International Classification System for Ocular Complications of Anti-Vascular Endothelial Growth Factor Agents in Clinical Trials.

OBJECTIVE: Complications associated with intravitreal anti-vascular endothelial growth factor (VEGF) therapies are inconsistently reported in the literature, thus limiting an accurate evaluation and comparison of safety between studies. This study aimed to develop a standardized classification system for anti-VEGF ocular complications using the Delphi consensus process. DESIGN: Systematic review and Delphi consensus process. PARTICIPANTS: 25 international retinal specialists participated in the Delphi consensus survey. METHODS: A systematic literature search was conducted to identify complications of intravitreal anti-VEGF agent administration based on randomized controlled trials (RCTs) of anti-VEGF therapy. A comprehensive list of complications was derived from these studies, and this list was subjected to iterative Delphi consensus surveys involving international retinal specialists that voted on inclusion, exclusion, rephrasing, and addition of complications. As well, surveys determined specifiers for the selected complications. This iterative process helped refine the final classification system. MAIN OUTCOME MEASURES: The proportion of retinal specialists who choose to include or exclude complications associated with anti-VEGF administration. RESULTS: After screening 18,229 articles, 130 complications were initially categorized from 145 included RCTs. Participant consensus via the Delphi method resulted in the inclusion of 91 (70%) complications after three rounds. After incorporating further modifications made based on participant suggestions, such as rewording certain phrases and combining similar terms, 24 redundant complications were removed, leaving a total of 67 (52%) complications in the final list. A total of 14 (11%) complications met exclusion thresholds and were eliminated by participants across both rounds. All other remaining complications not meeting inclusion or exclusion thresholds were also excluded from the final classification system after the Delphi process terminated. In addition, 47 out of 75 (63%) proposed complication specifiers were included based on participant agreement. CONCLUSION: Using the Delphi consensus process, a comprehensive, standardized classification system consisting of 67 ocular complications and 47 unique specifiers was established for intravitreal anti-VEGF agents in clinical trials. The adoption of this system in future trials could improve consistency and quality of adverse event reporting, potentially facilitating more accurate risk-benefit analyses.

Six-Year Outcomes in Subjects with Polypoidal Choroidal Vasculopathy in the EVEREST II Study.

INTRODUCTION: The EVEREST II study previously reported that intravitreally administered ranibizumab (IVR) combined with photodynamic therapy (PDT) achieved superior visual gain and polypoidal lesion closure compared to IVR alone in patients with polypoidal choroidal vasculopathy (PCV). This follow-up study reports the long-term outcomes 6 years after initiation of the EVEREST II study. METHODS: This is a non-interventional cohort study of 90 patients with PCV from 16 international trial sites who originally completed the EVEREST II study. The long-term outcomes were assessed during a recall visit at about 6 years from commencement of EVEREST II. RESULTS: The monotherapy and combination groups contained 41 and 49 participants, respectively. The change in best-corrected visual acuity (BCVA) from baseline to year 6 was not different between the monotherapy and combination groups; - 7.4 ± 23.0 versus - 6.1 ± 22.4 letters, respectively. The combination group had greater central subfield thickness (CST) reduction compared to the monotherapy group at year 6 (- 179.9 vs - 74.2 µm, p = 0.011). Fewer eyes had subretinal fluid (SRF)/intraretinal fluid (IRF) in the combination versus monotherapy group at year 6 (35.4% vs 57.5%, p = 0.032). Factors associated with BCVA at year 6 include BCVA (year 2), CST (year 2), presence of SRF/IRF at year 2, and number of anti-VEGF treatments (years 2-6). Factors associated with presence of SRF/IRF at year 6 include combination arm (OR 0.45, p = 0.033), BCVA (year 2) (OR 1.53, p = 0.046), and presence of SRF/IRF (year 2) (OR 2.59, p = 0.042). CONCLUSION: At 6 years following the EVEREST II study, one-third of participants still maintained good vision. As most participants continued to require treatment after exiting the initial trial, ongoing monitoring and re-treatment regardless of polypoidal lesion status are necessary in PCV. TRIAL REGISTRATION: ClinicalTrials.gov identifier, NCT01846273.

Faricimab Treat-and-Extend for Diabetic Macular Edema: Two-Year Results from the Randomized Phase 3 YOSEMITE and RHINE Trials.

PURPOSE: To evaluate the 2-year efficacy, durability, and safety of dual angiopoietin-2 and vascular endothelial growth factor (VEGF) A pathway inhibition with intravitreal faricimab according to a personalized treat-and-extend (T&E)-based regimen with up to every-16-week dosing in the YOSEMITE and RHINE (ClinicalTrials.gov identifiers, NCT03622580 and NCT03622593, respectively) phase 3 trials of diabetic macular edema (DME). DESIGN: Randomized, double-masked, noninferiority phase 3 trials. PARTICIPANTS: Adults with visual acuity loss (best-corrected visual acuity [BCVA] of 25-73 letters) due to center-involving DME. METHODS: Patients were randomized 1:1:1 to faricimab 6.0 mg every 8 weeks, faricimab 6.0 mg T&E (previously referred to as personalized treatment interval), or aflibercept 2.0 mg every 8 weeks. The T&E up to every-16-week dosing regimen was based on central subfield thickness (CST) and BCVA change. MAIN OUTCOME MEASURES: Included changes from baseline in BCVA and CST, number of injections, durability, absence of fluid, and safety through week 100. RESULTS: In YOSEMITE and RHINE (n = 940 and 951, respectively), noninferior year 1 visual acuity gains were maintained through year 2; mean BCVA change from baseline at 2 years (weeks 92, 96, and 100 average) with faricimab every 8 weeks (YOSEMITE and RHINE, +10.7 letters and +10.9 letters, respectively) or T&E (+10.7 letters and +10.1 letters, respectively) were comparable with aflibercept every 8 weeks (+11.4 letters and +9.4 letters, respectively). The median number of study drug injections was lower with faricimab T&E (YOSEMITE and RHINE, 10 and 11 injections, respectively) versus faricimab every 8 weeks (15 injections) and aflibercept every 8 weeks (14 injections) across both trials during the entire study. In the faricimab T&E arms, durability was improved further during year 2, with > 60% of patients receiving every-16-week dosing and approximately 80% receiving every-12-week or longer dosing at week 96. Almost 80% of patients who achieved every-16-week dosing at week 52 maintained every-16-week dosing without an interval reduction through week 96. Mean CST reductions were greater (YOSEMITE/RHINE weeks 92/96/100 average: faricimab every 8 weeks -216.0/-202.6 µm, faricimab T&E -204.5/-197.1 µm, aflibercept every 8 weeks -196.3/-185.6 µm), and more patients achieved absence of DME (CST < 325 µm; YOSEMITE/RHINE weeks 92-100: faricimab every 8 weeks 87%-92%/88%-93%, faricimab T&E 78%-86%/85%-88%, aflibercept every 8 weeks 77%-81%/80%-84%) and absence of intraretinal fluid (YOSEMITE/RHINE weeks 92-100: faricimab every 8 weeks 59%-63%/56%-62%, faricimab T&E 43%-48%/45%-52%, aflibercept every 8 weeks 33%-38%/39%-45%) with faricimab every 8 weeks or T&E versus aflibercept every 8 weeks through year 2. Overall, faricimab was well tolerated, with a safety profile comparable with that of aflibercept. CONCLUSIONS: Clinically meaningful visual acuity gains from baseline, anatomic improvements, and extended durability with intravitreal faricimab up to every 16 weeks were maintained through year 2. Faricimab given as a personalized T&E-based dosing regimen supports the role of dual angiopoietin-2 and VEGF-A inhibition to promote vascular stability and to provide durable efficacy for patients with DME. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Risk Stratification for Diabetic Retinopathy Screening Order Using Deep Learning: A Multicenter Prospective Study.

Purpose: Real-world evaluation of a deep learning model that prioritizes patients based on risk of progression to moderate or worse (MOD+) diabetic retinopathy (DR). Methods: This nonrandomized, single-arm, prospective, interventional study included patients attending DR screening at four centers across Thailand from September 2019 to January 2020, with mild or no DR. Fundus photographs were input into the model, and patients were scheduled for their subsequent screening from September 2020 to January 2021 in order of predicted risk. Evaluation focused on model sensitivity, defined as correctly ranking patients that developed MOD+ within the first 50% of subsequent screens. Results: We analyzed 1,757 patients, of which 52 (3.0%) developed MOD+. Using the model-proposed order, the model's sensitivity was 90.4%. Both the model-proposed order and mild/no DR plus HbA1c had significantly higher sensitivity than the random order (P < 0.001). Excluding one major (rural) site that had practical implementation challenges, the remaining sites included 567 patients and 15 (2.6%) developed MOD+. Here, the model-proposed order achieved 86.7% versus 73.3% for the ranking that used DR grade and hemoglobin A1c. Conclusions: The model can help prioritize follow-up visits for the largest subgroups of DR patients (those with no or mild DR). Further research is needed to evaluate the impact on clinical management and outcomes. Translational Relevance: Deep learning demonstrated potential for risk stratification in DR screening. However, real-world practicalities must be resolved to fully realize the benefit.

Large language models and their impact in ophthalmology.

The advent of generative artificial intelligence and large language models has ushered in transformative applications within medicine. Specifically in ophthalmology, large language models offer unique opportunities to revolutionise digital eye care, address clinical workflow inefficiencies, and enhance patient experiences across diverse global eye care landscapes. Yet alongside these prospects lie tangible and ethical challenges, encompassing data privacy, security, and the intricacies of embedding large language models into clinical routines. This Viewpoint highlights the promising applications of large language models in ophthalmology, while weighing up the practical and ethical barriers towards their real-world implementation. This Viewpoint seeks to stimulate broader discourse on the potential of large language models in ophthalmology and to galvanise both clinicians and researchers into tackling the prevailing challenges and optimising the benefits of large language models while curtailing the associated risks.

Assessment of Direct Costs of Admission Due to Presumed Microbial Keratitis in a Tertiary Referral Hospital in Thailand: A 7-Year Retrospective Study.

Objective: To evaluate the direct healthcare cost of admission and examine the effects of cost drivers of treating presumed microbial keratitis (MK) at a tertiary referral hospital. Design: Retrospective study. Methods: A total of 741 patients who presented with MK were included. All information regarding costs was collected, and demographic data were employed for risk factor analysis. Results: The total cost of treating MK over a 7-year period at Rajavithi Hospital was US$14,514,625.04, while the median cost was US$10,840.17 per patient (Q1-3, US$5866.56-24,172.28). The medical professional services were the highest cost category in terms of both total cost of treatment over 7 years and median cost per patient, accounting for US$6,474,718.43 and US$5235.20 (Q1-3, US$2582.79-10,474.24) respectively. In 2020, the total cost of treatment declined, corresponding with fewer hospitalized patients; however, the median cost per patient was the highest of all years, amounting to US$15,089.90 (Q1-3, US$8064.17-29102.50), while the median cost per patient from 2014 to 2019 was US$9969.96 (Q1-3, US$5177.98-21,942.68). Statistical significance was found in the median cost per patient in 2020 compared to the median cost per patient in 2014-2019 (p-value 0.019). Risk factors associated with the more expensive cost of treatment were longer length of stay (LOS); age more than 60 years old; readmission; diabetes mellitus (DM); hypertension; and heart disease. Conclusion: There were several key factors impacting the direct healthcare costs of severe MK treatment. Medical professional services emerged as the most substantial cost category, while longer hospital stays, older age groups, readmission cases, and comorbidities such as diabetes mellitus, hypertension, and heart disease were all linked to elevated treatment expenses. There were no statistically significant differences in the direct medical expenses during hospitalization associated with treating severe MK, whether the culture results were positive or negative, or regardless of the type of cultured organism utilized.

Clinical Correlation of Retinal Fluid Fluctuation Represented by Fluctuation Index in Wet Age-Related Macular Degeneration: TOWER Study Report 2.

Purpose: To explore outcomes and biomarkers associated with retinal fluid instability represented by a new parameter in neovascular age-related macular degeneration (nAMD). Methods: Patients with treatment-naïve nAMD receiving anti-vascular endothelial growth factor (VEGF) injections for a duration of 1 to 3 years were consecutively reviewed. Fluctuation Index (FI) of each eye, calculated by averaging the sum of differences in 1-mm central subfield thickness between each follow-up from months 3 to 24, was arranged into ascending order from the lowest to the highest and split equally into low, moderate, and high fluctuation groups. Outcomes were analyzed at 24 months. Results: Of 558 eyes, FI values showed a negative correlation with a degree-response gradient with 24-month visual improvement. After controlling for baseline best-corrected visual acuity and potential confounders, eyes with low fluctuation gained more Early Treatment Diabetic Retinopathy Study letters than those in the moderate and high fluctuation group (Δ, 10.1 and 14.0 letters, respectively). Significant best-corrected visual acuity improvement from baseline to month 24 (11.8 letters) was observed exclusively in the low fluctuation group despite the indifference in the number of injections and types of anti-VEGF drug used among groups. Patients presenting with central subfield thickness of ≥405 µm or intraretinal fluid coinciding with subretinal fluid showed a significant association with foveal thickness instability during the maintenance phase. Conclusions: Apart from the central subfield thickness values, unstable macular thickening represented by the FI was associated with some baseline features and may contribute to substandard visual outcomes. Translational Relevance: FI may be a valuable tool for assessing therapeutic adequacy in the treatment of nAMD.

Efficacy, Durability, and Safety of Faricimab in Patients From Asian Countries With Diabetic Macular Edema: 1-Year Subgroup Analysis of the Phase III YOSEMITE and RHINE Trials.

PURPOSE: To assess the 1-year efficacy, durability, and safety of faricimab in patients with diabetic macular edema from Asian and non-Asian countries. DESIGN: Global, multicenter, randomized, double-masked, active comparator-controlled, phase III trials. METHODS: Subgroup analysis of patients from Asian (N=144) and non-Asian (N=1747) countries randomized to faricimab 6.0 mg every 8 weeks (Q8W), faricimab per personalized treatment interval (PTI), or aflibercept 2.0 mg Q8W in the YOSEMITE/RHINE (NCT03622580/NCT03622593) trials. Primary endpoint: best-corrected visual acuity (BCVA) changes from baseline at 1 year, averaged over weeks 48, 52, and 56. RESULTS: Mean BCVA change from baseline at 1 year in the Asian country subgroup was similar between arms: faricimab Q8W (n=50), +10.9 (95% CI: 8.6-13.2); faricimab PTI (n=48) +10.0 (7.7-12.4) letters; aflibercept Q8W (n=46) +9.0 (6.6-11.4) letters. BCVA gains in the non-Asian country subgroup (n=582, 584, 581) were +11.3 (10.5-12.1), +11.2 (10.5-12.0), and +10.7 (9.9-11.5) letters, respectively. At 1 year, 49% of Asian country patients in the faricimab PTI arm achieved Q16W dosing (vs. 52% non-Asian) and 78% achieved ≥Q12W dosing (vs. 72% non-Asian). Anatomic improvementswere generally greater with faricimab versus aflibercept and similar between the Asian and non-Asian country subgroups. Faricimab was well tolerated, with no new safety signals. CONCLUSIONS: Vision, durability, anatomic, and safety outcomes were generally similar between the Asian and non-Asian country subgroups, suggesting that global YOSEMITE/RHINE results may be generalized to the Asian population. These data support the benefit-risk profile of faricimab for treating Asian patients with diabetic macular edema.

Patient, family member, and health care provider perspective on barriers and facilitators to diabetic retinopathy screening in Thailand: A qualitative study.

OBJECTIVES: Diabetic retinopathy (DR) can cause significant visual impairment which can be largely avoided by early detection through proper screening and treatment. People with DR face a number of challenges from early detection to treatment. The aim of this study was to investigate factors that influence DR screening in Thailand and to identify barriers to follow-up compliance from patient, family member, and health care provider (HCP) perspectives. METHODS: A total of 15 focus group discussions (FGDs) were held, each with five to twelve participants. There were three distinct stakeholders: diabetic patients (n = 47) presenting to a diabetic retinopathy clinic in Thailand, their family members (n = 41), and health care providers (n = 34). All focus group conversations were transcribed verbatim. Thematic analysis was used to examine textual material. RESULTS: Different themes emerged from the FGD on knowledge about diabetes, self-care behaviors of diabetes mellitus (DM), awareness about DR, barriers to DR screening, and the suggested solutions to address those barriers. Data showed lower knowledge and awareness about diabetes and DR in both patients and family members. Long waiting times, financial issues, and lack of a person to accompany appointments were identified as the major deterrents for attending DR screening. Family support for patients was found to vary widely, with some patients reporting to have received adequate support while others reported having received minimal support. Even though insurance covered the cost of attending diabetes/DR screening program, some patients did not show up for their appointments. CONCLUSION: Patients need to be well-informed about the asymptomatic nature of diabetes and DR. Communication at the patient level and shared decision-making with HCPs are essential. Family members and non-physician clinicians (such as diabetes nurses, diabetes educators, physician assistants) who work in the field of diabetes play a vital role in encouraging patients to attend diabetes and DR follow-ups visits regularly.

Potential Ocular Biomarkers for Early Detection of Alzheimer's Disease and Their Roles in Artificial Intelligence Studies.

Alzheimer's disease (AD) is the leading cause of dementia worldwide. Early detection is believed to be essential to disease management because it enables physicians to initiate treatment in patients with early-stage AD (early AD), with the possibility of stopping the disease or slowing disease progression, preserving function and ultimately reducing disease burden. The purpose of this study was to review prior research on the use of eye biomarkers and artificial intelligence (AI) for detecting AD and early AD. The PubMed database was searched to identify studies for review. Ocular biomarkers in AD research and AI research on AD were reviewed and summarized. According to numerous studies, there is a high likelihood that ocular biomarkers can be used to detect early AD: tears, corneal nerves, retina, visual function and, in particular, eye movement tracking have been identified as ocular biomarkers with the potential to detect early AD. However, there is currently no ocular biomarker that can be used to definitely detect early AD. A few studies that used AI with ocular biomarkers to detect AD reported promising results, demonstrating that using AI with ocular biomarkers through multimodal imaging could improve the accuracy of identifying AD patients. This strategy may become a screening tool for detecting early AD in older patients prior to the onset of AD symptoms.

Retinotomies and retinectomies: A review of indications, techniques, results, and complications.

Retinotomy refers to "cutting" or "incising" the retina, whereas retinectomy denotes "excising" the retina. Retinotomies and retinectomies aid in tackling traction and retinal shortening that persist following membrane dissection and scleral buckling. We performed a literature search using Google Scholar and PubMed, followed by a review of the references procured. All relevant literature was studied in detail and summarized. We discuss the indications of retinotomies and retinectomies for relaxing retinal stiffness, accessing the subretinal space for choroidal neovascular membrane, hemorrhage and abscess clearance, drainage retinotomies to allow retinal flattening, radial retinotomies to release circumferential traction, harvesting free retinal grafts, and prophylactic chorioretinectomies in trauma.

Recent evidence of economic evaluation of artificial intelligence in ophthalmology.

PURPOSE OF REVIEW: Health economic evaluation (HEE) is essential for assessing value of health interventions, including artificial intelligence. Recent approaches, current challenges, and future directions of HEE of artificial intelligence in ophthalmology are reviewed. RECENT FINDINGS: Majority of recent HEEs of artificial intelligence in ophthalmology were for diabetic retinopathy screening. Two models, one conducted in the rural USA (5-year period) and another in China (35-year period), found artificial intelligence to be more cost-effective than without screening for diabetic retinopathy. Two additional models, which compared artificial intelligence with human screeners in Brazil and Thailand for the lifetime of patients, found artificial intelligence to be more expensive from a healthcare system perspective. In the Thailand analysis, however, artificial intelligence was less expensive when opportunity loss from blindness was included. An artificial intelligence model for screening retinopathy of prematurity was cost-effective in the USA. A model for screening age-related macular degeneration in Japan and another for primary angle close in China did not find artificial intelligence to be cost-effective, compared with no screening. The costs of artificial intelligence varied widely in these models. SUMMARY: Like other medical fields, there is limited evidence in assessing the value of artificial intelligence in ophthalmology and more appropriate HEE models are needed.

Colour vision restrictions for driving: an evidence-based perspective on regulations in ASEAN countries compared to other countries.

Colour vision deficiency is an impairment in discriminating colours. Beyond occupational opportunities, colour vision-based restrictions may limit driving, which is a daily task for many people. This review aims to compare existing colour vision requirements for obtaining a driving license in southeast Asian countries to the rest of the world. Subsequently, to review existing published literature and provide evidence-based recommendations for future guidelines for colour-deficient drivers. Color vision requirements for obtaining a driving license vary widely amongst countries. While colour-deficient drivers may face mild challenges in driving, increased awareness and developing effective compensatory strategies could enable them to drive safely. The current evidence does not support a strict exclusion of all colour-deficient individuals from driving. Instead, emphasis is needed on screening to increase awareness and insight into their disability. Future studies should consider compensatory adaptive strategies that are specific for high-risk situations such as challenging driving conditions.

The impact of artificial intelligence on retinal disease management: Vision Academy retinal expert consensus.

PURPOSE OF REVIEW: The aim of this review is to define the "state-of-the-art" in artificial intelligence (AI)-enabled devices that support the management of retinal conditions and to provide Vision Academy recommendations on the topic. RECENT FINDINGS: Most of the AI models described in the literature have not been approved for disease management purposes by regulatory authorities. These new technologies are promising as they may be able to provide personalized treatments as well as a personalized risk score for various retinal diseases. However, several issues still need to be addressed, such as the lack of a common regulatory pathway and a lack of clarity regarding the applicability of AI-enabled medical devices in different populations. SUMMARY: It is likely that current clinical practice will need to change following the application of AI-enabled medical devices. These devices are likely to have an impact on the management of retinal disease. However, a consensus needs to be reached to ensure they are safe and effective for the overall population.

Current status and practical considerations of artificial intelligence use in screening and diagnosing retinal diseases: Vision Academy retinal expert consensus.

PURPOSE OF REVIEW: The application of artificial intelligence (AI) technologies in screening and diagnosing retinal diseases may play an important role in telemedicine and has potential to shape modern healthcare ecosystems, including within ophthalmology. RECENT FINDINGS: In this article, we examine the latest publications relevant to AI in retinal disease and discuss the currently available algorithms. We summarize four key requirements underlining the successful application of AI algorithms in real-world practice: processing massive data; practicability of an AI model in ophthalmology; policy compliance and the regulatory environment; and balancing profit and cost when developing and maintaining AI models. SUMMARY: The Vision Academy recognizes the advantages and disadvantages of AI-based technologies and gives insightful recommendations for future directions.

Investigating public behavior with artificial intelligence-assisted detection of face mask wearing during the COVID-19 pandemic.

OBJECTIVES: Face masks are low-cost, but effective in preventing transmission of COVID-19. To visualize public's practice of protection during the outbreak, we reported the rate of face mask wearing using artificial intelligence-assisted face mask detector, AiMASK. METHODS: After validation, AiMASK collected data from 32 districts in Bangkok. We analyzed the association between factors affecting the unprotected group (incorrect or non-mask wearing) using univariate logistic regression analysis. RESULTS: AiMASK was validated before data collection with accuracy of 97.83% and 91% during internal and external validation, respectively. AiMASK detected a total of 1,124,524 people. The unprotected group consisted of 2.06% of incorrect mask-wearing group and 1.96% of non-mask wearing group. Moderate negative correlation was found between the number of COVID-19 patients and the proportion of unprotected people (r = -0.507, p<0.001). People were 1.15 times more likely to be unprotected during the holidays and in the evening, than on working days and in the morning (OR = 1.15, 95% CI 1.13-1.17, p<0.001). CONCLUSIONS: AiMASK was as effective as human graders in detecting face mask wearing. The prevailing number of COVID-19 infections affected people's mask-wearing behavior. Higher tendencies towards no protection were found in the evenings, during holidays, and in city centers.

Artificial Intelligence for Diabetic Retinopathy Screening Using Color Retinal Photographs: From Development to Deployment.

Diabetic retinopathy (DR), a leading cause of preventable blindness, is expected to remain a growing health burden worldwide. Screening to detect early sight-threatening lesions of DR can reduce the burden of vision loss; nevertheless, the process requires intensive manual labor and extensive resources to accommodate the increasing number of patients with diabetes. Artificial intelligence (AI) has been shown to be an effective tool which can potentially lower the burden of screening DR and vision loss. In this article, we review the use of AI for DR screening on color retinal photographs in different phases of application, ranging from development to deployment. Early studies of machine learning (ML)-based algorithms using feature extraction to detect DR achieved a high sensitivity but relatively lower specificity. Robust sensitivity and specificity were achieved with the application of deep learning (DL), although ML is still used in some tasks. Public datasets were utilized in retrospective validations of the developmental phases in most algorithms, which require a large number of photographs. Large prospective clinical validation studies led to the approval of DL for autonomous screening of DR although the semi-autonomous approach may be preferable in some real-world settings. There have been few reports on real-world implementations of DL for DR screening. It is possible that AI may improve some real-world indicators for eye care in DR, such as increased screening uptake and referral adherence, but this has not been proven. The challenges in deployment may include workflow issues, such as mydriasis to lower ungradable cases; technical issues, such as integration into electronic health record systems and integration into existing camera systems; ethical issues, such as data privacy and security; acceptance of personnel and patients; and health-economic issues, such as the need to conduct health economic evaluations of using AI in the context of the country. The deployment of AI for DR screening should follow the governance model for AI in healthcare which outlines four main components: fairness, transparency, trustworthiness, and accountability.

Polypoidal Choroidal Vasculopathy: Updates on Risk Factors, Diagnosis, and Treatments.

There have been recent advances in basic research and clinical studies in polypoidal choroidal vasculopathy (PCV). A recent, large-scale, population-based study found systemic factors, such as male gender and smoking, were associated with PCV, and a recent systematic review reported plasma C-reactive protein, a systemic biomarker, was associated with PCV. Growing evidence points to an association between pachydrusen, recently proposed extracellular deposits associated with the thick choroid, and the risk of development of PCV. Many recent studies on diagnosis of PCV have focused on applying criteria from noninvasive multimodal retinal imaging without requirement of indocyanine green angiography. There have been attempts to develop deep learning models, a recent subset of artificial intelligence, for detecting PCV from different types of retinal imaging modality. Some of these deep learning models were found to have high performance when they were trained and tested on color retinal images with corresponding images from optical coherence tomography. The treatment of PCV is either a combination therapy using verteporfin photodynamic therapy and anti-vascular endothelial growth factor (VEGF), or anti-VEGF monotherapy, often used with a treat-and-extend regimen. New anti-VEGF agents may provide more durable treatment with similar efficacy, compared with existing anti-VEGF agents. It is not known if they can induce greater closure of polypoidal lesions, in which case, combination therapy may still be a mainstay. Recent evidence supports long-term follow-up of patients with PCV after treatment for early detection of recurrence, particularly in patients with incomplete closure of polypoidal lesions.