Daytime naps, motor memory consolidation and regionally specific sleep spindles

Abstract

Background: Increasing evidence demonstrates that motor-skill memories improve across a night of sleep, and that non-rapid eye movement (NREM) sleep commonly plays a role in orchestrating these consolidation enhancements. Here we show the benefit of a daytime nap on motor memory consolidation and its relationship not simply with global sleep-stage measures, but unique characteristics of sleep spindles at regionally specific locations; mapping to the corresponding memory representation.

Methodology/principal findings: Two groups of subjects trained on a motor-skill task using their left hand - a paradigm known to result in overnight plastic changes in the contralateral, right motor cortex. Both groups trained in the morning and were tested 8 hr later, with one group obtaining a 60-90 minute intervening midday nap, while the other group remained awake. At testing, subjects that did not nap showed no significant performance improvement, yet those that did nap expressed a highly significant consolidation enhancement. Within the nap group, the amount of offline improvement showed a significant correlation with the global measure of stage-2 NREM sleep. However, topographical sleep spindle analysis revealed more precise correlations. Specifically, when spindle activity at the central electrode of the non-learning hemisphere (left) was subtracted from that in the learning hemisphere (right), representing the homeostatic difference following learning, strong positive relationships with offline memory improvement emerged-correlations that were not evident for either hemisphere alone.

Conclusions/significance: These results demonstrate that motor memories are dynamically facilitated across daytime naps, enhancements that are uniquely associated with electrophysiological events expressed at local, anatomically discrete locations of the brain.

Figure 1

Experimental design. a, Both groups were trained in the morning and test 8 hr later. Following training, the Nap group obtained a 60–90 min midday sleep period, while the No nap group remained awake across the 8hr delay. b, The nap period was recorded with digitized polysomnography (PSG) using a referenced electrode montage. The electrode montage (represented by blue discs) included EEG sites C3 and C4, covering localized learning regions of interest (motor cortex), together with O1 and O2 sites (referenced to A1 and A2, left and right outer canthi). A bipolar left and right submental array was used for monitoring of EMG (not shown), while left and right EOG channels (L-EOG, R-EOG) were used for eye-movement evaluation. For reference purposes, the electrode array is superimposed on top of the known fMRI changes in activation that occur across a night of sleep (modified from ; EEG anatomical precision not inferred), demonstrating enhanced activation in the right, contralateral motor cortex (activation strength in red/yellow, display threshold; P<0.05^FWE).

Figure 2

Motor memory performance. a, Motor skill performance at the end of the initial training session (“post-training”) compared with later testing following the 8hr intervening period in the No Nap and Nap groups. b, Correlation between the extent of offline memory improvement and the amount of stage-2 NREM sleep obtained within the Nap group.

Figure 3

Spindle density and offline (nap) memory enhancement. a, Correlations between offline motor memory enhancement and spindle density in the non-learning hemisphere (electrode site C3) and learning hemisphere (electrode site C4) individually. b, Correlations between offline motor memory improvement and the subtracted difference in spindle density between the learning hemisphere versus the non-learning hemisphere (C4–C3). Pearson's correlation coefficients (r) and corresponding significance (p) are displayed within each correlation window.

Figure 4

Spindle power and offline motor memory enhancement. a, Spindle event-related time-frequency activity, evaluated across a 2 second epoch (0.5 seconds before spindle onset and the 1.5 seconds after), incorporating a frequency range of 1–30 Hz after band-pass filtering (12–16 Hz, encompassing sigma-band power), in the non-learning hemisphere (electrode site C3) and learning hemisphere (electrode site C4) individually. b, Corresponding correlations between motor memory improvement and mean spindle power. c, Subtracted difference in spindle power between the learning hemisphere versus the non-learning hemisphere (C4–C3). d, Corresponding correlation between motor memory improvement and subtracted spindle power (C4–C3). Spindle power is depicted in µV² (strength indicated by right side color bar). Pearson's correlation coefficients (r) and corresponding significance (p) are displayed within each correlation window.