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

Background: Many 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. Methods: This 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. Results: One 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. Conclusion: Ophthalmologists 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.

Predicting the immediate impact of national lockdown on neovascular age-related macular degeneration and associated visual morbidity: an INSIGHT Health Data Research Hub for Eye Health report.

OBJECTIVE: Predicting the impact of neovascular age-related macular degeneration (nAMD) service disruption on visual outcomes following national lockdown in the UK to contain SARS-CoV-2. METHODS AND ANALYSIS: This retrospective cohort study includes deidentified data from 2229 UK patients from the INSIGHT Health Data Research digital hub. We forecasted the number of treatment-naïve nAMD patients requiring anti-vascular endothelial growth factor (anti-VEGF) initiation during UK lockdown (16 March 2020 through 31 July 2020) at Moorfields Eye Hospital (MEH) and University Hospitals Birmingham (UHB). Best-measured visual acuity (VA) changes without anti-VEGF therapy were predicted using post hoc analysis of Minimally Classic/Occult Trial of the Anti-VEGF Antibody Ranibizumab in the Treatment of Neovascular AMD trial sham-control arm data (n=238). RESULTS: At our centres, 376 patients were predicted to require anti-VEGF initiation during lockdown (MEH: 325; UHB: 51). Without treatment, mean VA was projected to decline after 12 months. The proportion of eyes in the MEH cohort predicted to maintain the key positive visual outcome of ≥70 ETDRS letters (Snellen equivalent 6/12) fell from 25.5% at baseline to 5.8% at 12 months (UHB: 9.8%-7.8%). Similarly, eyes with VA <25 ETDRS letters (6/96) were predicted to increase from 4.3% to 14.2% at MEH (UHB: 5.9%-7.8%) after 12 months without treatment. CONCLUSIONS: Here, we demonstrate how combining data from a recently founded national digital health data repository with historical industry-funded clinical trial data can enhance predictive modelling in nAMD. The demonstrated detrimental effects of prolonged treatment delay should incentivise healthcare providers to support nAMD patients accessing care in safe environments. TRIAL REGISTRATION NUMBER: NCT00056836.

Safety and efficacy of an artificial intelligence-enabled decision tool for treatment decisions in neovascular age-related macular degeneration and an exploration of clinical pathway integration and implementation: protocol for a multi-methods validation study.

INTRODUCTION: Neovascular age-related macular degeneration (nAMD) management is one of the largest single-disease contributors to hospital outpatient appointments. Partial automation of nAMD treatment decisions could reduce demands on clinician time. Established artificial intelligence (AI)-enabled retinal imaging analysis tools, could be applied to this use-case, but are not yet validated for it. A primary qualitative investigation of stakeholder perceptions of such an AI-enabled decision tool is also absent. This multi-methods study aims to establish the safety and efficacy of an AI-enabled decision tool for nAMD treatment decisions and understand where on the clinical pathway it could sit and what factors are likely to influence its implementation. METHODS AND ANALYSIS: Single-centre retrospective imaging and clinical data will be collected from nAMD clinic visits at a National Health Service (NHS) teaching hospital ophthalmology service, including judgements of nAMD disease stability or activity made in real-world consultant-led-care. Dataset size will be set by a power calculation using the first 127 randomly sampled eligible clinic visits. An AI-enabled retinal segmentation tool and a rule-based decision tree will independently analyse imaging data to report nAMD stability or activity for each of these clinic visits. Independently, an external reading centre will receive both clinical and imaging data to generate an enhanced reference standard for each clinic visit. The non-inferiority of the relative negative predictive value of AI-enabled reports on disease activity relative to consultant-led-care judgements will then be tested. In parallel, approximately 40 semi-structured interviews will be conducted with key nAMD service stakeholders, including patients. Transcripts will be coded using a theoretical framework and thematic analysis will follow. ETHICS AND DISSEMINATION: NHS Research Ethics Committee and UK Health Research Authority approvals are in place (21/NW/0138). Informed consent is planned for interview participants only. Written and oral dissemination is planned to public, clinical, academic and commercial stakeholders.

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

Background Many 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. Methods This 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. Results One 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. Conclusion Ophthalmologists 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.

Teleophthalmology-enabled and artificial intelligence-ready referral pathway for community optometry referrals of retinal disease (HERMES): a Cluster Randomised Superiority Trial with a linked Diagnostic Accuracy Study-HERMES study report 1-study protocol.

INTRODUCTION: Recent years have witnessed an upsurge of demand in eye care services in the UK. With a large proportion of patients referred to Hospital Eye Services (HES) for diagnostics and disease management, the referral process results in unnecessary referrals from erroneous diagnoses and delays in access to appropriate treatment. A potential solution is a teleophthalmology digital referral pathway linking community optometry and HES. METHODS AND ANALYSIS: The HERMES study (Teleophthalmology-enabled and artificial intelligence-ready referral pathway for community optometry referrals of retinal disease: a cluster randomised superiority trial with a linked diagnostic accuracy study) is a cluster randomised clinical trial for evaluating the effectiveness of a teleophthalmology referral pathway between community optometry and HES for retinal diseases. Nested within HERMES is a diagnostic accuracy study, which assesses the accuracy of an artificial intelligence (AI) decision support system (DSS) for automated diagnosis and referral recommendation. A postimplementation, observational substudy, a within-trial economic evaluation and discrete choice experiment will assess the feasibility of implementation of both digital technologies within a real-life setting. Patients with a suspicion of retinal disease, undergoing eye examination and optical coherence tomography (OCT) scans, will be recruited across 24 optometry practices in the UK. Optometry practices will be randomised to standard care or teleophthalmology. The primary outcome is the proportion of false-positive referrals (unnecessary HES visits) in the current referral pathway compared with the teleophthalmology referral pathway. OCT scans will be interpreted by the AI DSS, which provides a diagnosis and referral decision and the primary outcome for the AI diagnostic study is diagnostic accuracy of the referral decision made by the Moorfields-DeepMind AI system. Secondary outcomes relate to inappropriate referral rate, cost-effectiveness analyses and human-computer interaction (HCI) analyses. ETHICS AND DISSEMINATION: Ethical approval was obtained from the London-Bromley Research Ethics Committee (REC 20/LO/1299). Findings will be reported through academic journals in ophthalmology, health services research and HCI. TRIAL REGISTRATION NUMBER: ISRCTN18106677 (protocol V.1.1).

FENETRE study: quality-assured follow-up of quiescent neovascular age-related macular degeneration by non-medical practitioners: study protocol and statistical analysis plan for a randomised controlled trial.

OBJECTIVE: Management of age-related macular degeneration (AMD) places a high demand on already constrained hospital-based eye services. This study aims to assess the safety and quality of follow-up within the community led by suitably trained non-medical practitioners for the management of quiescent neovascular AMD (QnAMD). METHODS/DESIGN: This is a prospective, multisite, randomised clinical trial. 742 participants with QnAMD will be recruited and randomised to either continue hospital-based secondary care or to receive follow-up within a community setting. Participants in both groups will be monitored for disease reactivation over the course of 12 months and referred for treatment as necessary. Outcomes measures will assess the non-inferiority of primary care follow-up accounting for accuracy of the identification of disease reactivation, patient loss to follow-up and accrued costs and the budget impact to the National Health Service. ETHICS AND DISSEMINATION: Research ethics approval was obtained from the London Bloomsbury Ethics Committee. The results of this study will be disseminated through academic peer-reviewed publications, conferences and collaborations with eye charities to insure the findings reach the appropriate patient populations. TRIAL REGISTRATION NUMBER: NCT03893474.