Machine learning predicts cancer outcomes across genetic ancestry continuum
Beyond Discrete Ancestry Groups: Distribution-Aware In-Context Learning for Cancer Outcome Prediction Across the Genetic Ancestry Continuum
Summary
Machine learning models often predict cancer outcomes without fully considering genetic ancestry or by grouping people into broad ancestry categories. The authors found that prediction accuracy drops as a person's genetics differ more from those in the training data, even within the same ancestry group. They propose a new method called distribution-aware in-context learning that models genetic ancestry as a continuum rather than fixed groups. This approach better captures how genetic differences influence cancer outcome predictions and improves accuracy. They provide theoretical reasoning and experimental evidence supporting their method.
What this means in practice
- •For hospital data teams: Improve cancer outcome prediction models by integrating genetic ancestry as a continuum to enhance accuracy across diverse patient populations.
- •For biomedical software developers: Create software tools that incorporate distribution-aware in-context learning to provide personalized cancer risk assessments accounting for genetic diversity.