Research initiation award: AI-powered data framework for probing microscale blood flow

The National Science Foundation Division of Undergraduate Education awarded Florida A & M University $450,000 on September 1, 2026, under the HBCU Undergraduate Program Research Initiation Award to develop an AI-powered data framework for probing microscale blood flow. The project runs through August 31, 2029, and is performed in Tallahassee, Florida.

The award funds research combining computational modeling, artificial intelligence, and miniature laboratory devices that recreate tiny blood vessels to advance understanding of how blood flows through the body's smallest vessels. The project aims to link observable phenomena in flowing blood to its underlying physical properties, enabling scientists to better understand why blood flow becomes abnormal in diseases such as sickle cell disease and thrombotic microangiopathies. The knowledge generated will lay groundwork for future tools that improve disease assessment, monitor treatment response, and guide development of new therapies.

The Research Initiation Award supports junior and mid-career faculty at historically black colleges and universities who are building new research programs or redirecting existing ones. The award will advance the faculty member's research capability and effectiveness and improve research and teaching at the home institution. The project will also provide interdisciplinary research and training opportunities for undergraduate and graduate students at the intersection of engineering, biology, computation, and medicine.

Abstract

The historically black colleges and universities undergraduate program (hbcu-up) through research initiation awards (RIA) provide support for junior and mid-career faculty at historically black colleges and universities who are building new research programs or redirecting and rebuilding existing research programs. IT is expected that the award will help to further the faculty member's research capability and effectiveness and improve research and teaching at the home institution. This award will advance understanding of how blood flows at the smallest scales. Blood disorders contribute to heart attacks, strokes, excessive bleeding, and many other life-threatening conditions that affect millions of people each year. Although doctors can measure many components of blood, they still cannot directly determine how blood flows through the body?s smallest blood vessels, where many diseases begin. This project aims to develop new ways to understand and measure blood flow by combining computational modeling, artificial intelligence, and miniature laboratory devices that recreate the tiny blood vessels found in the human body. By linking what can be observed in flowing blood to its underlying physical properties, the research will enable scientists to better understand why blood flow becomes abnormal in diseases such as sickle cell disease and thrombotic microangiopathies. The knowledge generated by this project will lay the groundwork for future tools that can improve disease assessment, monitor treatment response, and guide the development of new therapies. The project will also provide interdisciplinary research and training opportunities for undergraduate and graduate students at the intersection of engineering, biology, computation, and medicine. Blood rheology governs microvascular blood flow, tissue perfusion, and thrombosis, yet rheological properties measured in bulk blood often differ substantially from those governing blood flow in the microcirculation, where confinement, heterogeneous cell distributions, and local hemodynamic conditions dominate blood behavior. Quantitative characterization of microscale hemorheology under pathophysiologic flow conditions remains a fundamental challenge. This research will develop a deep learning-powered data assimilation platform for probing microscale hemorheology by integrating multiscale computational modeling, physics-informed deep learning, and biomimetic microfluidic experiments. The project consists of three complementary objectives. The first objective will develop cell-resolved computational models to determine how cell mechanical properties, cell packing, and vessel geometry collectively influence the spatiotemporal evolution of blood viscosity and clot permeability under healthy and diseased hemodynamic conditions. The second objective will develop a physics-informed deep learning framework constrained by generalized navier?stokes equations to inversely infer microscale rheological properties directly from sparse microvascular flow kinematic data. The third objective will integrate imaging data from a microvasculature-on-a-chip device, flow physics, and synthetic training data within the physics-informed deep learning framework to enable quantitative characterization of microscale blood rheology from small blood samples. Together, these objectives will establish a unified data assimilation platform that quantitatively reconstructs microscale blood rheological properties from observable microvascular flow measurements. The resulting methodology will enable quantitative characterization of microscale hemorheology under physiologically relevant flow conditions and establish a general computational framework for inverse characterization of complex biological transport phenomena. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the foundation's intellectual merit and broader impacts review criteria.- subawards are not planned for this award.