PT  - JOURNAL ARTICLE
AU  - Pim Mostert
AU  - Anke Marit Albers
AU  - Loek Brinkman
AU  - Larisa Todorova
AU  - Peter Kok
AU  - Floris P. de Lange
TI  - Eye Movement-Related Confounds in Neural Decoding of Visual Working Memory Representations
AID  - 10.1523/ENEURO.0401-17.2018
DP  - 2018 Jul 01
TA  - eneuro
PG  - ENEURO.0401-17.2018
VI  - 5
IP  - 4
4099  - http://www.eneuro.org/content/5/4/ENEURO.0401-17.2018.short
4100  - http://www.eneuro.org/content/5/4/ENEURO.0401-17.2018.full
SO  - eNeuro2018 Jul 01; 5
AB  - A relatively new analysis technique, known as neural decoding or multivariate pattern analysis (MVPA), has become increasingly popular for cognitive neuroimaging studies over recent years. These techniques promise to uncover the representational contents of neural signals, as well as the underlying code and the dynamic profile thereof. A field in which these techniques have led to novel insights in particular is that of visual working memory (VWM). In the present study, we subjected human volunteers to a combined VWM/imagery task while recording their neural signals using magnetoencephalography (MEG). We applied multivariate decoding analyses to uncover the temporal profile underlying the neural representations of the memorized item. Analysis of gaze position however revealed that our results were contaminated by systematic eye movements, suggesting that the MEG decoding results from our originally planned analyses were confounded. In addition to the eye movement analyses, we also present the original analyses to highlight how these might have readily led to invalid conclusions. Finally, we demonstrate a potential remedy, whereby we train the decoders on a functional localizer that was specifically designed to target bottom-up sensory signals and as such avoids eye movements. We conclude by arguing for more awareness of the potentially pervasive and ubiquitous effects of eye movement-related confounds.