To warrant clinical adoption AI models require a multi-faceted implementation evaluation.

Autor: van de Sande D; Erasmus MC University Medical Center, Department of Adult Intensive Care, Rotterdam, The Netherlands., Chung EFF; Erasmus MC University Medical Center, Department of Adult Intensive Care, Rotterdam, The Netherlands., Oosterhoff J; Delft University of Technology, Faculty of Technology, Policy and Management, Delft, The Netherlands., van Bommel J; Erasmus MC University Medical Center, Department of Adult Intensive Care, Rotterdam, The Netherlands., Gommers D; Erasmus MC University Medical Center, Department of Adult Intensive Care, Rotterdam, The Netherlands., van Genderen ME; Erasmus MC University Medical Center, Department of Adult Intensive Care, Rotterdam, The Netherlands. m.vangenderen@erasmusmc.nl.
Jazyk: angličtina
Zdroj: NPJ digital medicine [NPJ Digit Med] 2024 Mar 06; Vol. 7 (1), pp. 58. Date of Electronic Publication: 2024 Mar 06.
DOI: 10.1038/s41746-024-01064-1
Abstrakt: Despite artificial intelligence (AI) technology progresses at unprecedented rate, our ability to translate these advancements into clinical value and adoption at the bedside remains comparatively limited. This paper reviews the current use of implementation outcomes in randomized controlled trials evaluating AI-based clinical decision support and found limited adoption. To advance trust and clinical adoption of AI, there is a need to bridge the gap between traditional quantitative metrics and implementation outcomes to better grasp the reasons behind the success or failure of AI systems and improve their translation into clinical value.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz: