Using machine learning to reduce unnecessary lab tests in pediatric intensive care.
Official title: ML-ROVER: Machine Learning to Reduce Laboratory Test Overutilization
Funded at University of Rochester · NIH-10948765 · Data updated 2026-11-12
This study is working to help doctors in pediatric intensive care units know when lab tests are really needed for kids, using smart computer tools to make sure tests are only done when they can truly help, which will lead to better care and fewer complications.
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 start | August 1, 2024 |
| Project end | July 31, 2026 |
| Funding year | 2024 |
| Award (this year) | $172,785 |
| NIH project number | 1R21HS030123-01 |
| Project ID | NIH-10948765 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research are pediatric patients in intensive care units who are at risk of undergoing unnecessary laboratory tests.
✕Less likely to help
Patients who are not in intensive care or do not require laboratory testing will likely not benefit from this research.
What this research studies
This research aims to tackle the issue of unnecessary laboratory tests in pediatric intensive care units, which can lead to complications like iatrogenic anemia. By utilizing machine learning techniques, the project seeks to develop predictive models that can identify when lab tests are truly needed, thereby improving patient care. The study will leverage existing electronic health records and clinical databases to create a more effective clinical decision support system tailored for pediatric patients. The goal is to ensure that lab tests are only performed when medically necessary, enhancing the overall quality of care.
Why it matters
Potential benefit: If successful, this research could significantly reduce the number of unnecessary lab tests, leading to better patient outcomes and reduced complications for children in intensive care.
How similar studies have gone: While there have been few predictive models for adults, this approach is novel in the pediatric context and has not been extensively tested.
Where this research is happening
-
University of Rochester
Rochester, United States Active
Researchers
- Principal investigator: Dziorny, Adam C. — University of Rochester
- Study coordinator: Dziorny, Adam C.
Related research
Other NIH-funded projects on the same topics.
-
Rapid automated breast lump diagnosis without a radiologist or sonographer
A new AI-powered ultrasound tool helps determine if a palpable breast lump is likely benign or malignant, using a simplified technique that can be used by people with minimal ultrasound training.
-
ML-ROVER: Reducing Unneeded Lab Tests in Kids with AI
Aims to use machine learning to cut unnecessary blood tests in children in intensive care, helping avoid anemia and improve care quality.
-
Aggressive fever-reducing therapy to protect the brains of children with CNS malaria
A study planned for children with CNS malaria will test whether aggressive fever-reducing treatment can lower death and brain-related problems.
-
Aggressive fever-reducing therapy to protect brains in children with CNS malaria
A plan to test whether giving strong fever-reducing medications to children with central nervous system malaria can lower death and brain injury.
-
Aggressive fever-fighting treatment to protect the brain in kids with CNS malaria
A plan to test whether giving strong fever-reducing treatment alongside standard care can lower death and brain injury in children with CNS malaria.
-
Aggressive fever-reducing treatment to protect brains in kids with CNS malaria
A plan to test whether giving strong fever-reducing medicine alongside standard malaria treatment can lower deaths and brain injuries in children with CNS malaria.
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.