Search

Artificial intelligence (AI) has great potential in ophthalmology. We investigated how ambiguous outputs from an AI diagnostic support system (AI-DSS) affected diagnostic responses from optometrists when assessing cases of suspected retinal disease. Thirty optometrists (15 more experienced, 15 less) assessed 30 clinical cases. For ten, participants saw an optical coherence tomography (OCT) scan, basic clinical information and retinal photography ('no AI'). For another ten, they were also given AI-generated OCT-based probabilistic diagnoses ('AI diagnosis'); and for ten, both AI-diagnosis and AI-generated OCT segmentations ('AI diagnosis + segmentation') were provided. Cases were matched across the three types of presentation and were selected to include 40% ambiguous and 20% incorrect AI outputs. Optometrist diagnostic agreement with the predefined reference standard was lowest for 'AI diagnosis + segmentation' (204/300, 68%) compared to 'AI diagnosis' (224/300, 75% p = 0.010), and 'no Al' (242/300, 81%, p =  < 0.001). Agreement with AI diagnosis consistent with the reference standard decreased (174/210 vs 199/210, p = 0.003), but participants trusted the AI more (p = 0.029) with segmentations. Practitioner experience did not affect diagnostic responses (p = 0.24). More experienced participants were more confident (p = 0.012) and trusted the AI less (p = 0.038). Our findings also highlight issues around reference standard definition., (© 2024. The Author(s).)

Introduction: Novel teleophthalmology technologies have the potential to reduce unnecessary and inaccurate referrals between community optometry practices and hospital eye services and as a result improve patients' access to appropriate and timely eye care. However, little is known about the acceptability and facilitators and barriers to the implementations of these technologies in real life., Methods and Analysis: A theoretically informed, qualitative study will explore patients' and healthcare professionals' perspectives on teleophthalmology and Artificial Intelligence Decision Support System models of care. A combination of situated observations in community optometry practices and hospital eye services, semistructured qualitative interviews with patients and healthcare professionals and self-audiorecordings of healthcare professionals will be conducted. Participants will be purposively selected from 4 to 5 hospital eye services and 6-8 affiliated community optometry practices. The aim will be to recruit 30-36 patients and 30 healthcare professionals from hospital eye services and community optometry practices. All interviews will be audiorecorded, with participants' permission, and transcribed verbatim. Data from interviews, observations and self-audiorecordings will be analysed thematically and will be informed by normalisation process theory and an inductive approach., Ethics and Dissemination: Ethical approval has been received from London-Bromley research ethics committee. Findings will be reported through academic journals and conferences in ophthalmology, health services research, management studies and human-computer interaction., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2022. Re-use permitted under CC BY. Published by BMJ.)

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)., Competing Interests: Competing interests: PAK has previously been consultant for Google DeepMind., (© Author(s) (or their employer(s)) 2022. Re-use permitted under CC BY. Published by BMJ.)

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.

Systematic screening for diabetic retinopathy (DR) has been widely recommended for early detection in patients with diabetes to address preventable vision loss. However, substantial manpower and financial resources are required to deploy opportunistic screening and transition to systematic DR screening programs. The advent of artificial intelligence (AI) technologies may improve access and reduce the financial burden for DR screening while maintaining comparable or enhanced clinical effectiveness. To deploy an AI-based DR screening program in a real-world setting, it is imperative that health economic assessment (HEA) and patient safety analyses are conducted to guide appropriate allocation of resources and design safe, reliable systems. Few studies published to date include these considerations when integrating AI-based solutions into DR screening programs. In this article, we provide an overview of the current state-of-the-art of AI technology (focusing on deep learning systems), followed by an appraisal of existing literature on the applications of AI in ophthalmology. We also discuss practical considerations that drive the development of a successful DR screening program, such as the implications of false-positive or false-negative results and image gradeability. Finally, we examine different plausible methods for HEA and safety analyses that can be used to assess concerns regarding AI-based screening., Competing Interests: Disclosure: Y. Xie, None; D.V. Gunasekeran, None; K. Balaskas, None; P.A. Keane, None; D.A. Sim, None; L.M. Bachmann, None; C. Macrae, None; D.S.W. Ting, Deep learning system for retinal diseases (P), (Copyright 2020 The Authors.)

Background: Hospital Eye Services (HES) in the UK face an increasing number of optometric referrals driven by progress in retinal imaging. The National Health Service (NHS) published a 10-year strategy (NHS Long-Term Plan) to transform services to meet this challenge. In this study, we implemented a cloud-based referral platform to improve communication between optometrists and ophthalmologists., Methods: Retrospective cohort study conducted at Moorfields Eye Hospital, Croydon (NHS Foundation Trust, London, UK). Patients classified into the HES referral pathway by contributing optometrists have been included into this study. Main outcome measures was the reduction of unnecessary referrals., Results: After reviewing the patient's data in a web-based interface 54 (52%) out of 103 attending patients initially classified into the referral pathway did not need a specialist referral. Fourteen (14%) patients needing urgent treatment were identified. Usability was measured in duration for data input and reviewing which was an average of 9.2 min (median: 5.4; IQR: 3.4-8.7) for optometrists and 3.0 min (median: 3.0; IQR: 1.7-3.9) min for ophthalmologists. A variety of diagnosis was covered by this tool with dry age-related macular degeneration (n=34) being most common., Conclusion: After implementation more than half of the HES referrals have been avoided. This platform offers a digital-first solution that enables rapid-access eye care for patients in community optometrists, facilitates communication between healthcare providers and may serve as a foundation for implementation of artificial intelligence., Competing Interests: Competing interests: KB reports grants from Bayer AG, personal fees from Alimera, from Allergan, outside the submitted work; PAK reports other from Big Picture Eye Health, during the conduct of the study; personal fees from DeepMind, personal fees from Optos, personal fees from Novartis, personal fees from Bayer, personal fees from Allergan, personal fees from Heidelberg Engineering, personal fees from Topcon, personal fees from Carl Zeiss Meditec, personal fees from Haag Streit, personal fees from Santen, grants from National Institute for Health Research, grants from Fight For Sight UK, outside the submitted work; TM reports other from Big Picture Medical, outside the submitted work; In addition, TM has a patent 2016265973 pending; KK reports personal fees from Big Picture Eye Health, during the conduct of the study; grants and personal fees from Novartis Pharma, grants and personal fees from Bayer Pharma, personal fees from Zeiss, personal fees from Allergan, personal fees from Alcon, personal fees from Google Deepmind, AD has nothing to disclose; outside the submitted work; DS reports other from Big Picture Eye Health, during the conduct of the study; personal fees from Allergan, personal fees from Novartis, personal fees from Bayer, personal fees from Big Picture Eye Health, personal fees from Haag Streit, outside the submitted work; no other relationships or activities that could appear to have influenced the submitted work., (© Author(s) (or their employer(s)) 2020. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)

Purpose: Demographic changes as well as increasing referral rates from national screening services put pressure on available ophthalmologic resources in the United Kingdom. To improve resource allocation, virtual medical retina clinics were introduced in 2016 in Moorfields Eye Hospital, South Division. The scope of this work was to assess clinical outcomes of patients followed up in a virtual clinic setting., Design: Retrospective database study., Participants: Patients booked for a consecutive appointment in our virtual medical retina clinic., Methods: Seven hundred twenty-eight patients booked for their second virtual clinic appointment in a tertiary eye care referral center between November 2016 and July 2018 were identified retrospectively from our electronic health records and patient administration systems. Information about disease grade and clinical and visual outcomes was assessed., Main Outcome Measures: Clinical outcome of the virtual clinic visit, including virtual follow-up, urgent referral to face-to-face clinic, or discharge., Results: Seven hundred twelve of 728 patients received a clinical outcome. Four hundred ninety-seven patients (70%) were eligible for further virtual follow-up after the second virtual clinic visit, whereas 15% each (107 and 108 patients) were either discharged or referred to a face-to-face clinic. In total, 661 patients attended their appointments in person and were reviewed by trained staff. Seventeen patients were referred for urgent treatment and 8 patients were not suitable for virtual follow-up. In 542 (82%) of all patients, diabetic retinopathy was the most common diagnosis., Conclusions: This study reports clinical outcomes of a virtual model of care for medical retina clinics that imply safety of patient care in this clinic setting. This clinic format optimizes the use of already available resources and increases the skills of our existing workforce while maintaining high-quality clinical standards., (Copyright © 2019 American Academy of Ophthalmology. Published by Elsevier Inc. All rights reserved.)

Background: The increasing incidence of medical retinal diseases has created capacity issues across UK. In this study, we describe the implementation and outcomes of virtual medical retina clinics (VMRCs) at Moorfields Eye Hospital, South Division, London. It represents a promising solution to ensure that patients are seen and treated in a timely fashion METHODS: First attendances in the VMRC (September 2016-May 2017) were included. It was open to non-urgent external referrals and to existing patients in a face-to-face clinic (F2FC). All patients received visual acuity testing, dilated fundus photography and optical coherence tomography scans. Grading was performed by consultants, fellows and allied healthcare professionals. Outcomes of these virtual consultations and reasons for F2FC referrals were assessed., Results: A total number of 1729 patients were included (1543 were internal and 186 external referrals). The majority were diagnosed with diabetic retinopathy (75.1% of internal and 46.8% of external referrals). Of the internal referrals, 14.6% were discharged, 54.5% continued in VMRC and 30.9% were brought to a F2FC. Of the external referrals, 45.5% were discharged, 37.1% continued in VMRC and 17.4% were brought to a F2FC. The main reason for F2FC referrals was image quality (34.7%), followed by detection of potentially treatable disease (20.2%)., Conclusion: VMRC can be implemented successfully using existing resources within a hospital eye service. It may also serve as a first-line rapid-access clinic for low-risk referrals. This would enable medical retinal services to cope with increasing demand and efficiently allocate resources to those who require treatment., Competing Interests: Competing interests: None declared., (© Article author(s) (or their employer(s) unless otherwise stated in the text of the article) 2018. All rights reserved. No commercial use is permitted unless otherwise expressly granted.)

Background: Choroidal naevomelanocytic lesions are often identified as an incidental finding by community optometrists and referred for expert evaluation in hospital eye units or specialist ocular oncology centres. Optimal management strategy is undecided and most centres err on the side of caution. Our aim was to test a virtual model of service delivery relying on interpretation of imaging test results by non-medically trained graders., Methods: Patients with naevomelanocytic lesions referred to Manchester Royal Eye Hospital and Moorfields Eye Hospital were retrospectively included in this study. All patients underwent imaging tests including optical coherence tomography and ultrasound and management was subsequently decided clinically. Images were anonymised and transferred to the Moorfields Eye Hospital Reading Centre and were reviewed by a trained, masked grader who reached a management decision on the basis of a specific grading protocol. Agreement between decisions made on the basis of clinical examination and imaging ('gold standard') by an expert ophthalmologist in the clinic was compared with the decisions made by a masked ophthalmologist and a masked non-medical grader based on imaging tests alone., Results: There were 102 consecutive patients included in this study. Agreement between gold-standard clinical management and decisions made by masked, non-medical grader and masked ophthalmologist on the basis of imaging test results alone was 96.1% (κ=0.97) and 100%, respectively., Conclusions: In this pilot study, a streamlined, dedicated, virtual service for rapid assessment (within 2 weeks of referral) of choroidal naevomelanocytic lesions was shown to be feasible and safe. Such a model of service delivery may prove cost-efficient while optimising patient experience. Further prospective studies are required for formal validation of the proposed service model., (Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://www.bmj.com/company/products-services/rights-and-licensing/)

Demand in clinical services within the field of ophthalmology is predicted to rise over the future years. Artificial intelligence, in particular, machine learning-based systems, have demonstrated significant potential in optimizing medical diagnostics, predictive analysis, and management of clinical conditions. Ophthalmology has been at the forefront of this digital revolution, setting precedents for integration of these systems into clinical workflows. This review discusses integration of machine learning tools within ophthalmology clinical practices. We discuss key issues around ethical consideration, regulation, and clinical governance. We also highlight challenges associated with clinical adoption, sustainability, and discuss the importance of interoperability. Clinical integration is considered one of the most challenging stages within the implementation process. Successful integration necessitates a collaborative approach from multiple stakeholders around a structured governance framework, with emphasis on standardization across healthcare providers and equipment and software developers. [ABSTRACT FROM AUTHOR]