Adaptive validation strategies for real-world clinical artificial intelligence
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...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article (Journal) Editorial |
| Language: | English |
| Published: |
17 November 2025
|
| In: |
Nature computational science
Year: 2025, Volume: 5, Issue: 11, Pages: 980-986 |
| ISSN: | 2662-8457 |
| DOI: | 10.1038/s43588-025-00901-x |
| Online Access: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1038/s43588-025-00901-x Verlag, lizenzpflichtig, Volltext: https://www.nature.com/articles/s43588-025-00901-x 
|
| Author Notes: | Fiona R. Kolbinger & Jakob Nikolas Kather |
| Summary: | 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. |
|---|---|
| Item Description: | Gesehen am 06.03.2026 |
| Physical Description: | Online Resource |
| ISSN: | 2662-8457 |
| DOI: | 10.1038/s43588-025-00901-x |