Acceptance and Perception of Artificial Intelligence Usability in Eye Care (APPRAISE) for Ophthalmologists: A Multinational Perspective

Abstract

BackgroundMany artificial intelligence (AI) studies have focused on development of AI models, novel techniques, and reporting guidelines. However, little is understood about clinicians' perspectives of AI applications in medical fields including ophthalmology, particularly in light of recent regulatory guidelines. The aim for this study was to evaluate the perspectives of ophthalmologists regarding AI in 4 major eye conditions: diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD) and cataract.MethodsThis was a multi-national survey of ophthalmologists between March 1st, 2020 to February 29th, 2021 disseminated via the major global ophthalmology societies. The survey was designed based on microsystem, mesosystem and macrosystem questions, and the software as a medical device (SaMD) regulatory framework chaired by the Food and Drug Administration (FDA). Factors associated with AI adoption for ophthalmology analyzed with multivariable logistic regression random forest machine learning.ResultsOne thousand one hundred seventy-six ophthalmologists from 70 countries participated with a response rate ranging from 78.8 to 85.8% per question. Ophthalmologists were more willing to use AI as clinical assistive tools (88.1%, n = 890/1,010) especially those with over 20 years' experience (OR 3.70, 95% CI: 1.10–12.5, p = 0.035), as compared to clinical decision support tools (78.8%, n = 796/1,010) or diagnostic tools (64.5%, n = 651). A majority of Ophthalmologists felt that AI is most relevant to DR (78.2%), followed by glaucoma (70.7%), AMD (66.8%), and cataract (51.4%) detection. Many participants were confident their roles will not be replaced (68.2%, n = 632/927), and felt COVID-19 catalyzed willingness to adopt AI (80.9%, n = 750/927). Common barriers to implementation include medical liability from errors (72.5%, n = 672/927) whereas enablers include improving access (94.5%, n = 876/927). Machine learning modeling predicted acceptance from participant demographics with moderate to high accuracy, and area under the receiver operating curves of 0.63–0.83.ConclusionOphthalmologists are receptive to adopting AI as assistive tools for DR, glaucoma, and AMD. Furthermore, ML is a useful method that can be applied to evaluate predictive factors on clinical qualitative questionnaires. This study outlines actionable insights for future research and facilitation interventions to drive adoption and operationalization of AI tools for Ophthalmology.

Recent developments of telemedicine in glaucoma

“…Another area for progress is the integration of AI with teleglaucoma modalities [43,44]. In a survey of 1176 ophthalmologists from 70 countries, 70.7% reported that they would be willing to integrate AI for glaucoma screening [45 ▪ ]. Certainly, this confidence can be justified by recent advancements.…”

Explainable artificial intelligence in ophthalmology

“…More work is also needed to explore XAI methods in AI applications beyond medical image analysis [53 ▪▪ ], including unstructured data in large language models. In assessing the usefulness of XAI explanations, more emphasis on end-users perspectives, including clinicians, patients, and policymakers, should be explored to guide the improvement of XAI methods [12 ▪▪ ,17 ▪▪ ,54 ▪ ]. Finally, in addition to enhancing the transparency of AI models, concerted effort is needed along all stages of model development from data collection to deployment, to address all pillars in developing trustworthy AI [55,56 ▪▪ ].…”

Glaucoma and Telemedicine

“…Since ophthalmologists are receptive to adopting AI as an assistive tool for glaucoma,53 as soon as results of predictive models using AI are available to general ophthalmologists, modern clinical decision-support systems may become important tools to improve decision-making in the teleglaucoma setting 54. However, application in clinical practice still requires careful validation with transparent reporting that follows all AI guidelines 55–58.…”