J Jill Hopkins1, Pearse A Keane2,3, Konstantinos Balaskas2. 1. Ophthalmology Personalized Healthcare, Genentech, Inc., South San Francisco, California, USA. 2. Moorfields Eye Hospital NHS Foundation Trust. 3. Institute of Ophthalmology, University College London, London, UK.
Abstract
PURPOSE OF REVIEW: To review the current status of artificial intelligence systems in ophthalmology and highlight the steps required for clinical translation of artificial intelligence into personalized health care (PHC) in retinal disease. RECENT FINDINGS: Artificial intelligence systems for ophthalmological application have made rapid advances, but are yet to attain a state of technical maturity that allows their adoption into real-world settings. There remains an 'artificial intelligence chasm' in the spheres of validation, regulation, safe implementation, and demonstration of clinical impact that needs to be bridged before the full potential of artificial intelligence to deliver PHC can be realized. SUMMARY: Ophthalmology is currently in a stage between the demonstration of the potential of artificial intelligence and widespread deployment. Next stages include aggregating and curating datasets, training and validating artificial intelligence systems, establishing the regulatory framework, implementation and adoption with ongoing evaluation and model adjustment, and finally, meaningful human-artificial intelligence interaction with clinically validated tools that have demonstrated measurable impact on patient and healthcare system outcomes. Ophthalmologists should leverage the ability of artificial intelligence systems to glean insights from large volumes of multivariate data, and to interpret artificial intelligence recommendations in a clinical context. In doing so, the field will be well positioned to lead the transformation of health care in a personalized direction. VIDEO ABSTRACT: http://links.lww.com/COOP/A35.
PURPOSE OF REVIEW: To review the current status of artificial intelligence systems in ophthalmology and highlight the steps required for clinical translation of artificial intelligence into personalized health care (PHC) in retinal disease. RECENT FINDINGS: Artificial intelligence systems for ophthalmological application have made rapid advances, but are yet to attain a state of technical maturity that allows their adoption into real-world settings. There remains an 'artificial intelligence chasm' in the spheres of validation, regulation, safe implementation, and demonstration of clinical impact that needs to be bridged before the full potential of artificial intelligence to deliver PHC can be realized. SUMMARY: Ophthalmology is currently in a stage between the demonstration of the potential of artificial intelligence and widespread deployment. Next stages include aggregating and curating datasets, training and validating artificial intelligence systems, establishing the regulatory framework, implementation and adoption with ongoing evaluation and model adjustment, and finally, meaningful human-artificial intelligence interaction with clinically validated tools that have demonstrated measurable impact on patient and healthcare system outcomes. Ophthalmologists should leverage the ability of artificial intelligence systems to glean insights from large volumes of multivariate data, and to interpret artificial intelligence recommendations in a clinical context. In doing so, the field will be well positioned to lead the transformation of health care in a personalized direction. VIDEO ABSTRACT: http://links.lww.com/COOP/A35.
Authors: Rumana N Hussain; Sarah E Coupland; Helen Kalirai; Azzam F G Taktak; Antonio Eleuteri; Bertil E Damato; Carl Groenewald; Heinrich Heimann Journal: Cancers (Basel) Date: 2021-05-08 Impact factor: 6.639