Improving fairness in machine learning for radiology diagnostics
Official title: SCH: Quantifying and mitigating demographic biases of machine learning in real world radiology
Funded at Johns Hopkins University · NIH-10875636 · Data updated 2026-11-12
This study is looking at how computer programs used in medical imaging might unfairly affect certain groups of people, and it aims to make sure that cancer screenings, like those for breast and lung cancer, are accurate and fair for everyone, no matter their background.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Johns Hopkins University NIH-funded |
| Lab location | 1 site (Baltimore, United States) |
| Project start | July 1, 2023 |
| Project end | June 30, 2026 |
| Funding year | 2024 |
| Award (this year) | $282,680 |
| NIH project number | 5R01CA287422-02 |
| Project ID | NIH-10875636 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research include individuals undergoing breast or lung cancer screening, particularly those from under-represented demographic backgrounds.
✕Less likely to help
Patients who are not involved in cancer screening programs or those from demographic groups that are already well-represented in existing data may not benefit from this research.
What this research studies
This research investigates how machine learning algorithms used in radiology can unintentionally produce biased results against under-represented demographic groups, which may worsen existing health disparities. The project aims to develop methods to quantify and correct these biases, ensuring that diagnostic tools are fair and equitable for all patients. By analyzing how these algorithms perform across different demographic groups, the research seeks to enhance the accuracy and accessibility of cancer screening, particularly for breast and lung cancer. The approach includes creating algorithms that can adjust for biases even when sensitive demographic information is not directly available.
Why it matters
Potential benefit: If successful, this research could lead to more accurate and equitable cancer screening tools that benefit all demographic groups.
How similar studies have gone: Other research has shown promise in addressing algorithmic bias in healthcare, indicating that this approach could lead to significant advancements in equitable medical diagnostics.
Where this research is happening
-
Johns Hopkins University
Baltimore, United States Active
Researchers
- Principal investigator: Sulam, Jeremias — Johns Hopkins University
- Study coordinator: Sulam, Jeremias
Related research
Other NIH-funded projects on the same topics.
-
Targeting hidden brain injuries in iTTP to improve long-term brain health
A researcher aims to find out how silent brain injuries in people with immune thrombotic thrombocytopenic purpura (iTTP) happen, how they affect thinking and stroke risk, and how to prevent them.
-
Accelerated flap coverage for severe leg injuries: earlier reconstruction vs standard timing
This study tests whether doing early flap coverage after a severe leg injury lowers infection risk and improves healing for patients with open wounds and bone injury.
-
Placebo-controlled shunting for iNPH: does the surgery help with walking and balance?
A doctor-led trial at Johns Hopkins will test whether a shunt surgery improves walking and balance in older adults with idiopathic normal pressure hydrocephalus.
-
Omalizumab for COPD patients with allergen sensitization and exposure
A multicenter trial will test whether adding omalizumab helps people with COPD who are allergic to common indoor allergens and are exposed to them.
-
Johns Hopkins Total Worker Health Center focusing on mental health
A nationwide center at Johns Hopkins is working to improve mental health and well-being among workers by studying workplace health strategies and translating findings into practical tools.
-
Role of fat droplets in liver fat and inflammatory signals in NAFLD
A study at Johns Hopkins will explore how fat droplets in the liver influence molecules that drive inflammation and progression of non-alcoholic fatty liver disease (NAFLD) in adults.
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.