,” 51st IEEE Conference on Decision and Control (CDC). Maui, HI, pp. 3189-94. DOI: 10.1109/CDC.2012.6426566
  8. Santaniello S, Burns SP, Golby AJ, Singer JM, Anderson WS, Sarma SV (2011) “Quickest Detection of Drug-Resistant Seizures: An Optimal Control Approach,” Epilepsy Behav., vol. 22(Suppl. 1):S49-60. DOI: 10.1016/j.yebeh.2011.08.041
  9. Santaniello S, Sherman D, Mirski M, Thakor N, Sarma SV (2011) “A Bayesian Framework for Analyzing iEEG Data from a Rat Model of Epilepsy,” 33rd IEEE Annual Conference of the EMBS (EMBC). Boston, MA, pp. 1435-8. DOI: 10.1109/IEMBS.2011.6090355
  10. Kang X, Sarma SV, Santaniello S, Schieber M, Thakor NV (2015) “Task-Independent Cognitive State Transition Detection from Cortical Neurons during 3D Reach-to-Grasp Movements,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 23(4):676-82. DOI: 10.1109/TNSRE.2015.2396495
  11. Santaniello S, Granite SJ, Sarma SV, Winslow RL (2014) “Computing Network-based Features from Physiological Time Series: Application to Sepsis Detection,” 36th IEEE Annual Conference of the EMBS (EMBC). Chicago, IL, pp. 3825-8. DOI: 10.1109/EMBC.2014.6944457

Undergraduate Senior Design projects supported by this research program

  1. Hassan S., Murphy P., von Paternos A., Schmidt P. (2017) A Diagnostic System for Overnight Automatic Epileptogenic Zone Localization.
  2. Colberg A., Mierzejewski J., Newman R., Novikov E., Romero J. (2016) A Microcontroller-Based System for Real Time Seizure Onset Detection.