Improving the automation of removing personal information from medical imaging data
Official title: AUTOMATED DEIDENTIFICATION OF PATHOLOGY AND RADIOLOGY DATA
Funded at Impact Business Information Solutions INC. · NIH-10904320 · Data updated 2026-11-12
This study is working on smart computer programs that can automatically find and hide personal health information in medical images and reports, making it easier and quicker to share important medical data for research while keeping your privacy safe.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Impact Business Information Solutions INC. NIH-funded |
| Lab location | 1 site (Princeton, United States) |
| Project start | August 15, 2023 |
| Project end | August 14, 2025 |
| Funding year | 2023 |
| Award (this year) | $1,998,445 |
| NIH project number | 75N91023C00041-0-9999-1 |
| Project ID | NIH-10904320 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research are patients whose medical imaging data may be used in research settings, particularly those with burn injuries or related conditions.
✕Less likely to help
Patients who do not have any medical imaging data or whose data is not relevant to burn injuries may not benefit from this research.
What this research studies
This research focuses on developing advanced algorithms to automatically detect and redact personal health information (PHI) from radiology and pathology data. By enhancing deep learning models and natural language processing capabilities, the project aims to minimize the need for manual review and increase the efficiency of deidentifying sensitive medical data. The approach includes creating a comprehensive workflow that integrates human oversight when necessary and accurately measures the confidence of the deidentification process. This could lead to faster and safer sharing of medical data for research and analysis.
Why it matters
Potential benefit: If successful, this research could significantly streamline the process of deidentifying medical data, making it easier to share valuable information while protecting patient privacy.
How similar studies have gone: Other research has shown success in automating data deidentification processes, indicating that this approach has potential for effective implementation.
Where this research is happening
-
Impact Business Information Solutions INC.
Princeton, United States Active
Researchers
- Principal investigator: O'sullivan, Lawrence — Impact Business Information Solutions INC.
- Study coordinator: O'sullivan, Lawrence
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.