Electrical vestibular stimuli to enhance vestibulo-motor output and improve subject comfort

Abstract

Electrical vestibular stimulation is often used to assess vestibulo-motor and postural responses in both clinical and research settings. Stochastic vestibular stimulation (SVS) is a recently established technique with many advantages over its square-wave counterpart; however, the evoked muscle responses remain relatively small. Although the vestibular-evoked responses can be enhanced by increasing the stimulus amplitude, subjects often perceive these higher intensity electrical stimuli as noxious or painful. Here, we developed multisine vestibular stimulation (MVS) signals that include precise frequency contributions to increase signal-to-noise ratios (SNR) of stimulus-evoked muscle and motor responses. Subjects were exposed to three different MVS stimuli to establish that: 1) MVS signals evoke equivalent vestibulo-motor responses compared to SVS while improving subject comfort and reducing experimentation time, 2) stimulus-evoked vestibulo-motor responses are reliably estimated as a linear system and 3) specific components of the cumulant density time domain vestibulo-motor responses can be targeted by controlling the frequency content of the input stimulus. Our results revealed that in comparison to SVS, MVS signals increased the SNR 3-6 times, reduced the minimum experimentation time by 85% and improved subjective measures of comfort by 20-80%. Vestibulo-motor responses measured using both EMG and force were not substantially affected by nonlinear distortions. In addition, by limiting the contribution of high frequencies within the MVS input stimulus, the magnitude of the medium latency time domain motor output response was increased by 58%. These results demonstrate that MVS stimuli can be designed to target and enhance vestibulo-motor output responses while simultaneously improving subject comfort, which should prove beneficial for both research and clinical applications.

Figure 1. Raw EMG data and applied stimuli during each condition (SVS, MVS-S, MVS-4 and MVS-L).

A: 2.5 s of raw data depicting muscle EMG (r-mGAS) and anterior-posterior directed force (+ve anterior). B: 2.5 s of applied stimuli and power spectra for each of the stimulus conditions. Circles in MVS plots represent exact frequencies chosen to be included in each signal. SVS, stochastic vestibular stimulation; MVS, multisine vestibular stimulation; r-mGAS, right medial gastrocnemius; AP, anterior-posterior.

Figure 2. Assessment of system linearity using EMG and AP force data.

A: pooled (n = 8) power spectrum of EMG (top plots) and AP force (bottom plots) during the MVS-4 stimulus condition. Power at even and odd harmonic frequencies are similar to power at non-harmonic frequencies. B: nonlinear distortion test during the MVS-4 stimulus condition. Significant nonlinear distortions are detected when points exceed the horizontal segmented line representing the significance level of the F-distribution (α = 0.05).

Figure 3. Coherence-, gain- and phase-frequency estimates of stimulus conditions for stimulus-EMG (top) and stimulus-AP force (bottom).

A: pooled (n = 8) coherence plots for each stimulus condition. B: pooled (n = 8) gain plots for each stimulus condition. C: pooled (n = 8) phase plots for each stimulus condition. Gain and phase were plotted at frequencies with significant coherence and did not differ across stimulus conditions. Note the limited number of frequencies within the MVS-4 across the entire dynamic range and the limited number of frequencies in the MVS-L at high frequencies.

Figure 4. Pooled (n = 8) cumulant density estimates.

Responses indicate a biphasic response for both the stimulus-EMG (top plot) and stimulus-AP force estimates (bottom plot).

Figure 5. Reported psychophysical measures of intensity, unpleasantness and imbalance using visual analogue scales.

Error bars are the standard error (n = 8). *  = P<0.05, **  = P<0.01, ***  = P<0.001 indicate significant differences as obtained from the pairwise comparison of SVS and all MVS stimulus conditions using a Bonferroni correction for multiple comparisons.