Preprint
Aug 2026
A Statistical Framework for Data-Driven Discovery of Differential Performance in Clinical Risk Prediction Models
The unfairness tree (utree) is proposed, a data-driven recursive partitioning framework for identifying subgroups with differential model performance that exhibits nominal empirical type I error rates and good ability to detect, quantify, and characterize performance discrepancies defined by higher-order variable interactions.
A. Neher, Julian Wolfson
· 0 citations