Deep learning for automated detection of generalized paroxysmal fast activity in Lennox-Gastaut syndrome.

OBJECTIVES: Generalized paroxysmal fast activity (GPFA) is a key electroencephalographic (EEG) feature of Lennox-Gastaut Syndrome (LGS). Automated analysis of scalp EEG has been successful in detecting more typical abnormalities. Automatic detection of GPFA has been more challenging, due to its variability from patient to patient and similarity to normal brain rhythms. In this work, a deep learning model is investigated for detection of GPFA events and estimating their overall burden from scalp EEG. METHODS: Data from 10 patients recorded during four ambulatory EEG monitoring sessions are used to generate and validate the model. All patients had confirmed LGS and were recruited into a trial for thalamic deep-brain stimulation therapy (ESTEL Trial). RESULTS: The correlation coefficient between manual and model estimates of event counts was r2 = 0.87, and for total burden was r2 = 0.91. The average GPFA detection sensitivity was 0.876, with an average false-positive rate of 3.35 per minute. There was no significant difference found between patients with early or delayed deep brain stimulation (DBS) treatment, or those with active vagal nerve stimulation (VNS). CONCLUSIONS: Overall, the deep learning model was able to accurately detect GPFA and provide accurate estimates of the overall GPFA burden and electrographic event counts, albeit with a high false-positive rate. SIGNIFICANCE: Automated GPFA detection may enable automated calculation of EEG biomarkers of burden of disease in LGS.