Adaptive validation strategies for real-world clinical artificial intelligence
Research output: Contribution to journal › Comment/Debate › Contributed › peer-review
Contributors
Abstract
Technical metrics used to evaluate medical artificial intelligence tools often fail to predict their clinical impact. We characterize this discordance and propose a framework of study designs to guide the translational process for clinical artificial intelligence tools, acknowledging their diversity and specific validation requirements.
Details
| Original language | English |
|---|---|
| Pages (from-to) | 980-986 |
| Number of pages | 7 |
| Journal | Nature Computational Science |
| Volume | 5 |
| Issue number | 11 |
| Publication status | Published - Nov 2025 |
| Peer-reviewed | Yes |
External IDs
| ORCID | /0000-0003-2265-4809/work/199217296 |
|---|---|
| ORCID | /0000-0002-3730-5348/work/199217851 |