Predictive modeling by tumor type: Comparing performance and feature importance of machine learning–based predictive models in patients with hematologic and solid tumors. This is an ASCO Meeting ...

This study compared 6 algorithmic fairness–improving approaches for low-birth-weight predictive models and found that they improved accuracy but decreased sensitivity for Black populations. Objective: ...

Categorizing patients with cancer by their disease stage can be an important tool when conducting administrative claims-based studies. As claims databases frequently do not capture this information, ...