Toward safer ophthalmic artificial intelligence via distributed validation on real-world data.

Autor:	Nath S; Department of Ophthalmology and Visual Sciences, McGill University, Montréal, Québec, Canada., Rahimy E; Byers Eye Institute, Stanford University, Palo Alto, California, USA., Kras A; Save Sight Institute, Sydney University, Sydney, Australia.; Moorfields Eye Hospital NHS Foundation Trust, London, UK., Korot E; Byers Eye Institute, Stanford University, Palo Alto, California, USA.; Moorfields Eye Hospital NHS Foundation Trust, London, UK.; Retina Specialists of Michigan, Grand Rapids, Michigan, USA.
Jazyk:	angličtina
Zdroj:	Current opinion in ophthalmology [Curr Opin Ophthalmol] 2023 Sep 01; Vol. 34 (5), pp. 459-463. Date of Electronic Publication: 2023 Jul 17.
DOI:	10.1097/ICU.0000000000000986
Abstrakt:	Purpose of Review: The current article provides an overview of the present approaches to algorithm validation, which are variable and largely self-determined, as well as solutions to address inadequacies. Recent Findings: In the last decade alone, numerous machine learning applications have been proposed for ophthalmic diagnosis or disease monitoring. Remarkably, of these, less than 15 have received regulatory approval for implementation into clinical practice. Although there exists a vast pool of structured and relatively clean datasets from which to develop and test algorithms in the computational 'laboratory', real-world validation remains key to allow for safe, equitable, and clinically reliable implementation. Bottlenecks in the validation process stem from a striking paucity of regulatory guidance surrounding safety and performance thresholds, lack of oversight on critical postdeployment monitoring and context-specific recalibration, and inherent complexities of heterogeneous disease states and clinical environments. Implementation of secure, third-party, unbiased, pre and postdeployment validation offers the potential to address existing shortfalls in the validation process. Summary: Given the criticality of validation to the algorithm pipeline, there is an urgent need for developers, machine learning researchers, and end-user clinicians to devise a consensus approach, allowing for the rapid introduction of safe, equitable, and clinically valid machine learning implementations. (Copyright © 2023 Wolters Kluwer Health, Inc. All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu