The Current State of Artificial Intelligence in Neuro-Ophthalmology. A Review

This article presents a summary of recent advances in the development and use of complex systems using artificial intelligence (AI) in neuro-ophthalmology. The aim of the following article is to present the principles of AI and algorithms that are currently being used or are still in the stage of evaluation or validation within the neuro-ophthalmology environment. For the purpose of this text, a literature search was conducted using specific keywords in available scientific databases, cumulatively up to April 2023. The AI systems developed across neuro-ophthalmology mostly achieve high sensitivity, specificity and accuracy. Individual AI systems and algorithms are subsequently selected, simply described and compared in the article. The results of the individual studies differ significantly, depending on the chosen methodology, the set goals, the size of the test, evaluated set, and the evaluated parameters. It has been demonstrated that the evaluation of various diseases will be greatly speeded up with the help of AI and make the diagnosis more efficient in the future, thus showing a high potential to be a useful tool in clinical practice even with a significant increase in the number of patients.

Diagnostic decisions of specialist optometrists exposed to ambiguous deep-learning outputs.

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.

Ophthalmology Optical Coherence Tomography Databases for Artificial Intelligence Algorithm: A Review.

BACKGROUND: Imaging plays a pivotal role in eye assessment. With the introduction of advanced machine learning and artificial intelligence (AI), the focus has shifted to imaging datasets in ophthalmology. While disparities and health inequalities hidden within data are well-documented, the ophthalmology field faces specific challenges to the creation and maintenance of datasets. Optical Coherence Tomography (OCT) is useful for the diagnosis and monitoring of retinal pathologies, making it valuable for AI applications. This review aims to identify and compare the landscape of publicly available optical coherence tomography databases for AI applications. METHODS: We conducted a literature review on OCT and AI articles with publicly accessible datasets, using PubMed, Scopus, and Web of Science databases. The review retrieved 183 articles, and after full-text analysis, 50 articles were included. From the included articles were identified 8 publicly available OCT datasets, focusing on patient demographics and clinical details for thorough assessment and comparison. RESULTS: The resulting datasets encompass 154,313 images collected from Spectralis, Cirrus HD, Topcon 3D, and Bioptigen devices. These datasets included normal exams, age-related macular degeneration, and diabetic maculopathy, among others. Comprehensive demographic information is available in one dataset and the USA is the most represented population. DISCUSSION: Current publicly available OCT databases for AI applications exhibit limitations, stemming from their non-representative nature and the lack of comprehensive demographic information. Limited datasets hamper research and equitable AI development. To promote equitable AI algorithmic development in ophthalmology, there is a need for the creation and dissemination of more representative datasets.

Recent developments of telemedicine in glaucoma.

PURPOSE OF REVIEW: Telemedicine has an increasingly significant role in the fields of ophthalmology and glaucoma. This review covers recent advancements in the development and optimization of teleglaucoma techniques and applications. RECENT FINDINGS: Glaucoma monitoring and diagnosis via remote tonometry, perimetry, and fundus imaging have become a possibility based on recent developments. Many applications work in combination with smart devices, virtual reality, and artificial intelligence and have been tested in patient populations against conventional "reference-standard" measurement tools, demonstrating promising results. Of note, there is still much progress to be made in teleglaucoma and telemedicine at large, such as accessibility to internet, broadband, and smart devices, application affordability, and reimbursement for remote services. However, continued development and optimization of these applications suggest that the implementation of remote monitoring will be a mainstay for glaucoma patient care. SUMMARY: Especially since the beginning of the COVID-19 pandemic, remote patient care has taken on an important role in medicine and ophthalmology. Remote versions of tonometry, perimetry, and fundus imaging may allow for a more patient-centered and accessible future for glaucoma care.

Manhattan Vision Screening and Follow-Up Study (NYC-SIGHT): Subanalysis of Referral to Ophthalmology.

PURPOSE: The Manhattan Vision Screening and Follow-up Study aims to provide access to eye care for underserved populations, detect native rates of ocular pathology, and refer participants with eye disease to ophthalmology. This subanalysis describes the reasons for referral to ophthalmology and identifies risk factors associated with being referred. METHODS: Enrolled participants were aged ≥40 years, living independently in public housing developments and able to provide consent for eye health screenings. Those with habitual visual acuity 20/40 or worse, intraocular pressure (IOP) 23-29 mmHg, or an unreadable fundus image failed and were scheduled with the on-site optometrist. The optometric exam determined whether further referral to ophthalmology for a clinic exam was warranted. Those with an abnormal image or IOP ≥30 mmHg were referred directly to ophthalmology. Main outcome was factors associated with referral to ophthalmology. RESULTS: A total of 708 individuals completed the eye health screening over 15 months. A total of 468 participants were referred to ophthalmology (250 had an abnormal image and 218 were referred by the optometrist). Those referred were predominantly older adults (mean age 70.0 ± 11.4 years), female (66.7%), African American (55.1%) and Hispanic (39.5%). Seventy percent of participants had not had a recent eye exam. Stepwise multivariate logistic regression analysis showed that participants with pre-existing glaucoma (OR 3.14, 95% CI 1.62 to 6.08, p = 0.001), an IOP ≥23 mmHg (OR 5.04, 95% 1.91 to 13.28, p = 0.001), or vision impairment (mild) (OR 2.51, 95% CI 1.68 to 3.77, p = 0.001) had significantly higher odds of being referred to ophthalmology. CONCLUSION: This targeted community-based study in Upper Manhattan provided access to eye care and detected a significant amount of ocular pathology requiring referral to ophthalmology in this high-risk population.

Detecting Eye Disease Using Vision Transformers Informed by Ophthalmology Resident Gaze Data.

We showcase two proof-of-concept approaches for enhancing the Vision Transformer (ViT) model by integrating ophthalmology resident gaze data into its training. The resulting Fixation-Order-Informed ViT and Ophthalmologist-Gaze-Augmented ViT show greater accuracy and computational efficiency than ViT for detection of the eye disease, glaucoma.Clinical relevance- By enhancing glaucoma detection via our gaze-informed ViTs, we introduce a new paradigm for medical experts to directly interface with medical AI, leading the way for more accurate and interpretable AI 'teammates' in the ophthalmic clinic.

Artificial intelligence in glaucoma: opportunities, challenges, and future directions.

Artificial intelligence (AI) has shown excellent diagnostic performance in detecting various complex problems related to many areas of healthcare including ophthalmology. AI diagnostic systems developed from fundus images have become state-of-the-art tools in diagnosing retinal conditions and glaucoma as well as other ocular diseases. However, designing and implementing AI models using large imaging data is challenging. In this study, we review different machine learning (ML) and deep learning (DL) techniques applied to multiple modalities of retinal data, such as fundus images and visual fields for glaucoma detection, progression assessment, staging and so on. We summarize findings and provide several taxonomies to help the reader understand the evolution of conventional and emerging AI models in glaucoma. We discuss opportunities and challenges facing AI application in glaucoma and highlight some key themes from the existing literature that may help to explore future studies. Our goal in this systematic review is to help readers and researchers to understand critical aspects of AI related to glaucoma as well as determine the necessary steps and requirements for the successful development of AI models in glaucoma.

Artificial intelligence within ophthalmologic diseases.

As ophthalmology is an increasingly busy medical specialty relying solidly on imaging technology, this review investigates the introduction of artificial intelligence to improve diagnostic performance and reduce human resources. In diabetic retinopathy screening, algorithms are now regulatory-approved for international markets but not yet tailored for the Danish system. In age-related macular degeneration, algorithms are now able to facilitate the classification and segmentation of disease activity, and in upcoming years, these are likely to assist us to improve diagnosis and provide subsequent clinical care.

Potency of teleophthalmology as a detection tool for diabetic retinopathy.

In China, the prevalence of diabetic retinopathy (DR) is increasing, so it is necessary to provide convenient and effective community outreach screening programs for DR, especially in rural and remote areas. The purpose of this study was to use the results of ophthalmologists as the gold standard to evaluate the accuracy of community general practitioners' judgement and grading of DR to find a feasible and convenient DR screening method to reduce the risk of visual impairment and blindness in known diabetes patients. Retinal images of 1646 diabetic patients who underwent DR screening through teleophthalmology at Nanchang First Hospital were collected for 30 months (January 2020 to June 2022). Retinal images were collected without medication for mydriasis, stored by community general practitioner, and diagnosed by both community general practitioner and ophthalmologist of our hospital through teleophthalmology. The grading of ophthalmologist was used as a reference or gold standard for comparison with that of community general practitioner. A total of 1646 patients and 3185 eyes were examined, including 2310 eyes with DR. The evaluation by the community general practitioner had a Kappa value of 0.578, sensitivity of 80.58%, specificity of 89.94%, and accuracy of 83.38%% in 2020; a Kappa value of 0.685, sensitivity of 95.43%, specificity of 78.55%, and accuracy of 90.77% in 2021; and a Kappa value of 0.744, sensitivity of 93.99%, specificity of 88.97%, and accuracy of 92.86% in 2022. Teleophthalmology helped with large-scale screening of DR and made it possible for community general practitioner to grade images with high accuracy after appropriate training. It is possible to solve the current shortage of eye care personnel, promote the early recognition of disease and reduce the impact of diabetes-associated blindness.

[Chinese expert consensus on telemedicine for diabetic retinopathy (2023)].

The practice of telemedicine for diabetic retinopathy (DR) is an important measure to integrate the advantages of multi-level medical and health institutions and ensure quality medical services and safe treatment. According to both the clinical experience in preventive medicine and ophthalmology and the domestic and foreign guidelines, the experts of the Public Health Ophthalmology Branch of Chinese Preventive Medicine Association have developed the consensus opinions on the requirements of operating systems, quality requirements of fundus images, diagnostic criteria, recommendation and referral standards, and management objectives of DR telemedicine. The formulation of this consensus will help to improve the screening and diagnosis capacity of primary medical institutions for DR and contribute to the development of Healthy China.

The Current State of Artificial Intelligence in Neuro-Ophthalmology. A Review.

This article presents a  summary of recent advances in the development and use of complex systems using artificial intelligence (AI) in neuroophthalmology. The aim of the following article is to present the principles of AI and algorithms that are currently being used or are still in the stage of evaluation or validation within the neuro-ophthalmology environment. For the purpose of this text, a literature search was conducted using specific keywords in available scientific databases, cumulatively up to April 2023. The AI systems developed across neuro-ophthalmology mostly achieve high sensitivity, specificity and accuracy. Individual AI systems and algorithms are subsequently selected, simply described and compared in the article. The results of the individual studies differ significantly, depending on the chosen methodology, the set goals, the size of the test, evaluated set, and the evaluated parameters. It has been demonstrated that the evaluation of various diseases will be greatly speeded up with the help of AI and make the diagnosis more efficient in the future, thus showing a high potential to be a useful tool in clinical practice even with a significant increase in the number of patients.

Artificial intelligence in ophthalmology: The path to the real-world clinic.

Artificial intelligence (AI) has great potential to transform healthcare by enhancing the workflow and productivity of clinicians, enabling existing staff to serve more patients, improving patient outcomes, and reducing health disparities. In the field of ophthalmology, AI systems have shown performance comparable with or even better than experienced ophthalmologists in tasks such as diabetic retinopathy detection and grading. However, despite these quite good results, very few AI systems have been deployed in real-world clinical settings, challenging the true value of these systems. This review provides an overview of the current main AI applications in ophthalmology, describes the challenges that need to be overcome prior to clinical implementation of the AI systems, and discusses the strategies that may pave the way to the clinical translation of these systems.

A study establishing sensitivity and accuracy of smartphone photography in ophthalmologic community outreach programs: Review of a smart eye camera.

Purpose: Diseases affecting the cornea are a major cause of corneal blindness globally. The pressing issue we are facing today is the lack of diagnostic devices in rural areas to diagnose these conditions. The aim of the study is to establish sensitivity and accuracy of smartphone photography using a smart eye camera (SEC) in ophthalmologic community outreach programs. Methods: In this pilot study, a prospective non-randomized comparative analysis of inter-observer variability of anterior segment imaging recorded using an SEC was performed. Consecutive 100 patients with corneal pathologies, who visited the cornea specialty outpatient clinic, were enrolled. They were examined with a conventional non-portable slit lamp by a cornea consultant, and the diagnoses were recorded. This was compared with the diagnoses made by two other consultants based on SEC videos of the anterior segment of the same 100 patients. The accuracy of SEC was accessed using sensitivity, specificity, PPV, and NPV. Kappa statistics was used to find the agreement between two consultants by using STATA 17.0 (Texas, USA). Results: There was agreement between the two consultants to diagnosing by using SEC. Above 90% agreements were found in all the diagnoses, which were statistically significant (P-value < 0.001). More than 90% sensitivity and a negative predictive value were found. Conclusion: SEC can be used successfully in the community outreach programs like field visits, eye camps, teleophthalmology, and community centers, where either a clinical setup is lacking or ophthalmologists are not available.

A Review of Smartphone Adapters Capable of Imaging the Anterior Segment in Ophthalmology.

Teleophthalmology is a widely recognised way to provide health care to patients living in rural and remote regions by leveraging limited clinician availability and resources. This is most important in low socioeconomic areas, where the disparity between prevalence of preventable blindness and practicing ophthalmologists is greatest. The ubiquity and accessibility of smartphones allow them to be utilised in a clinical setting and facilitate teleophthalmology. While the current market of smartphone adapters capable of imaging ocular pathology is expanding, few focus on the anterior segment and operate independently of the slit-lamp microscope. This article reviews the available smartphone adapters capable of imaging anterior segment pathology.

Tracking Online Interest in Artificial Intelligence in Ophthalmology Using Google Trends.

PURPOSE: To examine trends in internet search queries related to artificial intelligence (AI) in ophthalmology and determine the correlation between online interest in AI, capital investment in AI, and peer-reviewed indexed publications regarding AI and ophthalmology. METHODS: Online search trends for "AI retina", "AI eye", and "AI healthcare" were obtained via Google Trends from 2016 to 2022 on a relative interest scale in 1-week intervals. Global venture financing of AI- and machine learning (ML)-focused companies in healthcare was tracked from 2010 to 2019 from the consulting company, Klynveld Peat Marwick Goerdeler (KPMG), and the technology market intelligence company, CB Insights. Citation count from pubmed.gov was determined using the search query "artificial intelligence retina" from 2012 to 2021. RESULTS: An increasingly linear growth in online search trends for "AI retina", "AI eye", and "AI healthcare" keyword searches was observed between 2016 and 2022. Global venture financing of AI and ML companies in healthcare also increased exponentially over the same time frame. There was an exponential increase in citations with nearly a 10-fold increase as reported by PubMed from 2015 onwards for the "artificial intelligence retina" search query. There was a significant and positive correlation between online search trends and investment trends (correlation coefficients of 0.98-0.99 and p-values <0.05) and between online search trends and citation count trends (correlation coefficients of 0.98-0.99 and p-values <0.05). CONCLUSIONS: These results demonstrate that the applications of AI and ML in ophthalmology are increasingly being investigated, financed, and formally researched, suggesting a prominent role for AI-derived tools in ophthalmology clinical practice in the near future.

Feasibility Analysis of Teleophthalmology Diagnosis and Referral in Remote Areas of Taiwan.

Background: Remote areas of Taiwan lack routine and specialized ophthalmology services. This study aimed to analyze feasibility of teleophthalmology service for diseases diagnosis and referral in remote areas of Taiwan. Methods: A retrospective study of medical records from 11 remote teleophthalmology clinics in the Taitung area of Taiwan was conducted from May 2020 to December 2021. Vision and intraocular pressure were checked. Ophthalmic imaging was performed by local trained nurses using a hand-held ophthalmoscope and slit lamp biomicroscope. The images were transmitted by telemedicine system to a medical center. Consultation was conducted via face-to-face real-time video calls. Ophthalmologists in the medical center provided diagnosis and treatment advice based on the real-time images and interactive history taking via the telemedicine system. All the images and data were collected and well-reviewed by ophthalmologists in the medical center, and disease prevalence and referral were analyzed for the program. A small-scale satisfaction questionnaire survey was conducted for efficacy evaluation of the program. Results: A total of 1,401 medical records from 1,094 patients were collected and screened. Patients' ages ranged from 9 months to 94 years, with a mean age of 57.27 (standard deviation ±20.47) years. The most frequent ophthalmologic diagnosis was dry eye disease (20.2%), followed by conjunctivitis (12.4%). Among 322 patients with underlying diseases of diabetes mellitus, 59 patients (18.3%) were diagnosed with diabetic retinopathy. Major diagnosis was made in 102 patients (7.3%) and referral to hospital for further management was suggested. This program had high overall satisfaction score of 89% (mean 4.43 ± 0.52 points) in satisfaction questionnaire survey. Conclusion: Teleophthalmology provides an alternative tool for ocular disease diagnosis and screening for patients in remote areas, especially during the COVID-19 pandemic. This service helps to detect major but undiagnosed diseases and promotes health care accessibility and availability in remote areas that lack specialists.

[Challenges and countermeasures in the development of artificial intelligence research in ophthalmology].

The advent of artificial intelligence (AI) technology has led to revolutionary advancements in the diagnosis and treatment of ophthalmic diseases, introducing a novel AI-assisted diagnostic approach for ophthalmology that is rich in imaging diagnostic technologies. However, as clinical applications continue to evolve, AI research in ophthalmology faces challenges such as the lack of standardized datasets and innovative algorithm models, insufficient cross-modal information fusion, and limited clinical interpretability. In response to the growing demand for AI research in ophthalmology, it is essential to establish ophthalmic data standards and sharing platforms, innovate core algorithms, and develop clinical logic interpretable models for the screening, diagnosis, and prediction of eye diseases. Additionally, the deep integration of cutting-edge technologies such as 5G, virtual reality, and surgical robots would advance the development of ophthalmic intelligent medicine into a new phase.

Diabetic retinopathy screenings in West Virginia: an assessment of teleophthalmology implementation.

BACKGROUND: The prevalence of diabetes in the state of West Virginia (WV) is amongst the highest in the United States, making diabetic retinopathy (DR) and diabetic macular edema (DME) a major epidemiological concern within the state. Several challenges exist regarding access to eye care specialists for DR screening in this rural population. A statewide teleophthalmology program has been implemented. We analyzed real-world data acquired via these systems to explore the concordance between image findings and subsequent comprehensive eye exams and explore the impact of age on image gradeability and patient distance from the West Virginia University (WVU) Eye Institute on follow-up. METHODS: Nonmydriatic fundus images of diabetic eyes acquired at primary care clinics throughout WV were reviewed by retina specialists at the WVU Eye Institute. Analysis included the concordance between image interpretations and dilated examination findings, hemoglobin A1c (HbA1c) levels and DR presence, image gradeability and patient age, and distance from the WVU Eye Institute and follow-up compliance. RESULTS: From the 5,512 fundus images attempted, we found that 4,267 (77.41%) were deemed gradable.  Out of the 289 patients whose image results suggested DR, 152 patients (52.6%) followed up with comprehensive eye exams-finding 101 of these patients to truly have DR/DME and allowing us to determine a positive predictive value of 66.4%. Patients within the HbA1c range of 9.1-14.0% demonstrated significantly greater prevalence of DR/DME (p < 0.01).  We also found a statistically significant decrease in image gradeability with increased age.  When considering distance from the WVU Eye Institute, it was found that patients who resided within 25 miles demonstrated significantly greater compliance to follow-up (60% versus 43%, p < 0.01). CONCLUSIONS: The statewide implementation of a telemedicine program intended to tackle the growing burden of DR in WV appears to successfully bring concerning patient cases to the forefront of provider attention.  Teleophthalmology addresses the unique rural challenges of WV, but there is suboptimal compliance to essential follow-up with comprehensive eye exams. Obstacles remain to be addressed if these systems are to effectively improve outcomes in DR/DME patients and diabetic patients at risk of developing these sight-threatening pathologies.