Changes in electroencephalographic power and bicoherence spectra according to depth of dexmedetomidine sedation in patients undergoing spinal anesthesia

Abstract

Background: Assessment the depth of dexmedetomidine sedation using electroencephalographic (EEG) features can improve the quality of procedural sedation. Previous volunteer studies of dexmedetomidine-induced EEG changes need to be validated, and changes in bicoherence spectra during dexmedetomidine sedation has not been revealed yet. We aimed to investigate the dexmedetomidine-induced EEG change using power spectral and bicoherence analyses in the clinical setting. Patients and Methods: Thirty-six patients undergoing orthopedic surgery under spinal anesthesia were enrolled in this study. Dexmedetomidine sedation was conducted by the stepwise increase in target effect site concentration (Ce) while assessing sedation levels. Bispectral index (BIS) and frontal electroencephalography were recorded continuously, and the performance of BIS and changes in power and bicoherence spectra were analyzed with the data from the F3 electrode. Results: The prediction probability values for detecting different sedation levels were 0.847, 0.841, and 0.844 in BIS, 95% spectral edge frequency, and dexmedetomidine Ce, respectively. As the depth of sedation increased, δ power increased, but high β and γ power decreased significantly (P <0.001). α and spindle power increased significantly under light and moderate sedation (P <0.001 in light vs baseline and deep sedation; P = 0.002 and P <0.001 in moderate sedation vs baseline and deep sedation, respectively). The bicoherence peaks of the δ and α-spindle regions along the diagonal line of the bicoherence matrix emerged during moderate and deep sedation. Peak bicoherence in the δ area showed sedation-dependent increases (29.93%±7.38%, 36.72%±9.70%, 44.88%±12.90%; light, moderate, and deep sedation; P = 0.008 and P <0.001 in light sedation vs moderate and deep sedation, respectively; P = 0.007 in moderate sedation vs deep sedation), whereas peak bicoherence in the α-spindle area did not change (22.92%±4.90%, 24.72%±4.96%, and 26.96%±8.42%, respectively; P=0.053). Conclusions: The increase of δ power and the decrease of high-frequency power were associated with the gradual deepening of dexmedetomidine sedation. The δ bicoherence peak increased with increasing sedation level and can serve as an indicator reflecting dexmedetomidine sedation levels.

Keywords: bicoherence; bispectral index; depth of anesthesia; dexmedetomidine; power spectral analysis; quadratic phase coupling.

Figure 1

The change in the electroencephalogram (EEG) relative band powers during dexmedetomidine sedation. The box and whiskers plots demonstrate the ratio of EEG band power (δ, θ, α, spindle, high β and γ) at baseline and predefined sedation levels. The upper and lower limits of the box reflect the 75^th and 25^th percentiles of the sample, and the horizontal line inside each box indicates the median. The upper and lower notches reflect the 90^th and 10^th percentiles of the sample. Values below and above the notches are drawn as individual points. One-way ANOVA with repeated measures, followed by post hoc Bonferroni or Dunnet test (corrected P < 0.0083).

Figure 2

Averaged bicoherence spectra of all patients during light (A), moderate (B) and deep (C) dexmedetomidine sedation.

Figure 3

Power and bicoherence values along the diagonal lines of the bicoherence matrix under the three levels of sedation, shown as mean of all patients. A, Overlay of mean absolute power spectra of light (green), moderate (yellow), and deep sedation (blue); B, Mean bicoherence values along the diagonal lines of the bicoherence matrix of light (black), moderate (thin grey) and deep sedation (thick grey).

Figure 4

Peak bicoherence around diagonal lines in δ (0.5-4 Hz) and α-spindle (9-15 Hz) bands in all patients are respectively summarized in three sedation levels. The upper and lower limits of the box reflect the 75^th and 25^th percentiles of the sample, and the horizontal line inside each box indicates the median. The upper and lower notches reflect the 90^th and 10^th percentiles of the sample. Values below and above the notches are drawn as individual points. One-way ANOVA with repeated measures, followed by post hoc Bonferroni test (corrected P < 0.0167).