{
  "id": 1982,
  "url": "https://link.springer.com/article/10.1007/s10462-026-11634-2",
  "title": "The interpretability paradox in cancer imaging and risk prediction: a critical narrative review of explainable AI, failure modes, and design alternatives",
  "summary": "Deep learning has advanced cancer imaging and cancer-related risk prediction, but many high-performing models remain difficult to interrogate in clinically meaningful terms. This creates an interpretability paradox: gains in predictive performance often coincide with reduced transparency, while widely used post-hoc explanations can be persuasive without providing reliable evidence of model reasoning. Here, we present a critical narrative review and position argument, supported by a semi-systemat",
  "authors": null,
  "category": "research",
  "topics": "safety-alignment,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-07T00:00:00.000Z",
  "fetched_at": "2026-07-14T16:11:46.979Z",
  "source_slug": "x-artificial-intelligence-review",
  "source_name": "Artificial Intelligence Review",
  "source_homepage": "https://link.springer.com/journal/10462",
  "ethics_ai_record_url": "https://ethics.ai/record/1982",
  "original_url": "https://link.springer.com/article/10.1007/s10462-026-11634-2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}