Quantitative analysis of visually reviewed normal scalp EEG predicts seizure freedom following anterior temporal lobectomy

Abstract

Objective Anterior temporal lobectomy (ATL) is a widely performed and successful intervention for drug‐resistant temporal lobe epilepsy (TLE). However, up to one third of patients experience seizure recurrence within 1 year after ATL. Despite the extensive literature on presurgical electroencephalography (EEG) and magnetic resonance imaging (MRI) abnormalities to prognosticate seizure freedom following ATL, the value of quantitative analysis of visually reviewed normal interictal EEG in such prognostication remains unclear. In this retrospective multicenter study, we investigate whether machine learning analysis of normal interictal scalp EEG studies can inform the prediction of postoperative seizure freedom outcomes in patients who have undergone ATL. Methods We analyzed normal presurgical scalp EEG recordings from 41 Mayo Clinic (MC) and 23 Cleveland Clinic (CC) patients. We used an unbiased automated algorithm to extract eyes closed awake epochs from scalp EEG studies that were free of any epileptiform activity and then extracted spectral EEG features representing (a) spectral power and (b) interhemispheric spectral coherence in frequencies between 1 and 25 Hz across several brain regions. We analyzed the differences between the seizure‐free and non–seizure‐free patients and employed a Naïve Bayes classifier using multiple spectral features to predict surgery outcomes. We trained the classifier using a leave‐one‐patient‐out cross‐validation scheme within the MC data set and then tested using the out‐of‐sample CC data set. Finally, we compared the predictive performance of normal scalp EEG‐derived features against MRI abnormalities. Results We found that several spectral power and coherence features showed significant differences correlated with surgical outcomes and that they were most pronounced in the 10–25 Hz range. The Naïve Bayes classification based on those features predicted 1‐year seizure freedom following ATL with area under the curve (AUC) values of 0.78 and 0.76 for the MC and CC data sets, respectively. Subsequent analyses revealed that (a) interhemispheric spectral coherence features in the 10–25 Hz range provided better predictability than other combinations and (b) normal scalp EEG‐derived features provided superior and potentially distinct predictive value when compared with MRI abnormalities (>10% higher F1 score). Significance These results support that quantitative analysis of even a normal presurgical scalp EEG may help prognosticate seizure freedom following ATL in patients with drug‐resistant TLE. Although the mechanism for this result is not known, the scalp EEG spectral and coherence properties predicting seizure freedom may represent activity arising from the neocortex or the networks responsible for temporal lobe seizure generation within vs outside the margins of an ATL.

Machine learning using multimodal clinical, electroencephalographic, and magnetic resonance imaging data can predict incident depression in adults with epilepsy: A pilot study

“…With the 60‐Hz notch filter applied, we manually isolated 10‐s epochs of eyes‐closed, relaxed wakefulness. Multiple epochs per patient were used (maximum of six per patient), replicating a previously published protocol for using quantitative EEG to predict seizure freedom 18 . EEG features were selected based on heuristics and theoretical frameworks.…”

“…Multiple epochs per patient were used (maximum of six per patient), replicating a previously published protocol for using quantitative EEG to predict seizure freedom. 18 EEG features were selected based on heuristics and theoretical frameworks. The quantitative EEG features included global explained variance of the EEG microstate maps, EEG microstate global field power peaks per second, Shannon entropy and entropy rate of the distribution of EEG microstates, 19 spectral entropy from electrode pairs, and power of beta and theta frequencies from electrode pairs.…”

From basic sciences and engineering to epileptology: A translational approach

“…Spectral features were extracted from EEG recordings and used as inputs to a Naïve Bayes classifier. 62 Abou Jaoude et al proposed an ML algorithm based on deep neural networks (HEAnet) for the detection of hippocampal epileptiform activity from scalp EEG recordings. 63…”

“…More recently, Varatharajah et al developed a classifier, based on scalp EEG, for the prediction of postoperative seizure freedom in patients who underwent anterior temporal lobectomy. Spectral features were extracted from EEG recordings and used as inputs to a Naïve Bayes classifier 62 . Abou Jaoude et al proposed an ML algorithm based on deep neural networks (HEAnet) for the detection of hippocampal epileptiform activity from scalp EEG recordings 63 …”

Network alterations in temporal lobe epilepsy during non-rapid eye movement sleep and wakefulness

“…Epileptic networks have been studied mainly during wakefulness, and results suggest that connectivity analyses could help differentiate patients with temporal lobe epilepsy (TLE) from healthy controls (HC) (Verhoeven et al, 2018), localize the seizure onset zone (Staljanssens et al, 2017) and predict seizure freedom after surgery (Varatharajah et al, 2022). Recent results suggest that high integration -meaning a more efficient information transfer across brain regions-could be a biomarker of epilepsy: during segments of scalp electroencephalography (EEG) without IEDs, TLE patients showed more integrated brain networks than HC (Carboni et al, 2020).…”