How AI Imaging is Transforming Pulmonary Fibrosis Drug Development
Some of the most promising drugs in respiratory disease research never make it to patients. It’s not because they don’t work—but because clinical trials struggle to prove their impact.
Progressive pulmonary fibrosis (PPF) is a disease that worsens over time, leading to irreversible lung scarring and loss of function. Measuring whether a treatment slows that decline is a major challenge. Traditional imaging techniques can detect scarring, but they fail to capture subtle, early improvements that could confirm a drug is working.
This is exactly what Qureight and Avalyn Pharma are tackling in their MIST study, a Phase 2b trial testing inhaled pirfenidone for PPF1. For the first time, AI-powered imaging analytics will be used to assess fibrosis progression—bringing precision to a field that has long relied on subjective interpretation.
The Measurement Problem That Slows Drug Development
PPF is difficult to track because small changes in lung function don’t always show up in conventional scans or breathing tests. Clinical trials often rely on forced vital capacity (FVC), which measures lung volume, but it’s an indirect marker of disease progression.
Why does this matter?
- Patients may improve, but existing tools aren’t sensitive enough to detect it.
- Regulatory agencies need hard data to approve new treatments.
- Trials take longer and cost more because they require large patient groups to confirm effectiveness.
If imaging could provide earlier, clearer signs of improvement, promising drugs could reach patients faster. This is where AI-powered imaging changes the game.
“Given the complex nature of PPF, we’ve made it a priority to leverage cutting-edge technology to measure treatment response in our ongoing MIST study.”
What AI Brings to Pulmonary Fibrosis Research
Qureight’s platform does something conventional scans can’t:
✔ Tracks fibrosis volume at a microscopic level, spotting treatment effects earlier.
✔ Analyzes lung compartments separately, revealing patterns hidden in overall scores.
✔ Delivers objective, repeatable data, making clinical trials more efficient2.
This makes a significant difference when evaluating whether an inhaled therapy like pirfenidone slows fibrosis progression.
Why AI in Clinical Trials Hasn’t Gone Mainstream (Yet)
If AI-powered imaging is so effective, why isn’t it standard practice?
🔹 Regulatory Validation Takes Time – The FDA and EMA are open to AI-powered biomarkers but require rigorous proof before accepting them as endpoints3.
🔹 Adoption Isn’t Equal Across the Globe – Countries like Japan and China have integrated AI into healthcare faster than Europe and North America, where regulatory complexity slows adoption4.
🔹 Data Standardization is a Bottleneck – Clinical trials run across multiple hospitals and imaging centers, each using different scanning protocols. AI models need consistent, high-quality data to be effective5.
“The key challenge for AI in clinical trials isn’t the technology—it’s how seamlessly it fits into existing regulatory and clinical workflows.”
For companies like Qureight and Avalyn, success will depend not just on proving that AI imaging works, but on demonstrating that regulators and clinicians can trust it.
How AI-Powered Imaging Will Shape Future Clinical Trials
The potential for AI-driven imaging extends far beyond pulmonary fibrosis. If MIST proves AI can accurately measure treatment response, expect to see:
🔹 Faster Drug Approvals – AI imaging could provide earlier proof of efficacy, reducing the need for long-duration trials.
🔹 Smarter Patient Selection – AI could identify which patients will benefit most from a treatment, improving trial success rates.
🔹 AI-Standardized Imaging in Global Trials – As AI biomarkers gain acceptance, we may see global adoption in respiratory, oncology, and neurological drug trials6.
“Our mission is to redefine precision medicine through AI in clinical trials, and this aligns perfectly with that of Avalyn in delivering effective and tolerable treatments for pulmonary fibrosis patients.”
Your Take: Will AI Reshape Drug Trials or Face More Roadblocks?
For biopharma leaders: If you’re not integrating AI-driven imaging into your clinical trials, your competitors likely are.
For digital health innovators: AI adoption isn’t just about technology—it’s about regulatory alignment and workflow integration.
Qureight and Avalyn’s partnership could redefine clinical trial standards, but AI-driven imaging still faces hurdles in validation, adoption, and standardization.
What do you think?
🔹 Will AI biomarkers become the norm in drug trials?
🔹 What challenges do you see in getting regulatory approval for AI-powered endpoints?
🔹 How can AI-driven imaging be scaled globally?
Let’s discuss—leave a comment below!
References
- Qureight and Avalyn Pharma Partnership Announcement – https://www.qureight.com/news/qureight-avalyn-partnership
- Raghu G, Remy-Jardin M, Myers JL, et al. Diagnosis of idiopathic pulmonary fibrosis: An official ATS/ERS/JRS/ALAT clinical practice guideline. (Am J Respir Crit Care Med.) – https://doi.org/10.1164/rccm.202003-0625ST
- FDA AI/ML-Based Software as a Medical Device Discussion Paper – https://www.fda.gov/media/152071/download
- EMA Reflection Paper on AI in Medicine Development – https://www.ema.europa.eu/en/documents/scientific-guideline/reflection-paper-use-artificial-intelligence-medicinal-product-lifecycle_en.pdf
- Wells AU, Brown KK, Flaherty KR, et al. Challenges in IPF clinical trials: The need for precision medicine. (Eur Respir J.) – https://doi.org/10.1183/13993003.01172-2020
- Various industry reports on AI applications in clinical trials.
