Reducing bias and gaps in medical records to improve health insights
Identifying and addressing missingness and bias to enhance discovery from multimodal health data
This project improves computer tools that use medical records so they give fairer, clearer results for patients from diverse backgrounds.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Brigham and Women's Hospital NIH-funded |
| Lab location | 1 site (Boston, United States) |
| Project ID | NIH-11289431 on NIH RePORTER |
What this research studies
The team will work with electronic health records and other health data to find where computer models make mistakes because of missing information or biased data. They will create new ways to measure these problems and build machine-learning models that can learn to fill in missing pieces while being constrained to avoid unfair errors. The researchers will test their methods on real hospital data and refine techniques that help make AI outputs easier to understand. The aim is to produce tools clinicians can rely on that do not unintentionally favor or harm certain patient groups.
Who could benefit from this research
Good fit: People whose electronic health records are in participating health systems or who agree to share de-identified EHR data could have their data included in this work.
Not a fit: Patients whose records are not part of the datasets used or whose care does not rely on EHR-based tools may not receive any direct benefit.
Why it matters
Potential benefit: If successful, patients could see more accurate and equitable recommendations from AI tools used in clinical care.
How similar studies have performed: Previous AI work has produced useful predictions from EHRs but has often struggled with missing data and unequal performance across groups, so this project is building new methods to address those gaps.
Where this research is happening
Boston, United States
- Brigham and Women's Hospital — Boston, United States (Active)
Researchers
- Principal investigator: Zhou, Li — Brigham and Women's Hospital
- Study coordinator: Zhou, Li
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.