Integrating Machine Learning with Computational Fluid Dynamics Models of Orally Inhaled Drug Products (U01) Clinical Trials Not Allowed

The Food and Drug Administration is seeking to advance the development of generic orally inhaled drug products by integrating machine learning with computational fluid dynamics models to overcome existing limitations in simulating inhaler performance. While CFD has become a valuable tool for bioequivalence assessments, reducing reliance on costly and time-intensive clinical trials, challenges such as computational speed, data resolution, model parameter estimation, and uncertainty quantification continue to hinder its broader application. This initiative aims to create a novel methodology that leverages machine learning to accelerate and enhance the accuracy of CFD simulations, providing a more efficient, scalable, and reliable alternative to traditional benchtop and clinical testing methods. The program, funded under a U01 grant mechanism, explicitly prohibits clinical trials and is focused solely on methodological development within computational modeling. It is part of the Department of Health and Human Services’ effort to modernize regulatory science for inhaled products, enabling faster approval pathways for generic inhalers without compromising safety or efficacy. Interested applicants must address the technical integration of machine learning algorithms with existing CFD frameworks to improve simulation fidelity, reduce computational burden, and facilitate robust uncertainty analysis. All proposals should align with the goal of supporting regulatory decision-making through innovative computational approaches. Inquiries should be directed to Terrin Brown, Grants Management Specialist at the FDA.