Feature tracking microfluidic analysis reveals differential roles of viscosity and friction in sickle cell blood

Abstract

Characterization of blood flow rheology in hematological disorders is critical for understanding disease pathophysiology. Existing methods to measure blood rheological parameters are limited in their physiological relevance, and there is a need for new tools that focus on the microcirculation and extract properties at finer resolution than overall flow resistance. Herein, we present a method that combines microfluidic systems and powerful object-tracking computational technologies with mathematical modeling to separate the red blood cell flow profile into a bulk component and a wall component. We use this framework to evaluate differential contributions of effective viscosity and wall friction to the overall resistance in blood from patients with sickle cell disease (SCD) under a range of oxygen tensions. Our results demonstrate that blood from patients with SCD exhibits elevated frictional and viscous resistances at all physiologic oxygen tensions. Additionally, the viscous resistance increases more rapidly than the frictional resistance as oxygen tension decreases, which may confound analyses that extract only flow velocities or overall flow resistances. Furthermore, we evaluate the impact of transfusion treatments on the components of the resistance, revealing patient variability in blood properties that may improve our understanding of the heterogeneity of clinical responses to such treatments. Overall, our system provides a new method to analyze patient-specific blood properties and can be applied to a wide range of hematological and vascular disorders.

Fig. 1. Device design and experimental setup. Our microfluidic device is a three-layer device with a (a) gas, (b) hydration, and (c) blood layer allowing blood flow shear rate and oxygen tension to be methodically controlled while time-resolved images are collected. (d) The multilayer device is fabricated using PDMS to PDMS plasma bonding techniques. The needle ports for fluid and gas inlets and outlets are punched and the PDMS device is subsequently bonded to glass (see Methods). (e) A cross sectional view of the device shows how the blood layer is separated from the hydration layer by 100 μm of PDMS (see Methods). The hydration layer is separated from the gas layer by 100 μm of PDMS using the same technique. The gas layer was fabricated to be 4 mm thick (images are not to scale). (f) For the experimental setup, a combination of hardware and controls systems are used to perfuse blood, maintain hydration, deliver different oxygen concentrations, and detect oxygen levels. An inverted, bright field microscope allows blood flow to be visualized and images to be acquired using a high-speed camera (representative figure, images are not drawn to scale).

Fig. 2. Quantification of red blood cell 1D velocity fields. (a) Bright field image of blood adjusted to 25% hematocrit (hct) inside the microfluidic device. The channel walls are automatically detected (red lines) and the feature-tracking algorithm is contained within this region of interest. (b) Implementation of the KLT algorithm using the MATLAB Computer Vision Toolbox and the MATLAB point tracker object identifies points of interest (blue ‘+’ symbols) in the initial frame of a 4-frame image stack. (c) Red blood cell velocities are calculated using the x-coordinate displacements computed from tracking the location of the points in sequential frames (see Methods). Velocities with the highest magnitude (green) are found in the center of the channel while velocities with the lowest magnitude (blue) are found near the channel walls. (d) Visual representation of the cross-sectional binning along the channel width for 30 bins. (e) Raw velocity data for each tracked point prior to binning as a function of channel width (black data points). Plot of binned velocity (30 bins, red data points). (f) Validation of RBC velocities determined manually and computationally (Pearson r = 0.98 and r₂ = 0.96). (image scale bar = 20 μm).

Fig. 3. Qualitative and quantitative oxygen dependence of representative samples of healthy (HbAA) and SCD (HbSS) blood flow. All samples fixed to 25% hct (see Methods). (a) Raw velocity profiles for one SCD sample at a fixed pressure drop indicate that the velocity decreases with decreasing oxygen tension but also qualitatively the profiles seem to flatten. Black lines show the curve fit to eqn (7) for each oxygen tension. (b) Healthy donor sample profiles show no response to oxygen tension at fixed pressure drop. (c and d) Comparison of SCD and healthy sample maximum velocity. (e and f) Comparison of SCD and healthy sample slip velocity factor (V_wall/V_max). (g and h) Comparison of SCD and healthy sample bluntness index (b). Error bars represent sample-specific confidence interval for the fit of the velocity profile to eqn (7) at each oxygen tension.

Fig. 4. Evaluation of effective material properties of SCD blood across a range of samples. (a) Bluntness index, (b) overall resistance, (c) frictional resistance, and (d) viscous resistance. The differences in overall and viscous resistance between HbSS and HbAA samples are statistically significant at 12% oxygen tension. This finding shows a systemic effect that even at arterial level oxygen tensions (12%), HbSS sample blood flow properties are affected. Sample information: 12 HbSS samples, 6 HbAA samples. p values correspond to p* < 0.05 and p** < 0.001 using a Mann–Whitney U test in GraphPad Prism version 9.0.

Fig. 5. In vitro transfusion therapy experiment reveals increasing healthy to SCD blood ratios (indicated by decreasing HbS concentrations) leads to a loss of blood rheological dependence on oxygen tension, with heterogeneity in patient responses to transfusion. (a–c) Viscous resistance, (d–f) frictional resistance, and (g–i) bluntness index results for 3 patients at 3 different oxygen tensions (0%, 6%, and 12%). Patient 1 (column 1), patient 2 (column 2) and patient 3 (column 3) HbS concentrations before transfusion were 82.1%, 74.8% and 93.8%, respectively, and correspond to a SCD : healthy blood ratio of 100 : 0.