Get reliable answers from your electronic health record
Trustworthy and High-Performance Question Answering for Electronic Health Records
This project builds AI tools so patients and clinicians can ask plain-language questions of EHRs and get accurate, trustworthy answers.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Texas Hlth Sci Ctr Houston NIH-funded |
| Lab location | 1 site (Houston, United States) |
| Project ID | NIH-11193457 on NIH RePORTER |
What this research studies
Researchers will combine large language AI models with systems that understand structured EHR data to create a question-answering tool tailored to medical records. They will train and test the tool using real electronic health record data and measures designed to prevent AI 'hallucinations' or false answers. Clinicians will use realistic tasks to check whether the tool returns correct, well-sourced information and to improve its safety and usability. The team will link answers back to specific notes and data fields so you can see where each answer came from.
Who could benefit from this research
Good fit: Ideal participants are patients whose electronic health records are stored at participating hospitals and who agree to let their de-identified records be used, or clinicians who work with those records.
Not a fit: People without accessible electronic health records at participating sites or whose records cannot be shared will likely not benefit directly from this work.
Why it matters
Potential benefit: If successful, the tool could help you and your care team find important information faster and reduce mistakes caused by incorrect AI answers.
How similar studies have performed: Large language models have shown promise answering medical questions but also produce dangerous hallucinations, so grounding them in EHR data is a newer approach with partial prior success.
Where this research is happening
Houston, United States
- University of Texas Hlth Sci Ctr Houston — Houston, United States (Active)
Researchers
- Principal investigator: Roberts, Kirk Edward — University of Texas Hlth Sci Ctr Houston
- Study coordinator: Roberts, Kirk Edward
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.