Auditory closed-loop stimulation of EEG slow oscillations strengthens sleep and signs of its immune-supportive function

Abstract

Sleep is essential for health. Slow wave sleep (SWS), the deepest sleep stage hallmarked by electroencephalographic slow oscillations (SOs), appears of particular relevance here. SWS is associated with a unique endocrine milieu comprising minimum cortisol and high aldosterone, growth hormone (GH), and prolactin levels, thereby presumably fostering efficient adaptive immune responses. Yet, whether SWS causes these changes is unclear. Here we enhance SOs in men by auditory closed-loop stimulation, i.e., by delivering tones in synchrony with endogenous SOs. Stimulation intensifies the hormonal milieu characterizing SWS (mainly by further reducing cortisol and increasing aldosterone levels) and reduces T and B cell counts, likely reflecting a redistribution of these cells to lymphoid tissues. GH remains unchanged. In conclusion, closed-loop stimulation of SOs is an easy-to-use tool for probing SWS functions, and might also bear the potential to ameliorate conditions like depression and aging, where disturbed sleep coalesces with specific hormonal and immunological dysregulations.

Fig. 1

Auditory stimulation phase locked to endogenous SO peaks boosts SO activity. a Setup: Upon online detection of an endogenous SO in the frontal EEG signal during non-rapid eye movement (NonREM) sleep, two tones (50 ms, pink noise, 50 dB SPL) were delivered via in-ear headphones with an inter-stimulus interval of 1.075 s to coincide with two consecutive SO peaks. In the Sham condition, time points of stimulation were marked, but no stimuli were presented. See “Methods” section for further details. Artwork by H.-V.V.N. b Mean (±s.e.m.) EEG signal recorded from a frontal (Fz) electrode position during NonREM sleep (S2, S3, and S4) in the 120-min stimulation period, time-locked to the first of the two tones (t = 0) for the Stimulation (STIM, black) and Sham condition (SHAM, gray). c Mean (±s.e.m.) normalized spectral power in the SO peak frequency band (0.8–1.1 Hz) and SO amplitude recorded from electrode position Fz and determined for NonREM sleep epochs of the 120-min stimulation period. The average number of NonREM sleep epochs used for this calculation was 158 and 169, respectively, for the Stimulation and the Sham condition. (There was no significant difference in the number of epochs between conditions, p = 0.123). For normalization, individual spectra were divided by the cumulative power (up to 30 Hz). **p < 0.01, *p < 0.05, for pairwise comparisons between the Stimulation condition (STIM, black) and the Sham condition (SHAM, gray) with paired t tests, two-sided. n = 14

Fig. 2

Impact of auditory SO stimulation on cortisol, aldosterone, and prolactin levels. Means (±s.e.m.) of cortisol (a, b), aldosterone (c), and prolactin (d) levels calculated for 1-h bins. Gray area represents the 120-min stimulation period. *p < 0.05, ^# p < 0.1 for pairwise comparisons between the Stimulation condition (STIM, black) and the Sham condition (SHAM, white) with Wilcoxon tests, two-sided. n = 10–14 (see “Methods” section for exact numbers)

Fig. 3

Impact of auditory SO stimulation on lymphocyte counts. Means (±s.e.m.) of circulating T and B cell numbers (shown as difference from baseline). Gray area represents the 120-min stimulation period. *p < 0.05 for pairwise comparisons between the Stimulation condition (STIM, black) and the Sham condition (SHAM, white) with Wilcoxon tests, two-sided. n = 9