Multimodal AI to diagnose and understand inherited craniofacial conditions
Official title: Multimodal machine learning for diagnosis and mechanistic phenotyping of inherited diseases
Funded at Children's Hosp of Philadelphia · NIH-11539402 · Data updated 2026-11-12
A new AI-powered system will combine facial photos, clinical data, and genetic information to help diagnose congenital craniofacial conditions in newborns.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Children's Hosp of Philadelphia NIH-funded |
| Lab location | 1 site (Philadelphia, United States) |
| Project start | June 6, 2025 |
| Project end | June 5, 2027 |
| Funding year | 2026 |
| Award (this year) | $1,217,898 |
| NIH project number | 3OT2OD037960-01S1 |
| Project ID | NIH-11539402 on NIH RePORTER |
Who could benefit from this research
✓Could help
Newborns with craniofacial abnormalities or facial gestalt features suggestive of genetic syndromes, and their families, could benefit.
✕Less likely to help
Patients without craniofacial anomalies or without access to the required data types may not benefit.
What this research studies
This project aims to create an ethically grounded, data-driven multimodal AI tool that uses frontal face images, clinical notes, demographics, and phenotypes to improve diagnosis of genetic syndromes in newborns. It also plans to incorporate 4D facial scans, photos, health records, and omics data to highlight genes involved in craniofacial features. The work emphasizes real-world relevance by involving patients and clinicians in setting training and evaluation goals, and will deliver an open-source modular software that separates the AI model from the underlying data models. The study is led by Children’s Hospital of Philadelphia and targets early, accurate identification of craniofacial anomalies to enable timely care and intervention.
Why it matters
Potential benefit: If successful, this could speed up accurate diagnoses for newborns with facial-focused syndromes and guide personalized treatment plans.
How similar studies have gone: Prior AI efforts show promise in image-based diagnosis, but this project combines multimodal data for a more accurate genetic-syndrome diagnosis.
Where this research is happening
-
Children's Hosp of Philadelphia
Philadelphia, United States Active
Researchers
- Principal investigator: Wang, Kai — Children's Hosp of Philadelphia
- Study coordinator: Wang, Kai
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.