AI-powered cancer data extraction improves accuracy in cancer registries
Official title: AI-Enhanced Methods for Cancer Surveillance: Improving Automated Information Extraction with DAC for Clinically Actionable Cancer Types
Funded at University of Kentucky · NIH-11433605 · Data updated 2026-11-12
A research project aims to make cancer registry reports faster and more reliable by improving an AI system that automatically reads pathology reports to classify cancer information.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Kentucky NIH-funded |
| Lab location | 1 site (Lexington, United States) |
| Project start | August 11, 2026 |
| Project end | July 31, 2031 |
| Funding year | 2026 |
| Award (this year) | $492,482 |
| NIH project number | 1R01CA316685-01 |
| Project ID | NIH-11433605 on NIH RePORTER |
Who could benefit from this research
✓Could help
Patients with cancer whose pathology reports are captured in SEER registries may indirectly benefit from faster and more accurate data processing.
✕Less likely to help
There may be no direct benefit for individual patients if you are not involved in data submission to SEER registries.
What this research studies
This project builds on a collaboration between national cancer and energy agencies to enhance an AI model already used by SEER registries. It focuses on reducing the number of reports the AI declines to classify by refining training methods and loss functions. The team will investigate how reporting gaps and evolving cancer terminology affect accuracy and how to fix them, so the model can help registries keep up with new knowledge. The goal is to maintain high accuracy while decreasing the need for human re-annotation and speeding up data availability for researchers and clinicians.
Why it matters
Potential benefit: If successful, the project could reduce manual chart review time and improve the timeliness and completeness of cancer data used for patient care and research.
How similar studies have gone: Previous AI methods achieved high accuracy but often abstained on a large fraction of reports; this project seeks to enhance those methods for broader coverage.
Where this research is happening
-
University of Kentucky
Lexington, United States Active
Researchers
- Principal investigator: Ellingson, Sally Rose — University of Kentucky
- Study coordinator: Ellingson, Sally Rose
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.