--- format: "aidr-story-markdown/v1" id: "5892cdd2297786aa71b016284c00409c716cee07d73aed28120a6695e65301dc" canonical_url: "https://aidr.today/5892cdd2?lang=en" title: "Bristol researchers say medicine already knows how to handle black boxes and AI could learn from it" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-09-21T14:06:28.000Z" category: "Research" topics: ["safety","regulation","rag","reasoning"] source_urls: ["https://the-decoder.com/bristol-researchers-say-medicine-already-knows-how-to-handle-black-boxes-and-ai-could-learn-from-it/"] summary: "Researchers at the University of Bristol want to make medical AI systems safer by borrowing from how drugs get approved. Their \"Learning Ensemble\" framework defines three areas to check, including system limits, fairness across patient groups, and clinical fit. The goal is to catch models that work technically but can still be dangerously wrong in the clinic." --- # Bristol researchers say medicine already knows how to handle black boxes and AI could learn from it > [Open the canonical story]() **Published:** 2026-09-21T14:06:28.000Z **Category:** Research **Topics:** safety, regulation, rag, reasoning ## Summary Researchers at the University of Bristol want to make medical AI systems safer by borrowing from how drugs get approved\. Their "Learning Ensemble" framework defines three areas to check, including system limits, fairness across patient groups, and clinical fit\. The goal is to catch models that work technically but can still be dangerously wrong in the clinic\. ## Sources - [Story source]()