TY  - JOUR
AU  - Reinke, Annika
TI  - Validation of artificial intelligence algorithms for the surgical practice. [Validierung von künstliche Intelligenz-Algorithmen für die chirurgische Praxis.]
JO  - Die Chirurgie
VL  - 96
IS  - 11
SN  - 2731-6971
CY  - [Berlin]
PB  - Springer Medizin Verlag GmbH
M1  - DKFZ-2025-01457
SP  - 913-917
PY  - 2025
N1  - #LA:E130# / 2025 Nov;96(11):913-917
AB  - Artificial intelligence (AI) is increasingly being used in surgery; however, the validation of such systems is often methodologically insufficient.Which validation issues arise in surgical AI and what requirements can be derived for clinically meaningful validation strategies?Metric-related pitfalls reported in the literature were analyzed, combined with insights from the interdisciplinary consensus process 'metrics reloaded' and its ongoing extension to surgical applications.Recurring weaknesses are observed at the levels of data, metrics and reporting. The lack of consideration of temporal structures and aggregation in video data is particularly critical.A structured, clinically grounded validation is essential for the safe use of surgical AI. The metrics reloaded procedure is currently being adapted to address surgery-specific requirements.
KW  - Assessment methods (Other)
KW  - Metrics (Other)
KW  - Metrics reloaded (Other)
KW  - Surgical video analysis (Other)
KW  - Video data (Other)
LB  - PUB:(DE-HGF)16
C6  - pmid:40643685
DO  - DOI:10.1007/s00104-025-02348-2
UR  - https://inrepo02.dkfz.de/record/303010
ER  -