Unresolved RBCs: An upscaling strategy for the CFD-DEM simulation of blood flow with deformable cells.

Numerical simulation of blood flow is a challenging topic due to the multiphase nature of this biological fluid. The choice of a specific method among the ones available in literature is often motivated by the physical scale of interest. Single-phase approximation allows for lower computational time, but does not consider this multiphase nature. Cell-level simulation, on the other hand, requires high computational resources and is limited to small scales. This work proposes a scale-up approach for cell-level simulation of blood flow, in the framework of unresolved CFD-DEM technique. This method offers the possibility to simulate hundreds of thousands of particles with limited computational effort, but requires specific models for fluid-particle interactions. Regarding blood flow, drag and lift force acting on the red blood cells (RBCs) are responsible for several macroscopic blood characteristics. Despite several correlations available for drag and lift force acting on rigid particles, specific force models for the simulation of deformable particles compatible with RBCs physics are missing. This study employs data obtained from cell-level simulations to derive equations then used in unresolved simulation of RBCs. The strategy followed during the modeling phase is presented, together with the model verification and validation. This approach returns satisfying results when used to simulate blood flow in large-scale channels. Up to half a million RBCs are considered, and computational effort is reported to allow a comparison with other existing methods. Future perspectives include further improvement of the model, such as a deeper understanding of particle-particle interactions.

Consequence of Red Blood Cells Deformability on Heat Sink Effect of Blood in a Three-Dimensional Bifurcated Vessel.

Several diseases like Sickle Cell Anemia, Thalassemia, Hereditary Spherocytosis, Malaria, and Micro-angiopathic Hemolytic Anemia can alter the normal shape of red blood cells (RBCs). The objective of this study is to gain insight into how a change in RBC deformability can affect blood heat transfer. The heat sink effect in a bifurcated vessel with two asymptotic cases (case 1: deformable and case 2: nondeformable RBCs) is being studied during hyperthermia treatment in a three-dimensional bifurcated vessel, whose wall is being subjected to constant heat flux boundary condition. Euler-Euler multiphase method along with the granular model and Kinetic theory is used to include the particle nature of RBCs during blood flow in the current model. To enhance the efficiency of the numerical model, user-defined functions (UDFs) are imported into the model from the C++ interface. The numerical model used is verified with the experimental results from (Carr and Tiruvaloor, 1989, "Enhancement of Heat Transfer in Red Cell Suspensions In Vitro Experiments," ASME J. Biomech. Eng., 111(2), pp. 152-156; Yeleswarapu et al. 1998, "The Flow of Blood in Tubes: Theory and Experiment," Mech. Res. Commun., 25(3), pp. 257-262). The results indicate that the deformability of RBCs can change both the flow dynamics and heat sink effect in a bifurcated vessel, which subsequently affects the efficacy and efficiency of the thermal ablation procedure. Both spatial and transient Nusselt numbers of blood flow with deformable RBCs are slightly higher compared to the one with nondeformable RBCs.

HIIT serves as an efficient training strategy for basketball players by improving blood fluidity and decreasing oxidative stress.

BACKGROUND: A challenge for coaches and athletes is to find the best combination of exercises during training. Considering its favorable effects, HIIT has been very popular recently. OBJECTIVE: The goal of this study was to investigate anthropometric features, performance, erythrocyte deformability, plasma viscosity (PV) and oxidative stress in response to acute and long-term (6 weeks) HIIT in adolescent basketball players. METHODS: 22 sportsmen between the ages of 14-16 were included. Tabata protocol was applied to the HIIT group in addition to their routine training program 3 days/week, for 6 weeks. Erythrocyte deformability was determined using an ectacytometer (LORCA), PV with a rotational viscometer. Total oxidant status (TOS), total antioxidant status (TAS) were measured by kits. RESULTS: HIIT for 6 weeks induced an improvement in performance tests and waist circumference. 6 weeks of HIIT resulted in a decrement, while the last exercise session yielded an increment in RBC deformability. PV and TOS of HIIT groups were decreased on the 6th week. CONCLUSIONS: Our results demonstrate that, HIIT in addition to the routine exercise program is beneficial for improving performance and blood fluidity as well as decreasing oxidative stress in basketball players. Therefore, HIIT seems as an efficient training strategy for highly-trained individuals.

Effect of Cell Age and Membrane Rigidity on Red Blood Cell Shape in Capillary Flow.

Blood flow in the microcirculatory system is crucially affected by intrinsic red blood cell (RBC) properties, such as their deformability. In the smallest vessels of this network, RBCs adapt their shapes to the flow conditions. Although it is known that the age of RBCs modifies their physical properties, such as increased cytosol viscosity and altered viscoelastic membrane properties, the evolution of their shape-adapting abilities during senescence remains unclear. In this study, we investigated the effect of RBC properties on the microcapillary in vitro flow behavior and their characteristic shapes in microfluidic channels. For this, we fractioned RBCs from healthy donors according to their age. Moreover, the membranes of fresh RBCs were chemically rigidified using diamide to study the effect of isolated graded-membrane rigidity. Our results show that a fraction of stable, asymmetric, off-centered slipper-like cells at high velocities decreases with increasing age or diamide concentration. However, while old cells form an enhanced number of stable symmetric croissants at the channel centerline, this shape class is suppressed for purely rigidified cells with diamide. Our study provides further knowledge about the distinct effects of age-related changes of intrinsic cell properties on the single-cell flow behavior of RBCs in confined flows due to inter-cellular age-related cell heterogeneity.

Tubulin-mediated anatomical and functional changes caused by Ca2+ in human erythrocytes.

In previous research, we observed that tubulin can be found in three fractions within erythrocytes, i.e., attached to the membrane, as a soluble fraction, or as part of a structure that can be sedimented by centrifugation. Given that its differential distribution within these fractions may alter several hemorheological properties, such as erythrocyte deformability, the present work studied how this distribution is in turn affected by Ca2+, another key player in the regulation of erythrocyte cytoskeleton stability. The effect of Ca2+ on some hemorheological parameters was also assessed. The results showed that when Ca2+ concentrations increased in the cell, whether by the addition of ionophore A23187, by specific plasma membrane Ca2 + _ATPase (PMCA) inhibition, or due to arterial hypertension, tubulin translocate to the membrane, erythrocyte deformability decreased, and phosphatidylserine exposure increased. Moreover, increased Ca2+ was associated with an inverse correlation in the distribution of tubulin and spectrin, another important cytoskeleton protein. Based on these findings, we propose the existence of a mechanism of action through which higher Ca2+ concentrations in erythrocytes trigger the migration of tubulin to the membrane, a phenomenon that results in alterations of rheological and molecular aspects of the membrane itself, as well as of the integrity of the cytoskeleton.

Dynamic response of red blood cells in health and disease.

The viscoelastic response of the red blood cells (RBCs) affected by hematological disorders become severely impaired by the altered biophysical and morphological properties. These include traits like reduced deformability, increased membrane viscosity, and change in cell shape, causing substantial changes in the overall hemodynamics. RBCs, by virtue of their highly elastic membrane and low bending rigidity, exhibit complex dynamics when exposed to cyclic, transient forces in the microcirculation. Here, we employ mesoscopic numerical simulations based on the dissipative particle dynamics (DPD) framework to explore the dynamics of healthy, schizont stage malaria-infected and type 2 diabetes mellitus affected RBCs subjected to external time-dependent loads. The paper focuses on the imposition and cessation of external forcing on the cells of two different typologies, saw-tooth cyclic wave loading and sudden loads in the form of creep and relaxation phenomena. The effects of varying the rate of stress and the applied stress magnitude were investigated. Our simulations disclosed unique shape transitions of the hysteresis curves at varied loading rates. A careful analysis reveals a critical threshold of half cycle time of the from wherein the deformation of all cells observed, healthy or otherwise, falls under the nearly reversible deformation regime displaying minimal energy dissipation. Finally, we also examined the individual effects of the different constitutive and geometric characteristics attributed to the pathological cells and observed interesting recovery dynamics of spherocytes and cells having high shear moduli. The distinguished deformation behaviour of healthy and diseased cells could establish external force as a valuable initial biomarker.

Effects of membrane viscoelasticity on the red blood cell dynamics in a microcapillary.

The mechanical properties of red blood cells (RBCs) play key roles in their biological functions in microcirculation. In particular, RBCs must deform significantly to travel through microcapillaries with sizes comparable with or even smaller than their own. Although the dynamics of RBCs in microcapillaries have received considerable attention, the effect of membrane viscoelasticity has been largely overlooked. In this work, we present a computational study based on the boundary integral method and thin-shell mechanics to examine how membrane viscoelasticity influences the dynamics of RBCs flowing through straight and constricted microcapillaries. Our results reveal that the cell with a viscoelastic membrane undergoes substantially different motion and deformation compared with results based on a purely elastic membrane model. Comparisons with experimental data also suggest the importance of accounting for membrane viscoelasticity to properly capture the transient dynamics of an RBC flowing through a microcapillary. Taken together, these findings demonstrate the significant effects of membrane viscoelasticity on RBC dynamics in different microcapillary environments. The computational framework also lays the groundwork for more accurate quantitative modeling of the mechanical response of RBCs in their mechanotransduction process in subsequent investigations.

Influence of storage and buffer composition on the mechanical behavior of flowing red blood cells.

On-chip study of blood flow has emerged as a powerful tool to assess the contribution of each component of blood to its overall function. Blood has indeed many functions, from gas and nutrient transport to immune response and thermal regulation. Red blood cells play a central role therein, in particular through their specific mechanical properties, which directly influence pressure regulation, oxygen perfusion, or platelet and white cell segregation toward endothelial walls. As the bloom of in-vitro studies has led to the apparition of various storage and sample preparation protocols, we address the question of the robustness of the results involving cell mechanical behavior against this diversity. The effects of three conservation media (EDTA, citrate, and glucose-albumin-sodium-phosphate) and storage time on the red blood cell mechanical behavior are assessed under different flow conditions: cell deformability by ektacytometry, shape recovery of cells flowing out of a microfluidic constriction, and cell-flipping dynamics under shear flow. The impact of buffer solutions (phosphate-buffered saline and density-matched suspension using iodixanol/Optiprep) are also studied by investigating individual cell-flipping dynamics, relative viscosity of cell suspensions, and cell structuration under Poiseuille flow. Our results reveal that storing blood samples up to 7 days after withdrawal and suspending them in adequate density-matched buffer solutions has, in most experiments, a moderate effect on the overall mechanical response, with a possible rapid evolution in the first 3 days after sample collection.

Accurate prediction of drug-induced heterogeneous response of red cell in vivo using a gravity-driven flow cytometry based on a microfluidic chip.

The drug-induced diverse response among patients is a severe problem for improving hemorheological character. However, there is no validated method for personalized therapy to the best of our knowledge. Here, we apply a gravity-driven deformability cytometry platform (GD-DCP) to profile the drug response of the red cell deformability (RCD) at the single-cell level using pentoxifylline (PTX) as a model drug, the effect of different concentrations of PTX (0, 2, 20, 200 µg mL-1, the clinical dosage of PTX is 20 µg mL-1) on RCD in patients with cardiovascular disease was explored. Based on the GD-DCP, about 38 and 56% of the acute phase of acute myocardial infarction (AMI) patients in the acute phase and coronary heart disease (CHD) patients respond positively to PTX, respectively, indicating that PTX has a strong patient dependency on RCD. Moreover, RCD is observed to be significantly inversely correlated with the activation of membrane protein kinase C (PKC) as well as the concentration of Ca2+ (both P < 0.001). The results of animal experiments show that the protective effects of PTX on myocardial ischemia rats have substantial individual variation, too. It is noted that the effect of PTX is highly consistent between RCD in vitro and in vivo outcomes (blood viscosity, myocardial injury, and electrocardiogram (ECG)) in the same rat. All these new findings suggest that the GD-DCP is a promising method that uses deformability in vitro as one of the important criteria in personalized medicine, and our study provides unique insight into the individual-dependent mechanisms of PTX for improving RCD.

Even patients with mild COVID-19 symptoms after SARS-CoV-2 infection show prolonged altered red blood cell morphology and rheological parameters.

Infection with the novel severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) and the associated coronavirus disease-19 (COVID-19) might affect red blood cells (RBC); possibly altering oxygen supply. However, investigations of cell morphology and RBC rheological parameters during a mild disease course are lacking and thus, the aim of the study. Fifty individuals with mild COVID-19 disease process were tested after the acute phase of SARS-CoV-2 infection (37males/13 females), and the data were compared to n = 42 healthy controls (30 males/12 females). Analysis of venous blood samples, taken at rest, revealed a higher percentage of permanently elongated RBC and membrane extensions in COVID-19 patients. Haematological parameters and haemoglobin concentration, MCH and MCV in particular, were highly altered in COVID-19. RBC deformability and deformability under an osmotic gradient were significantly reduced in COVID-19 patients. Higher RBC-NOS activation was not capable to at least in part counteract these reductions. Impaired RBC deformability might also be related to morphological changes and/or increased oxidative state. RBC aggregation index remained unaffected. However, higher shear rates were necessary to balance the aggregation-disaggregation in COVID-19 patients which might be, among others, related to morphological changes. The data suggest prolonged modifications of the RBC system even during a mild COVID-19 disease course.

Proteomic Analysis of the Role of the Adenylyl Cyclase-cAMP Pathway in Red Blood Cell Mechanical Responses.

Red blood cell (RBC) deformability is modulated by the phosphorylation status of the cytoskeletal proteins that regulate the interactions of integral transmembrane complexes. Proteomic studies have revealed that receptor-related signaling molecules and regulatory proteins involved in signaling cascades are present in RBCs. In this study, we investigated the roles of the cAMP signaling mechanism in modulating shear-induced RBC deformability and examined changes in the phosphorylation of the RBC proteome. We implemented the inhibitors of adenylyl cyclase (SQ22536), protein kinase A (H89), and phosphodiesterase (PDE) (pentoxifylline) to whole blood samples, applied 5 Pa shear stress (SS) for 300 s with a capillary tubing system, and evaluated RBC deformability using a LORRCA MaxSis. The inhibition of signaling molecules significantly deteriorated shear-induced RBC deformability (p < 0.05). Capillary SS slightly increased the phosphorylation of RBC cytoskeletal proteins. Tyrosine phosphorylation was significantly elevated by the modulation of the cAMP/PKA pathway (p < 0.05), while serine phosphorylation significantly decreased as a result of the inhibition of PDE (p < 0.05). AC is the core element of this signaling pathway, and PDE works as a negative feedback mechanism that could have potential roles in SS-induced RBC deformability. The cAMP/PKA pathway could regulate RBC deformability during capillary transit by triggering significant alterations in the phosphorylation state of RBCs.

A computational study of red blood cell deformability effect on hemodynamic alteration in capillary vessel networks.

Capillary blood vessels, the smallest vessels in the body, form an intricate network with constantly bifurcating, merging and winding vessels. Red blood cells (RBCs) must navigate through such complex microvascular networks in order to maintain tissue perfusion and oxygenation. Normal, healthy RBCs are extremely deformable and able to easily flow through narrow vessels. However, RBC deformability is reduced in many pathological conditions and during blood storage. The influence of reduced cell deformability on microvascular hemodynamics is not well established. Here we use a high-fidelity, 3D computational model of blood flow that retains exact geometric details of physiologically realistic microvascular networks, and deformation of every one of nearly a thousand RBCs flowing through the networks. We predict that reduced RBC deformability alters RBC trafficking with significant and heterogeneous changes in hematocrit. We quantify such changes along with RBC partitioning and lingering at vascular bifurcations, perfusion and vascular resistance, and wall shear stress. We elucidate the cellular-scale mechanisms that cause such changes. We show that such changes arise primarily due to the altered RBC dynamics at vascular bifurcations, as well as cross-stream migration. Less deformable cells tend to linger less at majority of bifurcations increasing the fraction of RBCs entering the higher flow branches. Changes in vascular resistance also seen to be heterogeneous and correlate with hematocrit changes. Furthermore, alteration in RBC dynamics is shown to cause localized changes in wall shear stress within vessels and near vascular bifurcations. Such heterogeneous and focal changes in hemodynamics may be the cause of morphological abnormalities in capillary vessel networks as observed in several diseases.

Red Blood Cell Morphodynamics in Patients with Polycythemia Vera and Stroke.

Polycythemia vera (PV) is a Ph-negative myeloproliferative neoplasm (MPN) which is characterized by erythrocytosis and a high incidence of thrombotic complications, including stroke. The study aimed to evaluate red blood cell (RBC) morphodynamic properties in PV patients and their possible association with stroke. We enrolled 48 patients with PV in this cross-sectional study, 13 of which have a history of ischemic stroke. The control group consisted of 90 healthy subjects. RBC deformability and aggregation analysis were performed using a laser-assisted optical rotational red cell analyzer. The following parameters were calculated: aggregation amplitude (Amp), RBC rouleaux formation time constant (Tf), time of formation of three-dimensional aggregates (Ts), aggregation index (AI), rate of complete disaggregation (y-dis), and the maximal elongation of RBC (EImax). Statistical analysis was performed with the R programming language. There were significant differences in RBCs morphodynamics features between patients with PV and the control group. Lower EImax (0.47 (0.44; 0.51) vs. 0.51 (0.47; 0.54), p < 0.001) and γ-dis (100 (100; 140) vs. 140 (106; 188) s-1, p < 0.001) along with higher amplitude (10.1 (8.6; 12.2) vs. 7.7 (6.6; 9.2), p < 0.001) was seen in patients with PV compared with control. A statistically significant difference between PV patients with and without stroke in aggregation amplitude was found (p = 0.03). A logistic regression model for stroke was built based on RBC morphodynamics which performed reasonably well (p = 0.01). RBC alterations may be associated with overt cerebrovascular disease in PV, suggesting a possible link between erythrocyte morphodynamics and increased risk of stroke.

Numerical investigation of blood flow and red blood cell rheology: the magnetic field effect.

In this study, the motion and deformation of a red blood cell in a Poiseuille flow through microvessels under the effect of a uniform transverse magnetic field is comprehensively investigated to get a better insight into blood hemorheology. The rheology of the RBC and the surrounding blood flow are examined numerically in two dimensions using a Finite Element Method. It is essential to know that the flow patterns of blood change in the presence of an RBC. The simulation results demonstrate that the magnetic field has significant influence on the flow stream and the behavior of the RBC, including the motion and the cells deformation.

The ektacytometric elongation Index (EI) of erythrocytes, validation of a prognostic, rheological biomarker for patients with sickle cell disease.

OBJECTIVES: Validation of the measurement of erythrocyte deformability as a useful prognostic, rheological biomarker for patients with sickle cell disease (SCD). METHODS: The degree of reduced deformability was based on the value of the maximum elongation index (EImax ) of the deformability curve of an osmotic gradient ektacytometer. The performance of this technique was analytically and clinically validated by analysing 200 normal subjects and 100 patients with well-documented thalassemia's and Hb variants in relation to their clinical condition. RESULTS: In this study, we show that EImax is a reproducible parameter with a small inter-individual coefficient of (Biological) variation (CV)=1.6% and a small intra-individual CV=3.5%. We demonstrate that loss of deformability correlates with the clinical condition and the various mutations underlying sickle cell disease and thalassemia. For SCD patients, a strongly reduced EImax with a cut-off =0.360 is a signal for future vaso-occlusive (VOC) events requiring hospitalisation with a specificity=85%, sensitivity=80%, PPV=81% and NPV=84% based on a ROC curve (AUC=0.89). CONCLUSION: This study validated the clinical utility of EImax as a prognostic marker for future clinical problems in individual high-risk SCD patients. In addition, EImax may help to achieve an adequate personal transfusion policy for an optimal blood flow in anaemic patients with SCD.

Erythrocyte morphological symmetry analysis to detect sublethal trauma in shear flow.

The viscoelastic properties of red blood cells (RBC) facilitate flexible shape change in response to extrinsic forces. Their viscoelasticity is intrinsically linked to physical properties of the cytosol, cytoskeleton, and membrane-all of which are highly sensitive to supraphysiological shear exposure. Given the need to minimise blood trauma within artificial organs, we observed RBC in supraphysiological shear through direct visualisation to gain understanding of processes leading to blood damage. Using a custom-built counter-rotating shear generator fit to a microscope, healthy red blood cells (RBC) were directly visualised during exposure to different levels of shear (10-60 Pa). To investigate RBC morphology in shear flow, we developed an image analysis method to quantify (a)symmetry of deforming ellipsoidal cells-following RBC identification and centroid detection, cell radius was determined for each angle around the circumference of the cell, and the resultant bimodal distribution (and thus RBC) was symmetrically compared. While traditional indices of RBC deformability (elongation index) remained unaltered in all shear conditions, following ~100 s of exposure to 60 Pa, the frequency of asymmetrical ellipses and RBC fragments/extracellular vesicles significantly increased. These findings indicate RBC structure is sensitive to shear history, where asymmetrical morphology may indicate sublethal blood damage in real-time shear flow.

Cellular transformers for targeted therapy.

Employing natural cells as drug carriers has been a hotspot in recent years, attributing to their biocompatibility and inherent dynamic properties. In the earlier stage, cells were mainly used as vehicles by virtue of their lipid-delimited compartmentalized structures and native membrane proteins. The scope emphasis was 'what cell displays' instead of 'how cell changes'. More recently, the dynamic behaviours, such as changes in surface protein patterns, morphologies, polarities and in-situ generation of therapeutics, of natural cells have drawn more attention for developing advanced drug delivery systems by fully taking advantage of these processes. In this review, we revolve around the dynamic cellular transformation behaviours which facilitate targeted therapy. Cellular deformation in geometry shape, spitting smaller vesicles, activation of antigen present cells, polarization between distinct phenotypes, local production of therapeutics, and hybridization with synthetic materials are involved. Other than focusing on the traditional delivery of concrete cargoes, more functional 'handles' that are derived from the cells themselves are introduced, such as information exchange, cellular communication and interactions between cell and extracellular environment.

Integrating deep learning with microfluidics for biophysical classification of sickle red blood cells adhered to laminin.

Sickle cell disease, a genetic disorder affecting a sizeable global demographic, manifests in sickle red blood cells (sRBCs) with altered shape and biomechanics. sRBCs show heightened adhesive interactions with inflamed endothelium, triggering painful vascular occlusion events. Numerous studies employ microfluidic-assay-based monitoring tools to quantify characteristics of adhered sRBCs from high resolution channel images. The current image analysis workflow relies on detailed morphological characterization and cell counting by a specially trained worker. This is time and labor intensive, and prone to user bias artifacts. Here we establish a morphology based classification scheme to identify two naturally arising sRBC subpopulations-deformable and non-deformable sRBCs-utilizing novel visual markers that link to underlying cell biomechanical properties and hold promise for clinically relevant insights. We then set up a standardized, reproducible, and fully automated image analysis workflow designed to carry out this classification. This relies on a two part deep neural network architecture that works in tandem for segmentation of channel images and classification of adhered cells into subtypes. Network training utilized an extensive data set of images generated by the SCD BioChip, a microfluidic assay which injects clinical whole blood samples into protein-functionalized microchannels, mimicking physiological conditions in the microvasculature. Here we carried out the assay with the sub-endothelial protein laminin. The machine learning approach segmented the resulting channel images with 99.1±0.3% mean IoU on the validation set across 5 k-folds, classified detected sRBCs with 96.0±0.3% mean accuracy on the validation set across 5 k-folds, and matched trained personnel in overall characterization of whole channel images with R2 = 0.992, 0.987 and 0.834 for total, deformable and non-deformable sRBC counts respectively. Average analysis time per channel image was also improved by two orders of magnitude (∼ 2 minutes vs ∼ 2-3 hours) over manual characterization. Finally, the network results show an order of magnitude less variance in counts on repeat trials than humans. This kind of standardization is a prerequisite for the viability of any diagnostic technology, making our system suitable for affordable and high throughput disease monitoring.

Dynamics of Deformation Properties of Erythrocytes in Wistar Rats during Postnatal Ontogeny.

We performed a detailed analysis of changes in the profiles of osmotic deformability using the method of gradient ektacytometry. Changes in all determinants that form the deformation properties of red blood cells in Wistar rats in the juvenile period and before puberty were determined. The dynamics of the formation of the rheological properties of the blood after birth is characterized by a wave-like change in the studied determinants. The changes are explained by adaptive reactions to extrauterine life as a result of hematopoiesis activation and the transition of the red bone marrow to a new level of functioning with the predominant replacement of physiological reticulocytosis in newborns with mature erythrocytes. The most critical period is from 10 days to 1 month after birth. Starting from the second month, the deformation parameters of erythrocytes are stabilized.

Numerical simulation of deformed red blood cell by utilizing neural network approach and finite element analysis.

In order to have research on the deformation characteristics and mechanical properties of human red blood cells (RBCs), finite element models of RBC optical tweezers stretching and atomic force microscope (AFM) indentation were established. Non-linear elasticity of cell membrane was determined by using the neo-Hookean hyperelastic material model, and the deformation of RBC during stretching and indentation had been researched in ABAQUS, respectively. Considering the application of machine learning (ML) in material parameters identification, ML algorithm was combined with finite element (FE) method to identify the constitutive parameters. The material parameters were estimated according to the deformation characteristics of RBC obtained from the change of cell diameter with stretching force when RBC was stretched. The non-linear relationship between material parameter and RBC deformation was established by building a FE-model. The FE simulation of RBC stretching was used to construct the training set and the neural network trained by a large number of samples was used to predict the material parameter. With the predicted parameter, FE simulation of RBC under AFM indentation to explore the local deformation mechanism was completed.