Heart rate and age modulate retinal pulsatile patterns

Abstract

Theoretical models of retinal hemodynamics showed the modulation of retinal pulsatile patterns (RPPs) by heart rate (HR), yet in-vivo validation and scientific merit of this biological process is lacking. Such evidence is critical for result interpretation, study design, and (patho-)physiological modeling of human biology spanning applications in various medical specialties. In retinal hemodynamic video-recordings, we characterize the morphology of RPPs and assess the impact of modulation by HR or other variables. Principal component analysis isolated two RPPs, i.e., spontaneous venous pulsation (SVP) and optic cup pulsation (OCP). Heart rate modulated SVP and OCP morphology (p_FDR < 0.05); age modulated SVP morphology (p_FDR < 0.05). In addition, age and HR demonstrated the effect on between-group differences. This knowledge greatly affects future study designs, analyses of between-group differences in RPPs, and biophysical models investigating relationships between RPPs, intracranial, intraocular pressures, and cardiovascular physiology.

Fig. 1. Image and statistical analysis workflow.

a The block diagram summarizes the whole image and statistical analysis workflow. ONH optic nerve head, ROI region of interest, SVP spontaneous venous pulsation, OCP optic cup pulsation, T period [s], Ampl amplitude, SlpD slope-down, SlpU slope-up, t_p time to peak, V_T total relative pulse stroke volume, ANCOVA analysis of covariance. b The block diagram summarizes the input-output system of the utilized principal component analysis (PCA). The left input side demonstrates array operations forming the PCA input matrix. The right output side demonstrates temporal and spatial extraction of the results. x, y spatial axes of images, n_t total number of time points, m total number of pixels of the ROI in one time point, n₁ index of the principal component number 1 in the output principal component and eigenvector matrices (first red-highlighted columns), and time point number 1 in the PCA input matrix. Each column in the eigenvector matrix represents an eigenvector time-course of the principal component in the corresponding column of the principal component matrix. In the right bottom corner, the thresholded n1 principal component of m-samples was reshaped back into the original xy space and overlayed the averaged anatomical background image. All images show recordings of the left eye.

Fig. 2. Heart rate modulated morphology of spontaneous venous pulsations (SVP).

a Visualization of mean single-pulses over all monocular (mono) and binocular (bino) retinal video-recordings from healthy controls and patients with medicated ocular hypertension (OHT). Graph lines are heart rate color-coded. b Evaluation of linear dependence between heart rate and SVP morphology measurements (Ampl amplitude of the SVP eigenvector, V_T total relative pulse stroke volume in the eigenvector measures, SlpD slope-down from the eigenvector value at the period beginning to the negative eigenvector peak ≈ peak of the maximal absolute blood volume time-point, SlpU slope-up from the negative eigenvector peak to the period end, t_p time to the negative eigenvector peak). Value r represents a corresponding Pearson correlation coefficient and value p the p-value of the correlation level.

Fig. 3. Heart rate modulated morphology of optic cup pulsations (OCP).

a Visualization of mean single-pulses over all monocular (mono) and binocular (bino) retinal video-recordings from healthy controls and patients with medicated ocular hypertension (OHT). Graph lines are heart rate color-coded. b Evaluation of linear dependence between heart rate and OCP morphology measurements (Ampl amplitude of the OCP eigenvector, V_T total relative pulse stroke volume in the eigenvector measures, SlpD slope-down from the eigenvector value at the period beginning to the negative eigenvector peak ≈ peak of the maximal absolute blood volume time-point, SlpU slope-up from the negative eigenvector peak to the period end, t_p time to the negative eigenvector peak). Value r represents a corresponding Pearson correlation coefficient and value p the p-value of the correlation level.

Fig. 4. Representative examples of heart rate (HR) dependent intra-participant variability of retinal pulsatile patterns in one healthy control and two medicated ocular hypertension (OHT) patients.

For each participant, one retinal video-recording (RVR) was acquired with the monocular video-ophthalmoscope (VO) utilizing the CCD camera chip and one with the binocular VO utilizing the CMOS camera chip. The between-acquisition time interval was about two years for each representative participant. In healthy control and one OHT participant (OHT1), intra-participant RPP morphologies were dissimilar at different HR while RPP morphology remained unchanged for comparable HR as captured for other OHT participant (OHT2). Another OHT participant had different HR over acquisitions with similar outcomes as presented for the OHT1 participant. SVP spontaneous venous pulsations, OCP optic cup pulsations, HR heart rate.

Fig. 5. Evaluation of linear dependence between age and morphology of retinal pulsatile patterns.

Value r represents a corresponding Pearson correlation coefficient and value p is the p-value of the correlation level. SVP spontaneous venous pulsations, OCP optic cup pulsations, Ampl amplitude of the single-pulse in eigenvector space, V_T total relative pulse stroke volume in the eigenvector measures, SlpD slope-down from the eigenvector value at the period beginning to the negative eigenvector peak ≈ peak of the maximal absolute blood volume time-point, SlpU slope-up from the negative eigenvector peak to the period end, t_p time to the negative eigenvector peak.

Fig. 6. Group averaged OCP pulses with 25–75% confidence intervals.

Confidence intervals are visualized as color-matched dashed lines.