Improving fairness in machine learning for health data analysis
Official title: Identifying and addressing missingness and bias to enhance discovery from multimodal health data
Funded at Brigham and Women's Hospital · NIH-11045765 · Data updated 2026-11-12
This study is working to make sure that computer programs used to look at health records treat everyone fairly, so that all patients get the best care possible, no matter their background or circumstances.
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 start | May 10, 2023 |
| Project end | February 28, 2027 |
| Funding year | 2025 |
| Award (this year) | $349,127 |
| NIH project number | 5R01LM014239-03 |
| Project ID | NIH-11045765 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research are individuals whose health data may be affected by biases in machine learning algorithms, particularly those from underrepresented or protected groups.
✕Less likely to help
Patients whose health data is complete and does not exhibit bias or those who are not part of the protected groups may not benefit from this research.
What this research studies
This research focuses on enhancing the fairness and accuracy of machine learning models used to analyze electronic health records (EHR). It aims to address biases that can arise from systematic differences in data and missing values, which can lead to unfair clinical decision-making. The project will develop new methodologies for evaluating fairness and create innovative machine learning techniques that incorporate these evaluations to improve health equity. By doing so, it seeks to ensure that all patient groups are represented fairly in clinical predictions and decisions.
Why it matters
Potential benefit: If successful, this research could lead to more equitable healthcare outcomes by reducing biases in clinical decision-making processes.
How similar studies have gone: Other research has shown promise in addressing biases in machine learning, but this approach is innovative in its focus on fairness evaluation and missing data handling.
Where this research is happening
-
Brigham and Women's Hospital
Boston, United States Active
Researchers
- Principal investigator: Zhou, Li — Brigham and Women's Hospital
- Study coordinator: Zhou, Li
Related research
Other NIH-funded projects on the same topics.
-
Targeted therapies for glioblastoma in adults and kids
A large NIH program is exploring new brain cancer therapies, including drugs that reach the brain and work against glioblastoma in both children and adults.
-
Statins to Prevent Cancer-Associated Blood Clots in Cancer Patients
A large study will test whether taking rosuvastatin every day for a year can lower the chance of dangerous blood clots in people with cancer, without raising the risk of bleeding.
-
Preterm infant body composition and early-life health after NICU stay
This grant studies how body composition in very preterm babies relates to later brain development and risk of obesity or diabetes, with findings meant to improve care from NICU through early childhood.
-
Rapid Emergency Skills for Prehospital Optimization and Delivery (RESPOND) for Guatemala
A lightweight, AI-enabled prehospital training and triage program helps volunteer firefighters in Guatemala deliver faster, better care to trauma patients.
-
Rapid Emergency Skills for Prehospital Optimization and Notification in Guatemala
A mobile, AI-powered training and triage program helps volunteer emergency responders in Guatemala provide faster, safer trauma care and notify hospitals more quickly.
-
Understanding antibiotic allergy to improve care for patients
Scientists are testing new ideas to understand why some people develop severe allergic reactions to antibiotics and how to prevent or treat them.
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.