Automated Analysis of EEG: Opportunities and Pitfalls

Scorepochs: A Computer-Aided Scoring Tool for Resting-State M/EEG Epochs

M/EEG resting-state analysis often requires the definition of the epoch length and the criteria in order to select which epochs to include in the subsequent steps. However, the effects of epoch selection remain scarcely investigated and the procedure used to (visually) inspect, label, and remove bad epochs is often not documented, thereby hindering the reproducibility of the reported results. In this study, we present Scorepochs, a simple and freely available tool for the automatic scoring of resting-state M/EEG epochs that aims to provide an objective method to aid M/EEG experts during the epoch selection procedure. We tested our approach on a freely available EEG dataset containing recordings from 109 subjects using the BCI2000 64 channel system.

Spectral Electroencephalogram Analysis for the Evaluation of Encephalopathy Grade in Children With Acute Liver Failure

OBJECTIVE

Spectral electroencephalogram analysis is a method for automated analysis of electroencephalogram patterns, which can be performed at the bedside. We sought to determine the utility of spectral electroencephalogram for grading hepatic encephalopathy in children with acute liver failure.

DESIGN

Retrospective cohort study.

SETTING

Tertiary care pediatric hospital.

PATIENTS

Patients between 0 and 18 years old who presented with acute liver failure and were admitted to the PICU.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

Electroencephalograms were analyzed by spectral analysis including total power, relative δ, relative θ, relative α, relative β, θ-to-Δ ratio, and α-to-Δ ratio. Normal values and ranges were first derived using normal electroencephalograms from 70 children of 0-18 years old. Age had a significant effect on each variable measured (p < 0.03). Electroencephalograms from 33 patients with acute liver failure were available for spectral analysis. The median age was 4.3 years, 14 of 33 were male, and the majority had an indeterminate etiology of acute liver failure. Neuroimaging was performed in 26 cases and was normal in 20 cases (77%). The majority (64%) survived, and 82% had a good outcome with a score of 1-3 on the Pediatric Glasgow Outcome Scale-Extended at the time of discharge. Hepatic encephalopathy grade correlated with the qualitative visual electroencephalogram scores assigned by blinded neurophysiologists (rs = 0.493; p < 0.006). Spectral electroencephalogram characteristics varied significantly with the qualitative electroencephalogram classification (p < 0.05). Spectral electroencephalogram variables including relative Δ, relative θ, relative α, θ-to-Δ ratio, and α-to-Δ ratio all significantly varied with the qualitative electroencephalogram (p < 0.025). Moderate to severe hepatic encephalopathy was correlated with a total power of less than or equal to 50% of normal for children 0-3 years old, and with a relative θ of less than or equal to 50% normal for children more than 3 years old (p > 0.05). Spectral electroencephalogram classification correlated with outcome (p < 0.05).

CONCLUSIONS

Spectral electroencephalogram analysis can be used to evaluate even young patients for hepatic encephalopathy and correlates with outcome. Spectral electroencephalogram may allow improved quantitative and reproducible assessment of hepatic encephalopathy grade in children with acute liver failure.

Computer-assisted interpretation of the EEG background pattern: a clinical evaluation

Objective

Interpretation of the EEG background pattern in routine recordings is an important part of clinical reviews. We evaluated the feasibility of an automated analysis system to assist reviewers with evaluation of the general properties in the EEG background pattern.

Methods

Quantitative EEG methods were used to describe the following five background properties: posterior dominant rhythm frequency and reactivity, anterior-posterior gradients, presence of diffuse slow-wave activity and asymmetry. Software running the quantitative methods were given to ten experienced electroencephalographers together with 45 routine EEG recordings and computer-generated reports. Participants were asked to review the EEGs by visual analysis first, and afterwards to compare their findings with the generated reports and correct mistakes made by the system. Corrected reports were returned for comparison.

Results

Using a gold-standard derived from the consensus of reviewers, inter-rater agreement was calculated for all reviewers and for automated interpretation. Automated interpretation together with most participants showed high (kappa > 0.6) agreement with the gold standard. In some cases, automated analysis showed higher agreement with the gold standard than participants. When asked in a questionnaire after the study, all participants considered computer-assisted interpretation to be useful for every day use in routine reviews.

Conclusions

Automated interpretation methods proved to be accurate and were considered to be useful by all participants.

Significance

Computer-assisted interpretation of the EEG background pattern can bring consistency to reviewing and improve efficiency and inter-rater agreement.