Imaging Modalities Employed in Diabetic Retinopathy Screening: A Review and Meta-Analysis

Barriers and enablers of access to diabetes eye care in Auckland, New Zealand: a qualitative study

OBJECTIVE

To explore the barriers and enablers to accessing diabetes eye care services among adults in Auckland.

DESIGN

This was a qualitative study that used semistructured interviews. We performed a thematic analysis and described the main barriers and enablers to accessing services using the Theoretical Domains Framework.

SETTING

The study took place in two of the three public funding and planning agencies that provide primary and secondary health services in Auckland, the largest city in Aotearoa New Zealand.

PARTICIPANTS

Thirty people with diabetes in Auckland who had experienced interrupted diabetes eye care, having missed at least one appointment or being discharged back to their general practitioner after missing several appointments.

RESULTS

We identified barriers and enablers experienced by our predominantly Pacific and Māori participants that aligned with 7 (of the 14) domains in the Theoretical Domains Framework. The most reported barriers were transport issues, lack of awareness regarding the importance of retinal screening, time constraints, limited and/or inflexible appointment times and competing family commitments. Enablers included positive interactions with healthcare providers and timely appointment notifications and reminders.

CONCLUSIONS

Diabetes eye services could be made more responsive by addressing systemic barriers such as service location and transport links, appointment availability and meaningful information to aid understanding.

Artificial Intelligence (AI)-Enhanced Detection of Diabetic Retinopathy From Fundus Images: The Current Landscape and Future Directions

Diabetic retinopathy (DR) remains a leading cause of vision loss worldwide, with early detection critical for preventing irreversible damage. This review explores the current landscape and future directions of artificial intelligence (AI)-enhanced detection of DR from fundus images. Recent advances in deep learning and computer vision have enabled AI systems to analyze retinal images with expert-level accuracy, potentially transforming DR screening. Key developments include convolutional neural networks achieving high sensitivity and specificity in detecting referable DR, multi-task learning approaches that can simultaneously detect and grade DR severity, and lightweight models enabling deployment on mobile devices. While these AI systems show promise in improving the efficiency and accessibility of DR screening, several challenges remain. These include ensuring generalizability across diverse populations, standardizing image acquisition and quality, addressing the "black box" nature of complex models, and integrating AI seamlessly into clinical workflows. Future directions in the field encompass explainable AI to enhance transparency, federated learning to leverage decentralized datasets, and the integration of AI with electronic health records and other diagnostic modalities. There is also growing potential for AI to contribute to personalized treatment planning and predictive analytics for disease progression. As the technology continues to evolve, maintaining a focus on rigorous clinical validation, ethical considerations, and real-world implementation will be crucial for realizing the full potential of AI-enhanced DR detection in improving global eye health outcomes.

Addressing Technical Failures in a Diabetic Retinopathy Screening Program

Purpose

Diabetic retinopathy (DR) is a preventable cause of blindness detectable through screening using retinal digital photography. The Irish National Diabetic Retina Screening (DRS) programme, Diabetic RetinaScreen, provides free screening services to patients with diabetes from aged 12 years and older. A technical failure (TF) occurs when digital retinal imaging is ungradable, resulting in delays in the diagnosis and treatment of sight-threatening disease. Despite their impact, the causes of TFs, and indeed the utility of interventions to prevent them, have not been extensively examined.

Aim

Primary analysis aimed to identify factors associated with TF. Secondary analysis examined a subset of cases, assessing patient data from five time points between 2019 and 2021 to identify photographer/patient factors associated with TF.

Methods

Patient data from the DRS database for one provider were extracted for analysis between 2018 and 2022. Information on patient demographics, screening results, and other factors previously associated with TF were analyzed. Primary analysis involved using mixed-effects logistic regression models with nested patient-eye random effects. Secondary analysis reviewed a subset of cases in detail, checking for causes of TF.

Results

The primary analysis included a total of 366,528 appointments from 104,407 patients over 5 years. Most patients had Type 2 diabetes (89.2%), and the overall TF rate was 4.9%. Diabetes type and duration, dilate pupil status, and the presence of lens artefacts on the camera were significantly associated with TF. The Secondary analysis identified the primary cause of TF was found to be optically dense cataracts, accounting for over half of the TFs.

Conclusion

This study provides insight into the causes of TF within the Irish DRS program, highlighting cataracts as the primary contributing factor. The identification of patient-level factors associated with TF facilitates appropriate interventions that can be put in place to improve patient outcomes and minimize delays in treatment and diagnosis.

Comparison of three fundus inspection methods during phacoemulsification in diabetic white cataract

AIM

To investigate whether Wild Field Imaging System (WFIS SW-8000), 25G endoilluminator, and intraoperative optical coherence tomography (iOCT) can perform real-time screening and diagnosing in patients with suspicious diabetic retinopathy (DR) during phacoemulsification, especially in cases of white cataract.

METHODS

A cross-sectional study was carried out. A total of 204 dense diabetic cataractous eyes of 204 patients with suspected DR treated from April 2020 to March 2021 were included. Phacoemulsification combined with intraocular lens implantation was performed. Following the removal of the lens opacity, the 25G endo-illuminator, fundus photography, and iOCT were performed successively. Optical coherence tomography (OCT) and/or fundus fluorescein angiography (FFA) were used to verify the fundus findings postoperatively. Intraoperative and postoperative results were compared to verify the accuracy of intraoperative diagnosis in each group.

RESULTS

Intraoperative and postoperative examinations revealed 58 and 62 eyes with DR, respectively (positive rate, 28.43% and 30.39%, respectively). During the phacoemulsification, WFIS SW-8000 detected 44 eyes with DR (the detection rate, 70.97%); 25G endo-illuminator found 56 eyes with DR (the detection rate, 90.32%); iOCT found 46 eyes with DR (the detection rate, 74.19%); and 58 eyes with DR were found by combining the three methods (the detection rate, 93.55%). There were statistically significant differences in the diagnostic sensitivity for DR among the methods (χ2=16.36, P=0.001).

CONCLUSION

WFIS SW-8000, 25G endo-illuminator, iOCT, and especially their combination can be used to inspect the fundus and detect DR intraoperatively; they are helpful for the timely diagnosis and treatment of DR in patients with dense cataract.

Examining the Role of Telemedicine in Diabetic Retinopathy

With the increasing prevalence of diabetic retinopathy (DR), screening is of the utmost importance to prevent vision loss for patients and reduce financial costs for the healthcare system. Unfortunately, it appears that the capacity of optometrists and ophthalmologists to adequately perform in-person screenings of DR will be insufficient within the coming years. Telemedicine offers the opportunity to expand access to screening while reducing the economic and temporal burden associated with current in-person protocols. The present literature review summarizes the latest developments in telemedicine for DR screening, considerations for stakeholders, barriers to implementation, and future directions in this area. As the role of telemedicine in DR screening continues to expand, further work will be necessary to continually optimize practices and improve long-term patient outcomes.

Circulating Biomarkers to Predict Diabetic Retinopathy in Patients with Diabetic Kidney Disease

The purpose of this review is to outline the currently available circulating biomarkers to predict diabetic retinopathy (DR) in patients with diabetic kidney disease (DKD). Studies have extensively reported the association between DR and DKD, suggesting the presence of common pathways of microangiopathy. The presence of other ocular complications including diabetic cataracts may hinder the detection of retinopathy, which may affect the visual outcome after surgery. Unlike DKD screening, the detection of DR requires complex, costly machines and trained technicians. Recognizing potential biological markers related to glycation and oxidative stress, inflammation and endothelial dysfunction, basement membrane thickening, angiogenesis, and thrombosis as well as novel molecular markers involved in the microangiopathy process may be useful as predictors of retinopathy and identify those at risk of DR progression, especially in cases where retinal visualization becomes a clinical challenge. Further investigations could assist in deciding which biomarkers possess the highest predictive power to predict retinopathy in clinical settings.

The Role of Medical Image Modalities and AI in the Early Detection, Diagnosis and Grading of Retinal Diseases: A Survey

Traditional dilated ophthalmoscopy can reveal diseases, such as age-related macular degeneration (AMD), diabetic retinopathy (DR), diabetic macular edema (DME), retinal tear, epiretinal membrane, macular hole, retinal detachment, retinitis pigmentosa, retinal vein occlusion (RVO), and retinal artery occlusion (RAO). Among these diseases, AMD and DR are the major causes of progressive vision loss, while the latter is recognized as a world-wide epidemic. Advances in retinal imaging have improved the diagnosis and management of DR and AMD. In this review article, we focus on the variable imaging modalities for accurate diagnosis, early detection, and staging of both AMD and DR. In addition, the role of artificial intelligence (AI) in providing automated detection, diagnosis, and staging of these diseases will be surveyed. Furthermore, current works are summarized and discussed. Finally, projected future trends are outlined. The work done on this survey indicates the effective role of AI in the early detection, diagnosis, and staging of DR and/or AMD. In the future, more AI solutions will be presented that hold promise for clinical applications.