Nurse Ewan S, Dalic Linda J, Clarke Shannon, Cook Mark, Archer John
Seer Medical, Melbourne, VIC 3000, Australia; Department of Medicine (St. Vincent's Hospital Melbourne), University of Melbourne, Fitzroy, VIC 3065, Australia.
Department of Medicine (Austin Hospital), University of Melbourne, Heidelberg, VIC 3084, Australia; Department of Neurology, Austin Health, Heidelberg, VIC 3084, Australia.
Epilepsy Behav. 2023 Oct;147:109418. doi: 10.1016/j.yebeh.2023.109418. Epub 2023 Sep 6.
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.
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).
The correlation coefficient between manual and model estimates of event counts was r = 0.87, and for total burden was r = 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).
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.
Automated GPFA detection may enable automated calculation of EEG biomarkers of burden of disease in LGS.
广泛性阵发快速活动（GPFA）是Lennox-Gastaut综合征（LGS）的关键脑电图（EEG）特征。头皮脑电图的自动分析已成功检测出更典型的异常情况。由于GPFA在患者之间存在变异性且与正常脑节律相似，因此自动检测GPFA更具挑战性。在这项研究中，研究了一种深度学习模型，用于检测头皮脑电图中的GPFA事件并估计其总体负荷。
使用10例患者在4次动态脑电图监测期间记录的数据来生成和验证模型。所有患者均确诊为LGS，并被纳入丘脑深部脑刺激治疗试验（ESTEL试验）。
事件计数的手动估计与模型估计之间的相关系数为r = 0.87，总负荷的相关系数为r = 0.91。GPFA的平均检测灵敏度为0.876，平均假阳性率为每分钟3.35次。早期或延迟进行深部脑刺激（DBS）治疗的患者与接受主动迷走神经刺激（VNS）的患者之间未发现显著差异。
总体而言，深度学习模型能够准确检测GPFA，并能准确估计GPFA的总体负荷和脑电图事件计数，尽管假阳性率较高。
自动检测GPFA可能有助于自动计算LGS疾病负担的脑电图生物标志物。
