Automated Data Cleaning for the Muse EEG

Delorme, Arnaud; Martin, Jeffery A.

doi:10.1109/bibm52615.2021.9669415

“…Using this metric, we also showed that for relatively clean EEG acquired in laboratory conditions, preprocessing techniques had little effect on data quality. This might not be the case for more noisy data acquired in other conditions 7 . We hope future work continues to develop the proposed method to unveil a new era of automated signal processing for EEG, MEG, and iEEG.…”

Section: Discussionmentioning

confidence: 94%

EEG is better left alone

Delorme

¹

2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

Automated preprocessing methods are critically needed to process the large publicly-available EEG databases, but the optimal approach remains unknown because we lack data quality metrics to compare them. Here, we designed a simple yet robust EEG data quality metric assessing the percentage of significant channels between two experimental conditions within a 100 ms post-stimulus time range. Because of volume conduction in EEG, given no noise, most brain-evoked related potentials (ERP) should be visible on every single channel. Using three publicly available collections of EEG data, we showed that, with the exceptions of high-pass filtering and bad channel interpolation, automated data corrections had no effect on or significantly decreased the percentage of significant channels. Referencing and advanced baseline removal methods were significantly detrimental to performance. Rejecting bad data segments or trials could not compensate for the loss in statistical power. Automated Independent Component Analysis rejection of eyes and muscles failed to increase performance reliably. We compared optimized pipelines for preprocessing EEG data maximizing ERP significance using the leading open-source EEG software: EEGLAB, FieldTrip, MNE, and Brainstorm. Only one pipeline performed significantly better than high-pass filtering the data.

show abstract

“…This might not be the case for more noisy data acquired in other conditions. 7 We hope future work continues to develop the proposed method to unveil a new era of automated signal processing for EEG, MEG, and iEEG.…”

Section: Discussionmentioning

confidence: 99%

“…To our knowledge, only one dataset with marked rejections from multiple raters has been released. 7 We used this dataset to determine which automated artifact detection method yielded the best result and found that the chosen algorithm agreed more with each human than humans agreed between themselves. 7 While waiting for more of these manually labeled collections of datasets to test automated preprocessing and cleaning pipelines, we can use other methods to assess preprocessing data quality, namely, the amplitude of brain response to experimental conditions.…”

Section: Introductionmentioning

confidence: 99%

“…7 We used this dataset to determine which automated artifact detection method yielded the best result and found that the chosen algorithm agreed more with each human than humans agreed between themselves. 7 While waiting for more of these manually labeled collections of datasets to test automated preprocessing and cleaning pipelines, we can use other methods to assess preprocessing data quality, namely, the amplitude of brain response to experimental conditions. 3 Multiverse analyses scanning the space of preprocessing parameters are a step in that direction, although they still rely on pre-defined ERPs.…”

Section: Introductionmentioning

confidence: 99%

“…To our knowledge, only one dataset with marked rejections from multiple raters has been released. 7 We used this dataset to determine which automated artifact detection method yielded the best result and found that the chosen algorithm agreed more with each human than humans agreed between themselves. 7…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

EEG is better left alone

Delorme

¹

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Automated preprocessing methods are critically needed to process the large publicly-available EEG databases, but the optimal approach remains unknown because we lack data quality metrics to compare them. Here, we designed a simple yet robust EEG data quality metric assessing the percentage of significant channels between two experimental conditions within a 100 ms post-stimulus time range. Because of volume conduction in EEG, given no noise, most brain-evoked related potentials (ERP) should be visible on every single channel. Using three publicly available collections of EEG data, we showed that, with the exceptions of high-pass filtering and bad channel interpolation, automated data corrections had no effect on or significantly decreased the percentage of significant channels. Referencing and advanced baseline removal methods were significantly detrimental to performance. Rejecting bad data segments or trials could not compensate for the loss in statistical power. Automated Independent Component Analysis rejection of eyes and muscles failed to increase performance reliably. We compared optimized pipelines for preprocessing EEG data maximizing ERP significance using the leading open-source EEG software: EEGLAB, FieldTrip, MNE, and Brainstorm. Only one pipeline performed significantly better than high-pass filtering the data.

show abstract