Detection of mesial temporal lobe epileptiform discharges on intracranial electrodes using deep learning. Issue 1 (January 2020)

• Record Type: Journal Article
• Authors: Abou Jaoude, Maurice; Jing, Jin; Sun, Haoqi; Jacobs, Claire S.; Pellerin, Kyle R.; Westover, M. Brandon; Cash, Sydney S.; Lam, Alice D.
• Is Part Of: Clinical neurophysiology. Volume 131:Issue 1(2020:Jan.)
• Page Start: 133
• Page End: 141
• Publication Date: 2020-01
• Subjects: Spike detection -- Epileptiform discharges -- Temporal lobe epilepsy -- Deep learning -- Convolutional neural networks; Neurophysiology -- Periodicals; Electroencephalography -- Periodicals; Electromyography -- Periodicals; Neurology -- Periodicals; 612.8
• DOI: 10.1016/j.clinph.2019.09.031
• Languages: English
• ISSNs: 1388-2457

Abstract

Highlights: We developed a deep learning algorithm to detect mesial temporal lobe epileptiform discharges on intracranial EEG. Convolutional neural networks with simple architectures deliver excellent performance in detecting epileptiform discharges. Quantification of intracranial epileptiform activity has many research and clinical applications. Abstract: Objective: Develop a high-performing algorithm to detect mesial temporal lobe (mTL) epileptiform discharges on intracranial electrode recordings. Methods: An epileptologist annotated 13, 959 epileptiform discharges from a dataset of intracranial EEG recordings from 46 epilepsy patients. Using this dataset, we trained a convolutional neural network (CNN) to recognize mTL epileptiform discharges from a single intracranial bipolar channel. The CNN outputs from multiple bipolar channel inputs were averaged to generate the final detector output. Algorithm performance was estimated using a nested 5-fold cross-validation. Results: On the receiver-operating characteristic curve, our algorithm achieved an area under the curve (AUC) of 0.996 and a partial AUC (for specificity > 0.9) of 0.981. AUC on a precision-recall curve was 0.807. A sensitivity of 84% was attained at a false positive rate of 1 per minute. 35.9% of the false positive detections corresponded to epileptiform discharges that were missed during expert annotation. Conclusions: Using deep learning, we developed a high-performing, patient non-specific algorithm for detection of mTL epileptiform discharges on intracranial electrodes. Significance: Our algorithm has many potential applications for understanding the impact of mTL epileptiform discharges in epilepsy and on cognition, and for developing therapies to specifically reduce mTL epileptiform activity.