AI models to predict how dry powder inhalers deliver medicine in different lungs
ML-CFD-DEM Based Reduced Order Models (ROM) to Quantify Variability in Inhalers, Drugs, and Users for Evaluating Comparability of Generic OIDP Complex Products
This project builds AI-driven models to predict how dry powder inhalers deliver medicine across different inhalers, formulations, and people who use them.
Quick facts
| Grant type | U01 cooperative agreement |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Oklahoma State University Stillwater NIH-funded |
| Lab location | 1 site (Stillwater, United States) |
| Project ID | NIH-11182729 on NIH RePORTER |
What this research studies
The research team combines detailed computer fluid dynamics and particle simulations with machine learning to create faster, simplified models of inhaler behavior. They use realistic human airway shapes and account for differences in inhaler design, drug powders, and how patients breathe or coordinate with their device. The goal is to capture how these factors change where and how much medicine reaches the lungs while cutting the huge computing time of full simulations. Faster models can be used to compare generic and brand inhalers more efficiently and to understand variability across patient groups.
Who could benefit from this research
Good fit: People who use dry powder inhalers for conditions like asthma or COPD, or those interested in how device design affects drug delivery, are the most relevant population for this work.
Not a fit: People who do not use inhaled medications or who use other inhaler types (for example, pressurized metered-dose inhalers) are unlikely to see direct benefits from this project.
Why it matters
Potential benefit: If successful, this work could make it easier to confirm that generic inhalers deliver the same dose as brand products and help ensure more reliable inhaler performance for patients.
How similar studies have performed: High-fidelity airflow and particle simulations have helped inhaler research before, but combining CFD-DEM with machine-learned reduced-order models to speed regulatory comparisons is relatively new.
Where this research is happening
Stillwater, United States
- Oklahoma State University Stillwater — Stillwater, United States (Active)
Researchers
- Principal investigator: Feng, Yu — Oklahoma State University Stillwater
- Study coordinator: Feng, Yu
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.