Computer screening to spot child physical abuse early in ERs
Natural Language Screening to Improve Early Recognition of Child Physical Abuse in Emergency Care Settings
This project uses computer analysis of doctors' notes to help emergency and urgent care teams find signs of physical abuse in infants and young children.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Colorado Denver NIH-funded |
| Lab location | 1 site (Aurora, UNITED STATES) |
| Project ID | NIH-11194443 on NIH RePORTER |
What this research studies
If my child goes to the ER with an injury, this project would use automated language analysis of the doctor's notes in the electronic health record to look for patterns that suggest physical abuse. The team will run a natural language processing (NLP) screener that reads unstructured clinical narratives and flags concerning signs like bruises, fractures, or inconsistent histories. They built and internally validated one tool and will externally validate and test it in emergency and urgent care settings to see how well it finds missed cases. The system runs in the background to support clinicians, aiming to reduce missed abuse and limit bias in recognition.
Who could benefit from this research
Good fit: Children (approximately 0–11 years old) who present to emergency departments or urgent care with injuries such as bruises, contusions, fractures, or unclear injury histories would be the focus of this work.
Not a fit: Children who do not visit participating emergency or urgent care clinics, who have non-injury visits, or whose medical records lack narrative detail are unlikely to be flagged by this screening approach.
Why it matters
Potential benefit: If successful, this could help identify abused children sooner, preventing repeat injuries and reducing the risk of severe harm or death.
How similar studies have performed: Automated NLP screeners for clinical notes have shown promise and internal validation, but external validation and real-world testing for child abuse detection remain limited.
Where this research is happening
Aurora, UNITED STATES
- University of Colorado Denver — Aurora, United States (Active)
Researchers
- Principal investigator: Lindberg, Daniel M — University of Colorado Denver
- Study coordinator: Lindberg, Daniel M
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.