Stable decoding of working memory load through frequency bands. Issue 1 (2nd January 2023)

• Record Type: Journal Article
• Authors: Duleme, Meyi; Perrey, Stephane; Dray, Gerard
• Is Part Of: Cognitive neuroscience. Volume 14:Issue 1(2023)
• Page Start: 1
• Page End: 14
• Publication Date: 2023-01-02
• Subjects: Working memory -- EEG -- Machine learning -- Persistent -- N-back; Cognitive neuroscience -- Periodicals; 612.8205
• DOI: 10.1080/17588928.2022.2026312
• Languages: English
• ISSNs: 1758-8928

Abstract

ABSTRACT: Numerous studies have shown that working memory modulates every frequency band's power in the human brain. Yet, the question of how the highly distributed working memory adapts to external demands remains unresolved. Here, we explored frequency band modulations underlying working memory load, taking executive control under account. We hypothesized that synchronizations underlying various cognitive functions may be sequenced in time to avoid interference and that transient modulation of decoding accuracy of task difficulty would vary with increasing difficulty. We recorded whole scalp EEG data from 12 healthy participants, while they performed a visuo-spatial n-back task with three conditions of increasing difficulty, after an initial learning phase. We analyzed evoked spectral perturbations and time-resolved decoding of individual synchronization. Surprisingly, our results provide evidence for persistent decoding above the level-of-chance (83.17% AUC) for combined frequency bands. In fact, the decoding accuracy was higher for the combined than for isolated frequency bands (AUC from 65.93% to 74.30%). However, in line with our hypothesis, frequency band clusters transiently emerged in parieto-occipital regions within two separate time windows for alpha-/beta-band (relative synchronization from approximately 200 to 600 ms) and for the delta-/theta-band (relative desynchronization from approximately 600 to 1000 ms). Overall, these findings highlight concurrent sustained and transient measurable features of working memory load. This could reflect the emergence of stability within and between functional networks of the complex working memory system. In turn, this process allows energy savings to cope with external demands.