Towards Early Diagnosis of Epilepsy from EEG Data

Diyuan Lu, Sebastian Bauer, Valentin Neubert, Laura Sophie Costard, Felix Rosenow, Jochen Triesch
Proceedings of the 5th Machine Learning for Healthcare Conference, PMLR 126:80-96, 2020.

Abstract

Epilepsy is one of the most common neurological disorders, affecting about 1% of the population at all ages. Detecting the development of epilepsy, i.e., epileptogenesis (EPG), before any seizures occur could allow for early interventions and potentially more effective treatments. Here, we investigate if modern machine learning (ML) techniques can detect EPG from intra-cranial electroencephalography (EEG) recordings prior to the occurrence of any seizures by a time frame of days or even weeks. We study a common form of epilepsy called mesial temporal lobe epilepsy (mTLE). Specifically, we use a rodent mTLE model where EPG is triggered by electrical stimulation of the brain, which induces hippocampal damages that resemble those in human patients. We propose a ML framework for EPG identification, which combines a deep convolutional neural network (CNN) with a prediction aggregation method to obtain the final classification decision. Specifically, the neural network is trained to distinguish five second segments of EEG recordings taken from either the pre-stimulation period or the post-stimulation period. Due to the gradual development of epilepsy, there is enormous overlap of the EEG patterns before and after the stimulation. Hence, a prediction aggregation process is introduced, which pools predictions over a longer period. By aggregating predictions over one hour, our approach achieves an area under the curve (AUC) of 0.99 on the EPG detection task. This demonstrates the potential of ML for EPG prediction from EEG recordings.

Cite this Paper

BibTeX
@InProceedings{pmlr-v126-lu20a, title = {Towards Early Diagnosis of Epilepsy from EEG Data}, author = {Lu, Diyuan and Bauer, Sebastian and Neubert, Valentin and Costard, Laura Sophie and Rosenow, Felix and Triesch, Jochen}, booktitle = {Proceedings of the 5th Machine Learning for Healthcare Conference}, pages = {80--96}, year = {2020}, editor = {Doshi-Velez, Finale and Fackler, Jim and Jung, Ken and Kale, David and Ranganath, Rajesh and Wallace, Byron and Wiens, Jenna}, volume = {126}, series = {Proceedings of Machine Learning Research}, month = {07--08 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v126/lu20a/lu20a.pdf}, url = {https://proceedings.mlr.press/v126/lu20a.html}, abstract = {Epilepsy is one of the most common neurological disorders, affecting about 1% of the population at all ages. Detecting the development of epilepsy, i.e., epileptogenesis (EPG), before any seizures occur could allow for early interventions and potentially more effective treatments. Here, we investigate if modern machine learning (ML) techniques can detect EPG from intra-cranial electroencephalography (EEG) recordings prior to the occurrence of any seizures by a time frame of days or even weeks. We study a common form of epilepsy called mesial temporal lobe epilepsy (mTLE). Specifically, we use a rodent mTLE model where EPG is triggered by electrical stimulation of the brain, which induces hippocampal damages that resemble those in human patients. We propose a ML framework for EPG identification, which combines a deep convolutional neural network (CNN) with a prediction aggregation method to obtain the final classification decision. Specifically, the neural network is trained to distinguish five second segments of EEG recordings taken from either the pre-stimulation period or the post-stimulation period. Due to the gradual development of epilepsy, there is enormous overlap of the EEG patterns before and after the stimulation. Hence, a prediction aggregation process is introduced, which pools predictions over a longer period. By aggregating predictions over one hour, our approach achieves an area under the curve (AUC) of 0.99 on the EPG detection task. This demonstrates the potential of ML for EPG prediction from EEG recordings.} }
Endnote
%0 Conference Paper %T Towards Early Diagnosis of Epilepsy from EEG Data %A Diyuan Lu %A Sebastian Bauer %A Valentin Neubert %A Laura Sophie Costard %A Felix Rosenow %A Jochen Triesch %B Proceedings of the 5th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2020 %E Finale Doshi-Velez %E Jim Fackler %E Ken Jung %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v126-lu20a %I PMLR %P 80--96 %U https://proceedings.mlr.press/v126/lu20a.html %V 126 %X Epilepsy is one of the most common neurological disorders, affecting about 1% of the population at all ages. Detecting the development of epilepsy, i.e., epileptogenesis (EPG), before any seizures occur could allow for early interventions and potentially more effective treatments. Here, we investigate if modern machine learning (ML) techniques can detect EPG from intra-cranial electroencephalography (EEG) recordings prior to the occurrence of any seizures by a time frame of days or even weeks. We study a common form of epilepsy called mesial temporal lobe epilepsy (mTLE). Specifically, we use a rodent mTLE model where EPG is triggered by electrical stimulation of the brain, which induces hippocampal damages that resemble those in human patients. We propose a ML framework for EPG identification, which combines a deep convolutional neural network (CNN) with a prediction aggregation method to obtain the final classification decision. Specifically, the neural network is trained to distinguish five second segments of EEG recordings taken from either the pre-stimulation period or the post-stimulation period. Due to the gradual development of epilepsy, there is enormous overlap of the EEG patterns before and after the stimulation. Hence, a prediction aggregation process is introduced, which pools predictions over a longer period. By aggregating predictions over one hour, our approach achieves an area under the curve (AUC) of 0.99 on the EPG detection task. This demonstrates the potential of ML for EPG prediction from EEG recordings.
APA
Lu, D., Bauer, S., Neubert, V., Costard, L.S., Rosenow, F. & Triesch, J.. (2020). Towards Early Diagnosis of Epilepsy from EEG Data. Proceedings of the 5th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 126:80-96 Available from https://proceedings.mlr.press/v126/lu20a.html.

Related Material