Improving fairness in AI models for detecting chest diseases
Investigating the Effect of Synthetic Medical Images on Fairness in Medical Deep Learning Research
This study is working to make sure that computer programs used to spot health issues in chest X-rays are fair for everyone, especially for people from different racial and ethnic backgrounds, by creating new images that represent these groups better.
Quick facts
| Grant type | R21 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Mayo Clinic Rochester NIH-funded |
| Lab location | 1 site (Rochester, United States) |
| Project ID | NIH-10867700 on NIH RePORTER |
What this research studies
This research focuses on enhancing the fairness of deep learning models used for detecting pathologies in chest radiographs. It aims to address health disparities by using generative modeling to create synthetic medical images that better represent racial and ethnic minority groups. The study will train deep learning models on a diverse dataset, including both real and synthetic images, to ensure accurate pathology detection without bias. By leveraging advanced techniques, the research seeks to improve diagnostic equity in healthcare.
Who could benefit from this research
Good fit: Ideal candidates for this research are individuals from racial and ethnic minority groups who may be affected by disparities in healthcare outcomes.
Not a fit: Patients who do not belong to racial or ethnic minority groups may not directly benefit from the specific focus of this research.
Why it matters
Potential benefit: If successful, this research could lead to more accurate and equitable medical diagnoses for patients from diverse backgrounds.
How similar studies have performed: Other research has shown promise in using synthetic data to improve fairness in AI applications, indicating that this approach could be effective.
Where this research is happening
Rochester, United States
- Mayo Clinic Rochester — Rochester, United States (Active)
Researchers
- Principal investigator: Khosravi, Bardia — Mayo Clinic Rochester
- Study coordinator: Khosravi, Bardia
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.