Why do probabilistic clinical models fail to transport between sites.

Autor: Lasko TA; Vanderbilt University Medical Center, Nashville, TN, USA. tom.lasko@vanderbilt.edu., Strobl EV; Vanderbilt University Medical Center, Nashville, TN, USA., Stead WW; Vanderbilt University Medical Center, Nashville, TN, USA.
Jazyk: angličtina
Zdroj: NPJ digital medicine [NPJ Digit Med] 2024 Mar 01; Vol. 7 (1), pp. 53. Date of Electronic Publication: 2024 Mar 01.
DOI: 10.1038/s41746-024-01037-4
Abstrakt: The rising popularity of artificial intelligence in healthcare is highlighting the problem that a computational model achieving super-human clinical performance at its training sites may perform substantially worse at new sites. In this perspective, we argue that we should typically expect this failure to transport, and we present common sources for it, divided into those under the control of the experimenter and those inherent to the clinical data-generating process. Of the inherent sources we look a little deeper into site-specific clinical practices that can affect the data distribution, and propose a potential solution intended to isolate the imprint of those practices on the data from the patterns of disease cause and effect that are the usual target of probabilistic clinical models.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz: