Integrating Machine Learning with Computational Fluid Dynamics Models of Orally Inhaled Drug Products (U01) Clinical Trials Not Allowed
This grant aims to combine machine learning and computational fluid dynamics to improve generic inhaled drug development and approval through alternative bioequivalence studies.
Funder: Food and Drug Administration
Due Dates: Forecasted (Estimated Application Due Date not yet posted)
Funding Amounts: Estimated total program funding: $600,000 | Expected number of awards: 1
Summary: Supports development of methodologies integrating machine learning with computational fluid dynamics to advance alternative bioequivalence studies for generic orally inhaled drug products.
Key Information: This is a forecasted opportunity; application details and deadlines are not yet available.
Description
This grant opportunity from the Food and Drug Administration (FDA) aims to support research that integrates machine learning (ML) with computational fluid dynamics (CFD) models for orally inhaled drug products (OIDPs). The goal is to develop new methodologies that can overcome current CFD limitations—such as computational time, grid resolution, and data processing—by leveraging ML techniques. The ultimate objective is to promote alternative bioequivalence (BE) studies, thereby enhancing and accelerating the development and regulatory approval of generic OIDPs.
CFD has become a valuable tool for evaluating generic inhaler devices, offering a cost- and time-efficient complement to traditional benchtop and clinical studies. However, challenges remain in terms of computational demands and data complexity. ML is increasingly recognized as a promising approach to address these bottlenecks, and this grant seeks to advance the integration of ML and CFD for regulatory science and generic drug development.
