Using AI to improve safety in radiation therapy treatment planning
Official title: Development and Assessment of Artificial Intelligence (AI)-Enhanced Pre-treatment Peer-review Process to Improve Patient Safety in Radiation Oncology
Funded at Univ of North Carolina Chapel Hill · NIH-11062383 · Data updated 2026-11-12
This study is testing a new AI tool to help doctors in radiation therapy work together better and make fewer mistakes before starting treatment, all to keep patients safer and improve their care.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Univ of North Carolina Chapel Hill NIH-funded |
| Lab location | 1 site (Chapel Hill, United States) |
| Project start | April 1, 2024 |
| Project end | March 31, 2027 |
| Funding year | 2025 |
| Award (this year) | $450,000 |
| NIH project number | 5R18HS029474-02 |
| Project ID | NIH-11062383 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research are patients undergoing radiation therapy for cancer treatment.
✕Less likely to help
Patients who are not receiving radiation therapy or those whose treatment plans are not subject to peer review may not benefit from this research.
What this research studies
This research aims to develop and implement an artificial intelligence (AI) and machine learning (ML) intervention to enhance the pre-treatment peer-review process in radiation oncology. By focusing on reducing physician variability, the project seeks to improve the performance of radiation therapy providers and ultimately enhance patient safety. The effectiveness of this intervention will be evaluated in real clinical settings, measuring the impact on treatment planning errors that can affect patient outcomes. The study will involve analyzing data from radiation therapy cases before and after the implementation of the AI-enhanced peer-review process.
Why it matters
Potential benefit: If successful, this research could significantly reduce treatment planning errors in radiation therapy, leading to safer and more effective cancer treatment for patients.
How similar studies have gone: Other research has shown promising results using AI to enhance clinical processes, indicating that this approach has potential for success.
Where this research is happening
-
Univ of North Carolina Chapel Hill
Chapel Hill, United States Active
Researchers
- Principal investigator: Mazur, Lukasz — Univ of North Carolina Chapel Hill
- Study coordinator: Mazur, Lukasz
Related research
Other NIH-funded projects on the same topics.
-
Addressing fairness in AI models for asthma in young children
This grant aims to ensure AI tools used for diagnosing and managing asthma in children aged 0-11 work fairly for all socioeconomic and demographic groups.
-
Using AI and drug modeling to understand why genes and other medicines change clopidogrel response
This project uses AI, genetic data, and drug-response models to find why people with different genes or taking other medications respond differently to clopidogrel.
-
AI-powered tools to improve periodontal diagnosis and treatment decisions
A dental AI tool helps doctors diagnose periodontitis more accurately and tailor care for adults, using 2D/3D images and health records.
-
Data and AI Core for Cardiovascular and Metabolic Health (Core D)
A central data and AI hub at the University of Louisville will help researchers collect, harmonize, and analyze data to understand how nutrition, metabolism, and heart health influence disease.
-
Making asthma care AI work fairly for all children
This project aims to improve AI tools used in pediatric asthma care so they give fairer and more reliable results for children from different incomes and backgrounds.
-
Using artificial intelligence to improve treatment planning for patients in end-of-life care
This study is exploring how artificial intelligence can help doctors create personalized care plans for patients in end-of-life and palliative care, making sure that treatment choices reflect what patients and their families want while also looking at any concerns about fairness and patient control.
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.