Evidence over explanations: put medical AI to the test
Medical AI often optimizes end-to-end performance while offering post-hoc explanations, widening an epistemic gap between behavior and justified clinical claims. Interpretable models and XAI help, but are insufficient. We advocate governance by testability: preregistered empirical trials of causal a...
Uloženo v:
| Hlavní autoři: | , , , , |
|---|---|
| Médium: | Artigo |
| Jazyk: | Inglês |
| Vydáno: |
Nature Portfolio
2026-06-01
|
| Edice: | npj Artificial Intelligence |
| On-line přístup: | https://doi.org/10.1038/s44387-026-00092-4 |
| Tagy: |
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|