{
  "id": 14854,
  "url": "https://arxiv.org/abs/2607.26333v1",
  "title": "Rethinking Clinical Relevance in Chest X-ray Machine Learning: How Evaluation References Define Performance",
  "summary": "Chest X-ray (CXR) machine learning relies heavily on automated evaluation using reference standards that aim to approximate clinical judgment. However, commonly used report-derived labels for pathology classification or generic image quality metrics for reconstruction may not reliably reflect clinical judgment. We systematically investigate how evaluation-reference choices affect model performance and ranking in both pathology classification and image quality assessment (IQA). To enable controll",
  "authors": "Panagiotis Fytas, Ian Selby, Clemens Karner, Judith Babar, Simon Baker, Jake Beckford et al.",
  "category": "research",
  "topics": "healthcare,finance-investment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-28T23:11:04.000Z",
  "fetched_at": "2026-07-30T05:10:24.387Z",
  "source_slug": "arxiv-cslg",
  "source_name": "arXiv cs.LG",
  "source_homepage": "https://arxiv.org/list/cs.LG/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/14854",
  "original_url": "https://arxiv.org/abs/2607.26333v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}