Computer tools to spot heart risk in breast cancer survivors using medical records
SCH: A New Computational Framework for Learning from Imbalanced Biomedical Data
This project builds computer methods to better spot which breast cancer survivors may develop heart problems using their medical records.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Minnesota NIH-funded |
| Lab location | 1 site (Minneapolis, United States) |
| Project ID | NIH-11161194 on NIH RePORTER |
What this research studies
From a patient's view, researchers will combine doctors' notes, test results, and images from electronic health records to teach new computer models how to find signals linked to heart disease after breast cancer. They will design methods that work well when outcomes are rare or unevenly distributed and that predict both whether and when heart problems might occur. The team will focus on making individualized risk predictions for breast cancer survivors so clinicians can use more detailed information than current general risk tools. Work will be done using data from participating health systems, with the goal of producing models that could be applied more broadly over time.
Who could benefit from this research
Good fit: Ideal candidates are breast cancer survivors whose electronic health records and follow-up data are available through participating health systems and who agree to data use for research.
Not a fit: Patients without accessible EHR data, with very short follow-up, or whose care occurs outside participating systems may not receive direct benefit from this work.
Why it matters
Potential benefit: If successful, this could help identify breast cancer survivors at higher risk for heart disease so doctors can tailor monitoring and prevention.
How similar studies have performed: Some previous EHR-based models have predicted cardiovascular outcomes in general populations, but applying new methods for imbalanced data specifically to breast cancer survivors is relatively novel.
Where this research is happening
Minneapolis, United States
- University of Minnesota — Minneapolis, United States (Active)
Researchers
- Principal investigator: Sun, Ju — University of Minnesota
- Study coordinator: Sun, Ju
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.