A Kansas State University assistant professor of engineering is working to develop a framework that better predicts disease progression and complications from drug interactions than traditional methods like animal testing.

Davood B. Pourkargar, assistant professor of chemical engineering in the Carl R. Ice College of Engineering, has received a $245,000 grant from the National Science Foundation to enhance the understanding of drug delivery dynamics through a multiscale modeling framework utilizing organ-on-a-chip experiments and machine learning.

The two-year project, “Physics-Informed Machine Learning with Organ-on-a-Chip Data for an In-Depth Understanding of Disease Progression and Drug Delivery Dynamics,” utilizes NSF funding that is focused on addressing the limitations of conventional animal modeling in drug development, emphasizing the ethical concerns and minimizing its use.

The research will leverage physicochemical-based multiscale models of healthy and diseased tissues, cutting-edge organ-on-a-chip experiments and machine learning to better predict disease progression and drug interactions.

“This innovative, physics-informed machine learning approach enhances organ-on-a-chip experiments, streamlining the preclinical process, improving drug efficacy and minimizing side effects,” Pourkargar said. “Ultimately, the project accelerates drug discovery, supports personalized treatments and fosters more efficient, affordable health care while reducing reliance on animal testing.”

The hybrid model being developed will surpass standard machine learning-based models, accurately extrapolating and interpolating organ-on-a-chip data with enhanced analytical simplicity, interpretability and a reduced need for training samples.

_ _ _

Photo via Kansas State University