SPIN Unprocessed
Source arXiv Machine Learning export.arxiv.org Analyst
July 10, 2026 ai_technology research

Who Gets Missed in the Tail? Thresholded Subgroup Underdiagnosis in Long-Tailed Chest X-ray Classification

View original on arxiv.org

Overview

arXiv:2607.07717v1 Announce Type: new Abstract: In chest X-ray (CXR) classification, acceptable ranking performance can still leave rare-positive patients below threshold, especially within subgroups. We study this pre-deployment fairness problem as an audit question: after a long-tailed multi-label CXR model is converted from scores into decisions, who is missed? Across VinDr-CXR and MIMIC-CXR/CXR-LT, we use a diagnostic ladder to separate class-level long-tail losses, subgroup-aware weighting,

SpinGraph analysis pending — check back after processing.

Ask AI about this story

Opens with the SpinGraph .md URL and structured context — one click, prompt included.

More from arXiv Machine Learning

View all →

Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO