Relevant for Research Area

C - Applications


Presurgical investigations of patients with focal epilepsy using intracranial recordings at the Epi-lepsy Center offer a unique chance to evaluate a setup of the key modules essential for closed loop intervention in the human. Strategies for online seizure detection can be adapted to individ-ual seizure and background patters as recorded with intracranial electrodes to test and optimize the performance of various detection algorithms, preselecting best performing algorithms and training of classifiers for early seizure detection. During a brief late phase of the recordings pre-ceding electrode explantation, when clinical diagnosis is finished, this system can be tested under real life conditions, to confirm the performance of correct detection in a prospective way and in-troduce predefined electrical stimuli to assess safety and efficacy of stimulation in interictal and ictal periods. In this project, a hardware setup has been implemented, seizure detection algorithms have been applied and successfully tested in 5 patients who volunteered to have stimulation performed dur-ing the last day of their implantation period. Its components are an online access to the recording EEG data stream, an online seizure detector, which uses a machine learning approach trained on the preceding recorded seizures of the patient during the presurgical workup, a connection from the detection software to a control software, which switches electrodes from the recording ampli-fiers to the stimulator output, and sends information to the stimulator to start a predefined stimula-tion sequence. In the 5 patients 11 of 13 seizures were correctly detected accompanied by 12 false detections (0.14 per hour). An improvement in the detector resulted in a detection delay from 18 and 39 seconds to 2 seconds for the second implanted seizure detection algorithm in the last patient in the group (B). Stimulations did not alter the time course of ictal activity so far. Interictal interven-tions based on false detections did not result in discomfort or in the generation of a seizure. This platform gives a unique opportunity to assess interventions strategies in human epilepsy for predefined parameters of possible interventions by intracranial electrical stimulation and also the possibility of developing a responsive neurostimulaiton implant for epilepsy patients.

Research Status

A hospital-based closed-loop setup for online seizure detection and intervention by electrical has been implemented using epileptic seizure detection algorithms with high sensitivity and a specificity which is far beyond present-day technical standard in the commercially available closed-loop stimulation device (Neuropace). Safety of interictal and ictal stimulation using the hospital setup was established, providing the prerequisites to systematically study closed-loop stimulation approaches. Whereas the period for training the classifier proved to be suffi-cient, the short intervention period allows only to assess few predefined settings for interven-tions within the parameter space.

Project Publications


Jacobs J, Golla T, Mader M, Schelter B, Dümpelmann M, Korinthenberg R, Schulze-Bonhage A: Electrical stimulation for cortical mapping reduces the density of high frequency oscillations. Epilepsy Res, 2014; 108: 1758-1769

Schulze-Bonhage A, Somerlik K, Dümpelmann M. Closed-Loop Stimulation zur Epilepsietherapie. Z Epileptologie 2014; 27: 55-59.

Dümpelmann M, Jacobs J, Schulze-Bonhage A. Temporal and spatial characteristics of high frequency oscillations as a new biomarker in epilepsy. Epilepsia 2015 56(2): 197–206.

Donos C, Dümpelmann M, Schulze-Bonhage A. Early Seizure Detection Algorithm Based on Intracranial EEG and Random Forest Classification. International Journal of Neural Systems 2015 Vol. 25, No. 5 1550023

Meisel C, Schulze-Bonhage A, Freestone D, Cook MJ, Achermann P, Plenz D. Intrinsic excitability measures track antiepileptic drug action and uncover increasing/decreasing excitability over the wake/sleep cycle. Proc Natl Acad Sci 2015 112(47):14694–9

Meisel C, Plenz D, Schulze-Bonhage A, Reichmann H. Quantifying antiepileptic drug effects using intrinsic excitability measures. Epilepsia 2016 57(11):e210–e215

Donos C, Malîia M, Dümpelmann M, Schulze-Bonhage A. Seizure onset predicts its type. Epilepsia 2018 59(3):650–660.

Conference proceedings (peer reviewed)

Somerlik-Fuchs KH, Christ O, Dümpelmann M, Hofmann UG, Stieglitz T, Schulze-Bonhage A. Development of a Closed Loop Stimulation System for Epilepsy Therapy. Proceedings of 6th European Conference of the International Federation for Medical and Biological Engineering (MBEC 2014), 2014

Manzouri F, Schulze-Bonhage A, Dümpelmann M, Heller S, Woias P. Optimized Detector for Closed-loop Devices for Neurostimulation. IEEE International Conference on Systems, Man, and Cybernetics, Banff, Canada, 2017; pp 2158-2163.

Hügle, M, Heller S, Watter M, Blum M, Manzouri F, Dümpelmann M, Schulze-Bonhage A, Woias P, Boedecker J. Early Seizure Detection with an Energy-Efficient Convolutional Neural Network on an Implantable Microcontroller. 2018 International Joint Conference on Neural Networks, Rio de Janeiro Brazil, 2018.

Heller S, Hügle M, Nematollahi I, Manzouri F, Dümpelmann M, Schulze-Bonhage A, Bödecker J, Woias P. Early Hardware Implementation of a Performance and Energy-Optimized Convolutional Neural Network for Seizure Detection. 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Honolulu , USA, 2018