AI and single-cell tests to predict Crohn's disease course in children
Official title: Predicting Clinical Phenotypes in Crohn's Disease Using Machine Learning and Single-Cell 'omics
Funded at Duke University · NIH-11404078 · Data updated 2026-11-12
This project uses artificial intelligence plus single-cell and other molecular data to predict which children and teens with Crohn's disease will have mild versus severe or treatment‑resistant disease.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Duke University NIH-funded |
| Lab location | 1 site (Durham, United States) |
| Project start | March 25, 2025 |
| Project end | April 30, 2027 |
| Funding year | 2026 |
| Award (this year) | $594,663 |
| NIH project number | 5R01DK131491-04 |
| Project ID | NIH-11404078 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates are children and adolescents with a diagnosis of Crohn's disease—especially those recently diagnosed or who have available biopsy tissue and clinical records for analysis.
✕Less likely to help
Adults without pediatric-onset Crohn's, people without available biopsy samples or clinical data, and those with other digestive diseases like ulcerative colitis are unlikely to be included or directly benefit.
What this research studies
You would be part of efforts that combine clinical records, tissue biopsy images, and detailed single-cell molecular measurements to teach computer models how Crohn's disease progresses. Researchers will use archived and new patient samples and data, apply automated image analysis and machine learning to extract tissue features, and build predictive algorithms. Models will be tested and validated to see how well they identify kids likely to respond to standard anti‑TNF therapy or to develop strictures or penetrating complications. The goal is a tool that could help clinicians choose the right treatment earlier for each child.
Why it matters
Potential benefit: If successful, this work could help doctors personalize treatment earlier, reducing unnecessary delays to stronger therapy or surgery for children likely to develop severe disease.
How similar studies have gone: Previous prediction models using only clinical data had limited accuracy, and combining single-cell 'omics with machine learning is a promising but still relatively new approach.
Where this research is happening
-
Duke University
Durham, United States Active
Researchers
- Principal investigator: Syed, Sana — Duke University
- Study coordinator: Syed, Sana
Related research
Other NIH-funded projects on the same topics.
-
Site-specific gene-microbial interactions in children with Crohn’s disease
A child-focused study explores how genes and gut microbes interact in very young children with Crohn’s disease to understand why the disease starts and how it might be treated.
-
Ultrasound markers to measure Crohn’s disease activity
A Mayo Clinic team is testing new 3D ultrasound methods to reliably track inflammation and scarring in Crohn’s disease using safe, affordable imaging that could replace more costly scans.
-
Understanding abnormal sugar building blocks in Crohn’s disease to guide smarter therapies
This project looks at how a specific genetic variation affects how Crohn’s disease works and whether targeting that pathway could lead to new treatments.
-
How IL-23 Blockade in Crohn's Disease Changes Immune Cells
This study looks at how the IL-23 blocking therapy risankizumab affects immune cells in people with Crohn’s disease.
-
Metabolic signatures that predict outcomes in children with Crohn's
This project looks at metabolism patterns in children with Crohn's disease to help predict how their condition will progress and respond to treatments.
-
Pediatric Crohn’s Disease: Endoscopic and Imaging Healing with Anti-TNF Therapy
A large pediatric study will look at how endoscopic healing and imaging healing relate to pre-treatment factors in kids newly diagnosed with Crohn’s disease who start anti-TNF therapy.
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.