Using advanced algorithms to improve machine learning in healthcare while protecting patient privacy
Official title: Federated learning algorithms to overcome statistical and algorithmic bias and privacy concerns in machine learning for health
Funded at Columbia University Health Sciences · NIH-10975494 · Data updated 2026-11-12
This study is working on smart computer programs that help improve healthcare while keeping your personal information safe, so doctors can make better decisions for all patients without sharing sensitive data.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Columbia University Health Sciences NIH-funded |
| Lab location | 1 site (New York, United States) |
| Project start | September 18, 2024 |
| Project end | August 31, 2028 |
| Funding year | 2024 |
| Award (this year) | $358,112 |
| NIH project number | 1R01LM014380-01A1 |
| Project ID | NIH-10975494 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research are individuals whose health data could contribute to improving machine learning models in healthcare, particularly those from diverse backgrounds.
✕Less likely to help
Patients who do not have health data that can be utilized in federated learning models may not benefit from this research.
What this research studies
This research focuses on developing innovative algorithms that enhance machine learning applications in healthcare without compromising patient privacy. By utilizing a method called federated learning, the project aims to create robust machine learning models using data from multiple healthcare institutions without the need to share sensitive information. The research addresses challenges such as bias and data variability, ensuring that the models are fair and effective across diverse patient populations. The team will implement new mathematical techniques to optimize data use while maintaining security and privacy.
Why it matters
Potential benefit: If successful, this research could lead to more accurate and equitable healthcare solutions that leverage data from various sources while safeguarding patient privacy.
How similar studies have gone: Other research has shown promise in using federated learning approaches in healthcare, indicating that this method could be a viable solution to existing challenges.
Where this research is happening
-
Columbia University Health Sciences
New York, United States Active
Researchers
- Principal investigator: Gursoy, Gamze — Columbia University Health Sciences
- Study coordinator: Gursoy, Gamze
Related research
Other NIH-funded projects on the same topics.
-
Precision phenotyping of emphysema in the elderly: a study in diverse adults
Researchers will look at CT scans and lung tests in older adults to understand different forms of emphysema and how they relate to health outcomes.
-
HPV-based cervical cancer screening and treatment implementation in resource-limited settings
A collaborative project to help doctors in South Africa put HPV-based screening and same-day treatment for cervical cancer into routine care, so more people get fast, effective care.
-
Cervical cancer screening and treatment rollout in resource-poor settings
A team from Columbia and the University of Cape Town is testing how to best implement affordable, same-day HPV-based screen-and-treat for cervical cancer in public health settings.
-
Understanding SCN3A-related Developmental Epileptic Encephalopathy and Finding Better Treatments
This NIH grant focuses on how SCN3A gene variants cause developmental epileptic encephalopathy and aims to develop more effective therapies for affected patients.
-
mChoice: Boosting PrEP Use and Adherence for Black and Latino MSM with Tailored Training and Support
A national study to help Black and Latino men who have sex with men start and stick with PrEP through culturally matched provider training and patient support.
-
M-CaRE: Mobile clinics and a smart heart-lung care tool for multimorbidity
A mobile, multilingual tool plus community health workers will help screen and manage high blood pressure and COPD in diverse adult patients, especially in underserved areas.
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.