Validation of the Openwater wearable optical system: cerebral hemodynamic monitoring during a breath-hold maneuver

Abstract

Significance: Bedside cerebral blood flow (CBF) monitoring has the potential to inform and improve care for acute neurologic diseases, but technical challenges limit the use of existing techniques in clinical practice.

Aim: Here, we validate the Openwater optical system, a novel wearable headset that uses laser speckle contrast to monitor microvascular hemodynamics.

Approach: We monitored 25 healthy adults with the Openwater system and concurrent transcranial Doppler (TCD) while performing a breath-hold maneuver to increase CBF. Relative blood flow (rBF) was derived from changes in speckle contrast, and relative blood volume (rBV) was derived from changes in speckle average intensity.

Results: A strong correlation was observed between beat-to-beat optical rBF and TCD-measured cerebral blood flow velocity (CBFv), $R=0.79$; the slope of the linear fit indicates good agreement, 0.87 (95% CI: 0.83 $-0.92$). Beat-to-beat rBV and CBFv were also strongly correlated, $R=0.72$, but as expected the two variables were not proportional; changes in rBV were smaller than CBFv changes, with linear fit slope of 0.18 (95% CI: 0.17 to 0.19). Further, strong agreement was found between rBF and CBFv waveform morphology and related metrics.

Conclusions: This first in vivo validation of the Openwater optical system highlights its potential as a cerebral hemodynamic monitor, but additional validation is needed in disease states.

Keywords: biomedical optics; breath-hold index; cerebral blood flow; cerebral hemodynamics; laser speckle contrast.

Fig. 1

Experimental setup and raw time-series data: (a) A schematic of the Openwater headset, demonstrating the light source/detector positioning and the theoretical light path. (b) A photograph depicts the experimental set-up. The Openwater Headset is on the subject’s head, and the TCD probe is insonating the MCA. The Doppler probe is fixed to the Openwater Headset using a custom probe holder. The Openwater Headset is tethered to the console and the console is plugged into a wall outlet power source (i.e., no onboard battery). (c) The frontal lobe is probed by the Openwater Headset over the lateral aspect of the forehead. The MCA is insonated by TCD. (d) An example of time-series data demonstrates one subject’s hemodynamic data during the breath-hold maneuver. The blue line represents the speckle contrast (informative of flow). The red line represents the light intensity (informative of volume). The orange line represents CBFv as measured by TCD. The gray shaded region represents the time during which the subject was holding their breath.

Fig. 2

The histogram depicts how the speckle intensity varies in time during the baseline resting-state monitoring (prior to breath-hold) for a representative subject. Each time point (40 per second) exhibits a histogram of digital signals detected for each pixel across the whole sensor. The change in the histogram over time is reflective of the subject’s pulse (Video 1, MP4, 178 KB [URL: https://doi.org/10.1117/1.NPh.11.1.015008.s1]).

Fig. 3

Waveform morphology before and after breath-hold: Representative raw waveform data are depicted from a single subject. All waveforms amplitudes are normalized (i.e., setting the $y$-axis scale from 0 to 1). (a) Prior to the initiation of the breath-hold, 5 s of data is depicted with both modalities. The dicrotic notch and three peaks are identified (P1, P2, P3). (b) At the end of the breath-hold, a change in waveform morphology, in particular an increase in the relative amplitude of P2, can be appreciated with both modalities. Again, 5 s of data are depicted. CBFv indicates cerebral blood flow velocity.

Fig. 4

Comparing optical and TCD beat-to-beat monitoring: All data are normalized to the 30-s period preceding the breath-hold. Beat-to-beat mean values are calculated for each metric from the start of the breath-hold through 5 s after the completion of the breath-hold. Each color represents a different subject. (a) A scatterplot depicts the beat-to-beat mean rCBFv ($x$-axis) and the beat-to-beat mean rBF ($y$-axis). The overall correlation coefficient is 0.79. The average correlation coefficient (when calculated for each subject individually) is 0.88 ($\pm 0.42$). The slope of the mixed-effects linear model is 0.87 (95% CI: 0.83 to 0.92). (b) A Bland–Altman plot indicates beat-to-beat mean rCBFv is on average 5% smaller than beat-to-beat mean rBF. The gray shaded region represents the 95% confidence interval for agreement. (c) A scatterplot depicts the beat-to-beat mean rCBFv ($x$-axis) and the beat-to-beat mean rBV ($y$-axis). The overall correlation coefficient is 0.72. The average correlation coefficient (when calculated for each subject individually) is 0.85 ($\pm 0.51$). The slope of the mixed-effects linear model is 0.18 (95% CI: 0.17 to 0.19), which indicates that changes in rBV are smaller than changes in rCBFv. (d) A Bland–Altman plot indicates rCBFv is on average 10% larger than rBV. The gray shaded region represents the 95% confidence interval for agreement. A negative trend is evident and indicates that as the average value increases, the difference between CBFv and rBV increases. TCD indicates transcranial Doppler. rCBFv indicates TCD measured relative cerebral blood flow velocity. rBF indicates optically measured relative blood flow. rBV indicates optically measured relative blood volume.

Fig. 5

Calculating BHI with optics and TCD: The BHI was calculated for each metric. (a) A scatterplot depicts the BHI based on TCD-derived CBFv ($x$-axis) and the BHI based on optically derived rBF ($y$-axis). The correlation coefficient is 0.78. The linear regression coefficient is 0.85 (95% CI: 0.54 to 1.16). (b) A scatterplot depicts the BHI based on TCD-derived CBFv ($x$-axis) and the BHI based on optically derived rBV ($y$-axis). The correlation coefficient is 0.75. The linear regression coefficient is 0.22 (95% CI: 0.13 to 0.31). TCD indicates transcranial Doppler. rBF indicates optically measured relative blood flow. rBV indicates optically measured relative blood volume. rCBV indicates TCD measured relative CBFv. BHI indicates breath-hold index.

Fig. 6

Timing of the cerebral hemodynamic effect: Time (seconds) was calculated from the initiation of the breath-hold to the maximum effect for each metric. (a) A scatterplot depicts the time to maximum effect for rCBFv ($x$-axis) and for rBF ($y$-axis). The correlation coefficient is 0.92. The linear regression coefficient is 0.90 (95% CI: 0.72 to 1.08). (b) A scatterplot depicts the time to maximum effect for rCBFv ($x$-axis) and for rBV ($y$-axis). The correlation coefficient is 0.92. The linear regression coefficient is 0.91 (95% CI: 0.74 to 1.08). rBF indicates optically measured relative blood flow. rBV indicates optically measured relative blood volume. rCBV indicates relative CBFv. S indicates seconds.

Fig. 7

Timing of waveform features: For each subject, waveforms were averaged across the 30 s baseline period. A peak-finding algorithm identified the dicrotic notch, P1, P2, and P3. (a) A scatterplot depicts the timing of each peak based on rCBFv ($x$-axis) and rBF ($y$-axis). The correlation coefficient for P1 is 0.69, and the linear regression coefficient is 0.86 (95% CI: 0.63 to 1.08). The correlation coefficient for P2 is 0.82, and the linear regression coefficient is 0.75 (95% CI: 0.51 to 0.99). The correlation coefficient for P3 is 0.86, and the linear regression coefficient is 0.85 (95% CI: 0.45 to 1.26). (b) A scatterplot depicts the timing of the dicrotic notch based on CBFv ($x$-axis) and rBF ($y$-axis). The correlation coefficient is 0.84, and the linear regression coefficient is 0.70 (95% CI: 0.50 to 0.91). rBF indicates optically measured relative blood flow. rCBV indicates relative cerebral blood flow velocity. S indicates seconds.

Fig. 8

Change in PI and Aix during breath-hold: (a) A scatterplot depicts PI based on rCBFv ($x$-axis) and rBF ($y$-axis). Each subject has a data point pre-hold and post-hold. PI is smaller post-hold because the pulse pressure is reduced during hypercapnia. The correlation coefficient is 0.84. (b) A scatterplot depicts the Aix (i.e., P2/P1) based on rCBFv ($x$-axis) and rBF ($y$-axis). Each subject has a data point pre-hold and post-hold, and the Aix is larger post-hold that reflects a relative increase in the P2 amplitude. The correlation coefficient is 0.82. rBF indicates optically measured relative blood flow. rCBFv indicates relative cerebral blood flow velocity. PI indicates pulsatility index. AIx indicates augmentation index.

Fig. 9

The effect of pulse length on speckle contrast data: While maintaining a constant total energy per pulse ($400\mu \mathrm{J}$), blood flow measurements were compared between two pulse lengths (200 and $1000\mu \mathrm{s}$). (a) The $200\mu \mathrm{s}$ pulse width resulted in higher contrast and larger waveform amplitude. For both the (b) $200\mu \mathrm{s}$ and (c) $1000\mu \mathrm{s}$ pulse widths, each individual heartbeat was readily isolated and waveforms normalized; each waveform was plotted on the same axis. The dark black line represents the average of individual beats. The increased amplitude using $200\mu \mathrm{s}$ resulted in a higher SNR.