Reducing demographic bias in biomedical machine learning for cancer detection using cfDNA methylation
DeBias offers an effective and generalizable strategy for correcting demographic biases in biomedical machine learning. It represents a step toward more equitable machine learning models that can deliver reliable and unbiased predictions across diverse patient populations.
Authors
- Vatche G. Agopian (ORCID: https://orcid.org/0000-0003-0130-9838)
- Preeti Ahuja (ORCID: https://orcid.org/0000-0002-1768-0941)
- Xiaohui Ni (ORCID: https://orcid.org/0000-0002-3626-3588)
- Angela Yeh
- Megumi Yokomizo
- Xianghong Jasmine Zhou (ORCID: https://orcid.org/0000-0002-4522-7490)
- Steven S. Raman (ORCID: https://orcid.org/0000-0003-0499-1676)
- Mary L. Stackpole (ORCID: https://orcid.org/0000-0003-4432-6718)
- Y. Zhou
- Denise R. Aberle (ORCID: https://orcid.org/0000-0002-8858-3401)
- Andrew Melehy (ORCID: https://orcid.org/0000-0001-7786-5086)
- William H. Hsu
- Kirti Shetty
- Benjamin Tran
- David S. Lu
- Steven M. Dubinett
- Chun-Chi Liu
- Yazhen Zhu
- Lopa Mishra
- Weihua Zeng
- Steven-Huy B. Han
- Wenyuan Li
- Shuo Li
Institutions
- QB3 (US)
- University of Maryland, Baltimore (US)
- Feinstein Institute for Medical Research (US)
- University of California, Los Angeles (US)
- George Washington University (US)
- Quantitative BioSciences (US)
- VA Greater Los Angeles Healthcare System (US)
- VPDiagnostics (United States) (US)
- Stanford University (US)
Publication Details
- Journal
- Genome biology
- Published
- 2026-02-25
- DOI
- https://doi.org/10.1186/s13059-026-04006-0
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00