An official website of the United States government
Normal routine electroencephalograms (EEGs) can cause delays in the diagnosis and treatment of epilepsy, especially in drug-resistant patients and those without structural abnormalities. There is a need for alternative quantitative approaches that can inform clinical decisions when traditional visual EEG review is inconclusive. We leverage a large population EEG database (N = 13,652 recordings, 12,134 unique patients) and an independent cohort of patients with focal epilepsy (N = 121) to investigate whether normal EEG segments could support the diagnosis of focal epilepsy. We decomposed expertly graded normal EEGs (N = 6,242) using unsupervised tensor decomposition to extract the dominant spatio-spectral patterns present in a clinical population. We then, using the independent cohort of patients with focal epilepsy, evaluated whether pattern loadings of normal interictal EEG segments could classify focal epilepsy, the epileptogenic lobe, presence of lesions, and drug response. We obtained six physiological patterns of EEG spectral power and connectivity with distinct spatio-spectral signatures. Both pattern types together effectively differentiated patients with focal epilepsy from non-epileptic controls (mean AUC 0.78) but failed to classify the epileptogenic lobe. Spectral power-based patterns best classified drug-resistant epilepsy (mean AUC 0.73) and lesional epilepsy (mean AUC 0.67), albeit with high variability across patients. Our findings support that visibly normal patient EEGs contain subtle quantitative differences of clinical relevance. Further development may yield normal EEG-based computational biomarkers that can augment traditional EEG review and epilepsy care.
more »
« less
Interictal EEG and ECG for SUDEP Risk Assessment: A Retrospective Multicenter Cohort Study
Objective Sudden unexpected death in epilepsy (SUDEP) is the leading cause of epilepsy-related mortality. Although lots of effort has been made in identifying clinical risk factors for SUDEP in the literature, there are few validated methods to predict individual SUDEP risk. Prolonged postictal EEG suppression (PGES) is a potential SUDEP biomarker, but its occurrence is infrequent and requires epilepsy monitoring unit admission. We use machine learning methods to examine SUDEP risk using interictal EEG and ECG recordings from SUDEP cases and matched living epilepsy controls. Methods This multicenter, retrospective, cohort study examined interictal EEG and ECG recordings from 30 SUDEP cases and 58 age-matched living epilepsy patient controls. We trained machine learning models with interictal EEG and ECG features to predict the retrospective SUDEP risk for each patient. We assessed cross-validated classification accuracy and the area under the receiver operating characteristic (AUC) curve. Results The logistic regression (LR) classifier produced the overall best performance, outperforming the support vector machine (SVM), random forest (RF), and convolutional neural network (CNN). Among the 30 patients with SUDEP [14 females; mean age (SD), 31 (8.47) years] and 58 living epilepsy controls [26 females (43%); mean age (SD) 31 (8.5) years], the LR model achieved the median AUC of 0.77 [interquartile range (IQR), 0.73–0.80] in five-fold cross-validation using interictal alpha and low gamma power ratio of the EEG and heart rate variability (HRV) features extracted from the ECG. The LR model achieved the mean AUC of 0.79 in leave-one-center-out prediction. Conclusions Our results support that machine learning-driven models may quantify SUDEP risk for epilepsy patients, future refinements in our model may help predict individualized SUDEP risk and help clinicians correlate predictive scores with the clinical data. Low-cost and noninvasive interictal biomarkers of SUDEP risk may help clinicians to identify high-risk patients and initiate preventive strategies.
more »
« less
- Award ID(s):
- 1835000
- PAR ID:
- 10394669
- Date Published:
- Journal Name:
- Frontiers in Neurology
- Volume:
- 13
- ISSN:
- 1664-2295
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We present SeizureFormer, a Transformer-based model for long-horizon seizure risk forecasting (1–14 days) using structured biomarkers—interictal epileptiform activity (IEA) and long episodes (LE)—extracted from responsive neurostimulation (RNS) systems. Unlike prior models based on raw scalp EEG, SeizureFormer leverages stable RNS biomarkers and integrates multi-scale CNN patch embedding, cross-variable temporal convolution, and squeeze-and-excitation attention to capture both short-term fluctuations and long-term seizure cycles. Tested across five patients and multiple prediction windows (1–14 days), SeizureFormer achieved state-of-the-art performance with mean ROC AUC of 79.44% and mean PR AUC of 76.29% across five patients and four prediction windows. Compared to statistical, classical ML, and deep learning baselines, it demonstrates superior generalizability under class imbalance. Clinically, it enables actionable multi-day forecasting, supporting personalized and proactive intervention in epilepsy care by forecasting seizurerelated events 1 to 14 days ahead.more » « less
-
Objectives: We set out to develop a machine learning model capable of distinguishing patients presenting with ischemic stroke from a healthy cohort of subjects. The model relies on a 3-min resting electroencephalogram (EEG) recording from which features can be computed. Materials and methods: Using a large-scale, retrospective database of EEG recordings and matching clinical reports, we were able to construct a dataset of 1385 healthy subjects and 374 stroke patients. With subjects often producing more than one recording per session, the final dataset consisted of 2401 EEG recordings (63% healthy, 37% stroke). Results: Using a rich set of features encompassing both the spectral and temporal domains, our model yielded an AUC of 0.95, with a sensitivity and specificity of 93% and 86%, respectively. Allowing for multiple recordings per subject in the training set boosted sensitivity by 7%, attributable to a more balanced dataset. Conclusions: Our work demonstrates strong potential for the use of EEG in conjunction with machine learning methods to distinguish stroke patients from healthy subjects. Our approach provides a solution that is not only timely (3-minutes recording time) but also highly precise and accurate (AUC: 0.95). Keywords: Electroencephalogram (EEG); Feature engineering; Ischemic stroke; Large vessel occlusion; Machine learning; Prehospital stroke scale.more » « less
-
Abstract ObjectiveCognitive impairment often impacts quality of life in epilepsy even if seizures are controlled. Word‐finding difficulty is particularly prevalent and often attributed to etiological (static, baseline) circuit alterations. We sought to determine whether interictal discharges convey significant superimposed contributions to word‐finding difficulty in patients, and if so, through which cognitive mechanism(s). MethodsTwenty‐three patients undergoing intracranial monitoring for drug‐resistant epilepsy participated in multiple tasks involving word production (auditory naming, short‐term verbal free recall, repetition) to probe word‐finding difficulty across different cognitive domains. We compared behavioral performance between trials with versus without interictal discharges across six major brain areas and adjusted for intersubject differences using mixed‐effects models. We also evaluated for subjective word‐finding difficulties through retrospective chart review. ResultsSubjective word‐finding difficulty was reported by the majority (79%) of studied patients preoperatively. During intracranial recordings, interictal epileptiform discharges (IEDs) in the medial temporal lobe were associated with long‐term lexicosemantic memory impairments as indexed by auditory naming (p = .009), in addition to their established impact on short‐term verbal memory as indexed by free recall (p = .004). Interictal discharges involving the lateral temporal cortex and lateral frontal cortex were associated with delayed reaction time in the auditory naming task (p = .016 andp = .018), as well as phonological working memory impairments as indexed by repetition reaction time (p = .002). Effects of IEDs across anatomical regions were strongly dependent on their precise timing within the task. SignificanceIEDs appear to act through multiple cognitive mechanisms to form a convergent basis for the debilitating clinical word‐finding difficulty reported by patients with epilepsy. This was particularly notable for medial temporal spikes, which are quite common in adult focal epilepsy. In parallel with the treatment of seizures, the modulation of interictal discharges through emerging pharmacological means and neurostimulation approaches may be an opportunity to help address devastating memory and language impairments in epilepsy.more » « less
-
null (Ed.)Using electroencephalography (EEG) data from epileptic patients 1 , we investigated and compared functional connectivity networks of three various types of epileptiform discharges (ED; single, complex & repetitive spikes) in 4 regions of the brain. Our results showed different connectivity patterns among three ED types within-and between-brain regions. The one-way ANOVA test indicated significant differences between the mean of the average connectivity matrices (ACMs) of the single spike, which characterize focal epilepsy, and the other two ED types (complex & repetitive) which characterize generalized epilepsy. The interictal EEG segments, through the connectivity patterns they yield, could be considered as one of the key indicators for the diagnosis of focal or generalized epilepsy.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Journal Article:
- https://doi.org/10.3389/fneur.2022.858333
