Introducing RELAX: An automated pre-processing pipeline for cleaning EEG data - Part 1: Algorithm and application to oscillations

Bailey, Neil W.; Biabani, Mana; Hill, Aron T.; Miljevic, Aleksandra; Rogasch, N.C.; McQueen, Brittany; Murphy, Oscar W.; Fitzgerald, Paul B.

doi:10.1016/j.clinph.2023.01.017

Cited by 23 publications

(33 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To pre-process the EEG data, we used the automatic EEG cleaning toolbox RELAX to clean the data (Bailey et al, 2022a;Bailey et al, 2022b). First, data was high-pass filtered using a fourth-order Butterworth filter at 1Hz, and a notch filter was applied from 47 to 53Hz.…”

Section: Eeg Pre-processingmentioning

confidence: 99%

“…However, on the other hand, these aspects are also an advantage of the current study, as the design of the current study aligns with how rTMS treatment response prediction would be applied in the clinic (i.e., a naturalistic model), suggesting the translation of these findings into practice is plausible. The computation approach required to obtain the predictions in the current study also makes the translation of our results into practice plausible, as both the RELAX EEG pre-processing pipeline (Bailey et al, 2022a;Bailey et al, 2022b) and hctsa are freely available software (Fulcher et al, 2013), and the EEG data can be processed and hctsa feature set computed within 3-5 minutes per participant. However, although the pre-processing and prediction algorithm could be fully automated, clinics would still require access to EEG equipment and staff trained in the collection of EEG data.…”

Section: Limitationsmentioning

confidence: 99%

“…Following this, we tested which EEG pre-processing pipeline provided better classification results. We tested RELAX (Bailey et al, 2022a;Bailey et al, 2022b) and the pre-processing approach provided as the default with the TDBRAIN dataset (van Dijk, van Wingen, et al, 2022), assessing prediction accuracy from the first three principal components. We found that the RELAX pipeline provided 60% (+/-5.43%) balanced accuracy in 10fold cross validation tests, while the default approach provided 55% (+/-8.62%) balanced accuracy.…”

Section: Parameter Testingmentioning

confidence: 99%

“…As such, we selected to use eyes-closed recordings in our primary analysis to maximise our sample size and potential prediction accuracy. Given these tests, the pre-processing parameters that enabled the highest prediction accuracy of sex in the parameter testing dataset were using RELAX (Bailey et al, 2022a;Bailey et al, 2022b) to pre-process the data, using 30s epochs, down sampling the data to 250Hz, and using eyes-closed EEG recordings.…”

Section: Parameter Testingmentioning

confidence: 99%

See 3 more Smart Citations

Prediction of response to transcranial magnetic stimulation treatment for depression using electroencephalography and statistical learning methods, including an out-of-sample validation

Bailey,

Fulcher,

Arns

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: Repetitive transcranial magnetic stimulation (rTMS) has shown efficacy for treating depression, but not for all patients. Accurate treatment response prediction could lower treatment burden. Research suggests machine learning trained with electroencephalographic (EEG) data may predict response, but only a limited range of measures have been tested. Objectives: We used >7000 time-series features to comprehensively test whether rTMS treatment response could be predicted in a discovery dataset and an independent dataset. Methods: Baseline EEG from 188 patients with depression treated with rTMS (125 responders) were decomposed into the top five principal components (PCs). The hctsa toolbox was used to extract 7304 time-series features from each participant and PC. A classification algorithm was trained to predict responders from the feature matrix separately for each PC. The classifier was applied to an independent dataset (N = 58) to test generalizability on an unseen sample. Results: Within the discovery dataset, the third PC (which showed a posterior-maximum and prominent alpha power) showed above-chance classification accuracy (68%, pFDR = 0.005, normalised positive predictive value = 114%). Other PCs did not outperform chance. The model generalized to the independent dataset with above-chance balanced accuracy (60%, p = 0.046, normalised positive predictive value = 114%). Analysis of feature-clusters suggested responders showed more high frequency power relative to total power, and a more negative skew in the distribution of their time-series values. Conclusion: The dynamical properties of PC3 predicted treatment response with moderate accuracy, which generalized to an independent dataset. Results suggest treatment stratification from pre-treatment EEG may be possible, potentially enabling better outcomes than "one-size-fits-all" treatment approaches.

show abstract

Section: Eeg Pre-processingmentioning

confidence: 99%

Section: Limitationsmentioning

confidence: 99%

Section: Parameter Testingmentioning

confidence: 99%

Section: Parameter Testingmentioning

confidence: 99%

See 2 more Smart Citations

Prediction of response to transcranial magnetic stimulation treatment for depression using electroencephalography and statistical learning methods, including an out-of-sample validation

Bailey,

Fulcher,

Arns

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…(2) extreme kurtosis; (3) extreme drift; (4) extremely improbable voltage distributions and (5) extreme outlying amplitudes (Bailey et al, 2023a). Rejection of a maximum of 20% of electrodes was allowed and if >20% were marked for removal, only the worst 20% were removed.…”

Section: Tasks and Stimulimentioning

confidence: 99%

Obsessive–compulsive disorder (OCD) is associated with increased engagement of frontal brain regions across multiple event-related potentials

et al. 2023

View full text Add to dashboard Cite

Background Obsessive–compulsive disorder (OCD) is a psychiatric condition leading to significant distress and poor quality of life. Successful treatment of OCD is restricted by the limited knowledge about its pathophysiology. This study aimed to investigate the pathophysiology of OCD using electroencephalographic (EEG) event-related potentials (ERPs), elicited from multiple tasks to characterise disorder-related differences in underlying brain activity across multiple neural processes. Methods ERP data were obtained from 25 OCD patients and 27 age- and sex-matched healthy controls (HCs) by recording EEG during flanker and go/nogo tasks. Error-related negativity (ERN) was elicited by the flanker task, while N200 and P300 were generated using the go/nogo task. Primary comparisons of the neural response amplitudes and the topographical distribution of neural activity were conducted using scalp field differences across all time points and electrodes. Results Compared to HCs, the OCD group showed altered ERP distributions. Contrasting with the previous literature on ERN and N200 topographies in OCD where fronto-central negative voltages were reported, we detected positive voltages. Additionally, the P300 was found to be less negative in the frontal regions. None of these ERP findings were associated with OCD symptom severity. Conclusions These results indicate that individuals with OCD show altered frontal neural activity across multiple executive function-related processes, supporting the frontal dysfunction theory of OCD. Furthermore, due to the lack of association between altered ERPs and OCD symptom severity, they may be considered potential candidate endophenotypes for OCD.

show abstract

EEG microstates in early‐to‐middle childhood show associations with age, biological sex, and alpha power

Hill,

Bailey,

Zomorrodi

et al. 2023

Human Brain Mapping

View full text Add to dashboard Cite

Electroencephalographic (EEG) microstates can provide a unique window into the temporal dynamics of large‐scale brain networks across brief (millisecond) timescales. Here, we analysed fundamental temporal features of microstates extracted from the broadband EEG signal in a large (N = 139) cohort of children spanning early‐to‐middle childhood (4–12 years of age). Linear regression models were used to examine if participants' age and biological sex could predict the temporal parameters GEV, duration, coverage, and occurrence, for five microstate classes (A–E) across both eyes‐closed and eyes‐open resting‐state recordings. We further explored associations between these microstate parameters and posterior alpha power after removal of the 1/f‐like aperiodic signal. The microstates obtained from our neurodevelopmental EEG recordings broadly replicated the four canonical microstate classes (A to D) frequently reported in adults, with the addition of the more recently established microstate class E. Biological sex served as a significant predictor in the regression models for four of the five microstate classes (A, C, D, and E). In addition, duration and occurrence for microstate E were both found to be positively associated with age for the eyes‐open recordings, while the temporal parameters of microstates C and E both exhibited associations with alpha band spectral power. Together, these findings highlight the influence of age and sex on large‐scale functional brain networks during early‐to‐middle childhood, extending understanding of neural dynamics across this important period for brain development.

show abstract

Introducing RELAX: An automated pre-processing pipeline for cleaning EEG data - Part 1: Algorithm and application to oscillations

Cited by 23 publications

References 80 publications

Prediction of response to transcranial magnetic stimulation treatment for depression using electroencephalography and statistical learning methods, including an out-of-sample validation

Prediction of response to transcranial magnetic stimulation treatment for depression using electroencephalography and statistical learning methods, including an out-of-sample validation

Obsessive–compulsive disorder (OCD) is associated with increased engagement of frontal brain regions across multiple event-related potentials

EEG microstates in early‐to‐middle childhood show associations with age, biological sex, and alpha power

Contact Info

Product

Resources

About