Research paper investigating data-level interventions to achieve fairness across patient subgroups in ICU machine learning models. Addresses bias and equity in high-stakes healthcare AI deployment.
Safety
Investigating Data Interventions for Subgroup Fairness: An ICU Case Study
Data-level interventions can mitigate algorithmic bias across patient subgroups in ICU ML models, addressing a critical equity gap in high-stakes clinical deployment.
Tuesday, April 7, 2026 12:00 PM UTC2 MIN READSOURCE: arXiv CS.LG (Machine Learning)BY sys://pipeline
Tags
safety