AiED: Artificial intelligence for the detection of intracranial interictal epileptiform discharges. (January 2022)

• Record Type: Journal Article
• Authors: Quon, Robert J.; Meisenhelter, Stephen; Camp, Edward J.; Testorf, Markus E.; Song, Yinchen; Song, Qingyuan; Culler, George W.; Moein, Payam; Jobst, Barbara C.
• Is Part Of: Clinical neurophysiology. Volume 133(2022)
• Page Start: 1
• Page End: 8
• Publication Date: 2022-01
• Subjects: Interictal epileptiform discharges -- EEG -- IED detection -- Epilepsy -- Deep learning -- CNN -- Artificial intelligence; Neurophysiology -- Periodicals; Electroencephalography -- Periodicals; Electromyography -- Periodicals; Neurology -- Periodicals; 612.8
• DOI: 10.1016/j.clinph.2021.09.018
• Languages: English
• ISSNs: 1388-2457

Abstract

Highlights: Deep learning method detects intracranial interictal epileptiform discharges with 91–98% accuracy. Most detector errors arose from interictal epileptiform discharges of atypical morphology. Our automated detector is available online to support research EEG analyses. Abstract: Objective: Deep learning provides an appealing solution for the ongoing challenge of automatically classifying intracranial interictal epileptiform discharges (IEDs). We report results from an automated method consisting of a template-matching algorithm and convolutional neural network (CNN) for the detection of intracranial IEDs ("AiED"). Methods: 1000 intracranial electroencephalogram (EEG) epochs extracted randomly from 307 subjects with refractory epilepsy were annotated independently by two expert neurophysiologists. These annotated epochs were divided into 1062 two-second epochs with IEDs and 1428 two-second epochs without IEDs, which were transformed into spectrograms prior to training the neural network. The highest performing network was validated on an annotated external test set. Results: The final network had an F1-score of 0.95 (95% CI: 0.91–0.98) and an average Area Under the Receiver Operating Characteristic of 0.98 (95% CI: 0.96–1.00). For the external test set, it showed an overall F1-score of 0.71, correctly identifying 100% of all high-amplitude IED complexes, 96.23% of all high-amplitude isolated IEDs, and 66.15% of all IEDs of atypical morphology. Conclusions: Template-matching combined with a CNN offers a fast, robust method for detecting intracranial IEDs. Significance: " AiED" is generalizable and achieves comparable performance to human reviewers; it may support clinical and research EEG analyses.