Machine learning to reduce unnecessary lab tests in the pediatric ICU
ML-ROVER: Machine Learning to Reduce Laboratory Test Overutilization
This project uses computer learning to help reduce unnecessary blood and lab tests for children in intensive care.
Quick facts
| Grant type | R21 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Rochester NIH-funded |
| Lab location | 1 site (Rochester, United States) |
| Project ID | NIH-11144546 on NIH RePORTER |
What this research studies
Researchers will combine electronic health record data from multiple pediatric intensive care units to train machine-learning models that predict when common lab tests are likely unnecessary. They will focus on children because smaller blood volumes make repeated testing more likely to cause anemia and other harms. The team will design and build easy-to-use electronic decision-support tools with input from bedside clinicians and test them in staged phases. The goal is to reduce avoidable blood draws and improve safety and care quality for critically ill children.
Who could benefit from this research
Good fit: Children admitted to pediatric intensive care units who undergo frequent laboratory testing are the primary group who could be included or benefit.
Not a fit: Patients outside pediatric intensive care (for example adults) or children who require frequent tests for unstable conditions may not benefit from this work.
Why it matters
Potential benefit: If successful, this could mean fewer unnecessary blood draws, less iatrogenic anemia, and safer care for children in intensive care.
How similar studies have performed: Some adult-focused machine-learning models have shown promise at reducing low-value testing, but such approaches are largely untested in children and rarely integrated into real-world clinical workflows.
Where this research is happening
Rochester, United States
- University of Rochester — Rochester, United States (Active)
Researchers
- Principal investigator: Dziorny, Adam C. — University of Rochester
- Study coordinator: Dziorny, Adam C.
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.