Computer-Assisted Interpretation of the EEG Background Pattern: A Clinical Evaluation

Abstract

ObjectiveInterpretation 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.MethodsQuantitative 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.ResultsUsing 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.ConclusionsAutomated interpretation methods proved to be accurate and were considered to be useful by all participants.SignificanceComputer-assisted interpretation of the EEG background pattern can bring consistency to reviewing and improve efficiency and inter-rater agreement.

Opportunities and methodological challenges in EEG and MEG resting state functional brain network research

“…To avoid any possible influences of the digital filters on the recorded signal, it is therefore important to consider elimination of software based filtering or to use zero-phase filtering, for example by a forward and reversed filtering approach. (Lodder et al , 2014). The current complexity and limited transparency of automated detection systems demotivate researchers to use it on a larger scale (Anderson et al , 2010) although recent advances are promising (Shibasaki et al , 2014).…”

Predicting sex from brain rhythms with deep learning

“…For several decades, traditional machine learning techniques have been frequently applied to brain imaging data, including electroencephalography (EEG), with applications ranging from characterization of the EEG background pattern 18 , 19 or quantification of focal or global ischaemia 20 – 22 to detection of epileptiform discharges 23 , 24 and diagnostics in depression 16 . Common to most of these techniques is the requirement for prior assumptions to guide extraction of particular features to be used for classification 25 .…”

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

“…In this context, it will assume a very important role the possibility to develop some kind of semi-automated analysis with the aim to help clinicians and researchers during these very crucial steps. Few recent studies used computer-assisted tools to allow interpreting EEG background patterns [7,8] but, probably, as suggested by van Diessen et. al.…”