Interpretable Epilepsy Detection in Routine, Interictal EEG Data using Deep Learning

Thomas Uyttenhove, Aren Maes, Tom Van Steenkiste, Dirk Deschrijver, Tom Dhaene
Proceedings of the Machine Learning for Health NeurIPS Workshop, PMLR 136:355-366, 2020.

Abstract

Epilepsy, a common serious neurological disorder, is characterized by its frequently occurring seizures that cause its patients to be three times as likely to die prematurely. While the application of machine learning to EEG recordings has enabled the successful prediction of whether and when such seizures will occur, the reliable detection of epilepsy during seizure-free periods is lacking. As far as the authors are aware, this work proposes the first deep learning approach for the latter task – and the second machine learning approach altogether. Additionally, it does so in an interpretable fashion to validate the proposed method for a more wide-spread adoption in healthcare and to potentially unveil unknown epileptic biomarkers. The performance of the Tiny Visual Geometry Group (t-VGG) convolutional neural network is evaluated against Temple University Hospital’s \textit{EEG Epilepsy Corpus}, a data set of variable-length EEG recordings gathered during routine checkups. The t-VGG network predicted individual $10$ second EEG windows with an Area Under the Precision-Recall Curve (AUPR) of $93.02%$ for epileptic predictions and $55.85%$ for healthy ones – a significant improvement of respectively $7.24$pp and $18.6$pp ($p\!<\!.001$) over the current state-of-the-art. Averaging window predictions per recording improved the t-VGG’s respective AUPR performances further to $95.52%$ and $77.27%$. The Gradient-weighted Class Activation Mapping method for interpretability confirmed that the model was able to learn sensible features with connections to well-known epilepsy markers.

Cite this Paper


BibTeX
@InProceedings{pmlr-v136-uyttenhove20a, title = {Interpretable Epilepsy Detection in Routine, Interictal EEG Data using Deep Learning}, author = {Uyttenhove, Thomas and Maes, Aren and Steenkiste, Tom Van and Deschrijver, Dirk and Dhaene, Tom}, booktitle = {Proceedings of the Machine Learning for Health NeurIPS Workshop}, pages = {355--366}, year = {2020}, editor = {Emily Alsentzer and Matthew B. A. McDermott and Fabian Falck and Suproteem K. Sarkar and Subhrajit Roy and Stephanie L. Hyland}, volume = {136}, series = {Proceedings of Machine Learning Research}, month = {11 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v136/uyttenhove20a/uyttenhove20a.pdf}, url = {http://proceedings.mlr.press/v136/uyttenhove20a.html}, abstract = {Epilepsy, a common serious neurological disorder, is characterized by its frequently occurring seizures that cause its patients to be three times as likely to die prematurely. While the application of machine learning to EEG recordings has enabled the successful prediction of whether and when such seizures will occur, the reliable detection of epilepsy during seizure-free periods is lacking. As far as the authors are aware, this work proposes the first deep learning approach for the latter task – and the second machine learning approach altogether. Additionally, it does so in an interpretable fashion to validate the proposed method for a more wide-spread adoption in healthcare and to potentially unveil unknown epileptic biomarkers. The performance of the Tiny Visual Geometry Group (t-VGG) convolutional neural network is evaluated against Temple University Hospital’s \textit{EEG Epilepsy Corpus}, a data set of variable-length EEG recordings gathered during routine checkups. The t-VGG network predicted individual $10$ second EEG windows with an Area Under the Precision-Recall Curve (AUPR) of $93.02%$ for epileptic predictions and $55.85%$ for healthy ones – a significant improvement of respectively $7.24$pp and $18.6$pp ($p\!<\!.001$) over the current state-of-the-art. Averaging window predictions per recording improved the t-VGG’s respective AUPR performances further to $95.52%$ and $77.27%$. The Gradient-weighted Class Activation Mapping method for interpretability confirmed that the model was able to learn sensible features with connections to well-known epilepsy markers.} }
Endnote
%0 Conference Paper %T Interpretable Epilepsy Detection in Routine, Interictal EEG Data using Deep Learning %A Thomas Uyttenhove %A Aren Maes %A Tom Van Steenkiste %A Dirk Deschrijver %A Tom Dhaene %B Proceedings of the Machine Learning for Health NeurIPS Workshop %C Proceedings of Machine Learning Research %D 2020 %E Emily Alsentzer %E Matthew B. A. McDermott %E Fabian Falck %E Suproteem K. Sarkar %E Subhrajit Roy %E Stephanie L. Hyland %F pmlr-v136-uyttenhove20a %I PMLR %P 355--366 %U http://proceedings.mlr.press/v136/uyttenhove20a.html %V 136 %X Epilepsy, a common serious neurological disorder, is characterized by its frequently occurring seizures that cause its patients to be three times as likely to die prematurely. While the application of machine learning to EEG recordings has enabled the successful prediction of whether and when such seizures will occur, the reliable detection of epilepsy during seizure-free periods is lacking. As far as the authors are aware, this work proposes the first deep learning approach for the latter task – and the second machine learning approach altogether. Additionally, it does so in an interpretable fashion to validate the proposed method for a more wide-spread adoption in healthcare and to potentially unveil unknown epileptic biomarkers. The performance of the Tiny Visual Geometry Group (t-VGG) convolutional neural network is evaluated against Temple University Hospital’s \textit{EEG Epilepsy Corpus}, a data set of variable-length EEG recordings gathered during routine checkups. The t-VGG network predicted individual $10$ second EEG windows with an Area Under the Precision-Recall Curve (AUPR) of $93.02%$ for epileptic predictions and $55.85%$ for healthy ones – a significant improvement of respectively $7.24$pp and $18.6$pp ($p\!<\!.001$) over the current state-of-the-art. Averaging window predictions per recording improved the t-VGG’s respective AUPR performances further to $95.52%$ and $77.27%$. The Gradient-weighted Class Activation Mapping method for interpretability confirmed that the model was able to learn sensible features with connections to well-known epilepsy markers.
APA
Uyttenhove, T., Maes, A., Steenkiste, T.V., Deschrijver, D. & Dhaene, T.. (2020). Interpretable Epilepsy Detection in Routine, Interictal EEG Data using Deep Learning. Proceedings of the Machine Learning for Health NeurIPS Workshop, in Proceedings of Machine Learning Research 136:355-366 Available from http://proceedings.mlr.press/v136/uyttenhove20a.html.

Related Material