TY - CHAP
T1 - Computationally efficient neural network classifiers for next generation closed loop neuromodulation therapy - a case study in epilepsy
AU - Kavoosi, Ali
AU - Toth, Robert
AU - Benjaber, Moaad
AU - Zamora, Mayela
AU - Valentín, Antonio
AU - Sharott, Andrew
AU - Denison, Timothy
N1 - Funding Information:
This work was supported by the John Fell Fund of the University of Oxford, the UK Medical Research Council (MC UU 00003/3, MC UU 00003/6) and the Royal Academy of Engineering. † Ali Kavoosi and Robert Toth contributed equally to this work and share first authorship. 1 Brain Network Dynamics Unit, Department of Pharmacology, University of Oxford, Oxford OX1 3TH, United Kingdom 2 Institute of Biomedical Engineering, Old Road Campus Research Building, Department of Engineering Sciences, University of Oxford, Oxford OX3 7DQ, United Kingdom 3 Department of Basic and Clinical Neuroscience, King’s College Lon-
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - This work explores the potential utility of neural network classifiers for real- time classification of field-potential based biomarkers in next-generation responsive neuromodulation systems. Compared to classical filter-based classifiers, neural networks offer an ease of patient-specific parameter tuning, promising to reduce the burden of programming on clinicians. The paper explores a compact, feed - forward neural network architecture of only dozens of units for seizure-state classification in refractory epilepsy. The proposed classifier offers comparable accuracy to filter- classifiers on clinician-labeled data, while reducing detection latency. As a trade-off to classical methods, the paper focuses on keeping the complexity of the architecture minimal, to accommodate the on-board computational constraints of implantable pulse generator systems. Clinical relevance-A neural network-based classifier is presented for responsive neurostimulation, with comparable accuracy to classical methods at reduced latency.
AB - This work explores the potential utility of neural network classifiers for real- time classification of field-potential based biomarkers in next-generation responsive neuromodulation systems. Compared to classical filter-based classifiers, neural networks offer an ease of patient-specific parameter tuning, promising to reduce the burden of programming on clinicians. The paper explores a compact, feed - forward neural network architecture of only dozens of units for seizure-state classification in refractory epilepsy. The proposed classifier offers comparable accuracy to filter- classifiers on clinician-labeled data, while reducing detection latency. As a trade-off to classical methods, the paper focuses on keeping the complexity of the architecture minimal, to accommodate the on-board computational constraints of implantable pulse generator systems. Clinical relevance-A neural network-based classifier is presented for responsive neurostimulation, with comparable accuracy to classical methods at reduced latency.
UR - http://www.scopus.com/inward/record.url?scp=85138128180&partnerID=8YFLogxK
U2 - 10.1109/EMBC48229.2022.9871793
DO - 10.1109/EMBC48229.2022.9871793
M3 - Conference paper
C2 - 36085909
AN - SCOPUS:85138128180
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 288
EP - 291
BT - 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022
Y2 - 11 July 2022 through 15 July 2022
ER -