Explore the vast range of titles available.

To assess the performance of deep learning algorithms for different tasks in retinal fundus images: (1) detection of retinal fundus images versus optical coherence tomography (OCT) or other images, (2) evaluation of good quality retinal fundus images, (3) distinction between right eye (OD) and left eye (OS) retinal fundus images,(4) detection of age-related macular degeneration (AMD) and (5) detection of referable glaucomatous optic neuropathy (GON). Five algorithms were designed. Retrospective study from a database of 306,302 images, Optretina's tagged dataset. Three different ophthalmologists, all retinal specialists, classified all images. The dataset was split per patient in a training (80%) and testing (20%) splits. Three different CNN architectures were employed, two of which were custom designed to minimize the number of parameters with minimal impact on its accuracy. Main outcome measure was area under the curve (AUC) with accuracy, sensitivity and specificity. Determination of retinal fundus image had AUC of 0.979 with an accuracy of 96% (sensitivity 97.7%, specificity 92.4%). Determination of good quality retinal fundus image had AUC of 0.947, accuracy 91.8% (sensitivity 96.9%, specificity 81.8%). Algorithm for OD/OS had AUC 0.989, accuracy 97.4%. AMD had AUC of 0.936, accuracy 86.3% (sensitivity 90.2% specificity 82.5%), GON had AUC of 0.863, accuracy 80.2% (sensitivity 76.8%, specificity 83.8%). Deep learning algorithms can differentiate a retinal fundus image from other images. Algorithms can evaluate the quality of an image, discriminate between right or left eye and detect the presence of AMD and GON with a high level of accuracy, sensitivity and specificity.

Diabetic Retinopathy is a microvascular complication of diabetes, that can go undetected and unnoticed until irreversible damage and even blindness has occurred. Effective screening for diabetic retinopathy has been proven to reduce the risk of sight loss. The National Health Service (NHS) which provides healthcare for all UK citizens, implemented systematic retinal screening for diabetic retinopathy in England in 2003, with the aim of identifying and treating all patients with sight threatening retinopathy. Crucial to this is patients partaking in the programme. Therefore, increasing screening uptake has been a major focus of the programme. This review explores the views of people living with diabetes who do not attend retinal screening, their characteristics, concerns, experiences of retinal screening and their understanding of the risks of diabetic retinopathy. All studies that satisfied the study inclusion criteria on ‘patients’ non-attendance at retinal screening’, between 2003 to 2017 were included after extensive database search. A total of 16 studies were included in the review. Findings showed that socio-economic deprivation was a major risk factor for non-attendance, about 11.5–13.4% of the screened population had sight threatening retinopathy (STDR), repeated nonattendance was linked to sight threatening diabetic retinopathy, and that certain factors, could be barriers or incentives for screening uptake. Some of those factors are modifiable whilst others are not.

Proof-of-concept study to test the feasibility of using an all-in-one portable retinal camera for the screening of diabetic retinopathy in the Pacific Island of Vanuatu, which has a high rate of diabetes and its associated complications and a dearth of ophthalmologists. From February 10, 2020, through February 28, 2020, 49 patients with diabetes mellitus from three islands in Vanuatu were recruited to participate in the study. Demographics, basic health data and retinal photography were obtained. A non-mydriatic, handheld camera was used (Volk Pictor Plus). Eleven participants (24%) had referral-warranted diabetic retinopathy. There was moderately high inter-rater reliability for our dependent variables: referral status (κ = 0.62, 95% CI 0.42-0.83), retinopathy severity (κ = 0.76, 95% CI 0.55-0.96), and clinically significant macular edema (κ = 0.50, 95% CI 0.25-0.74). Our study confirms that portable handheld cameras can be used to obtain retinal images of sufficient quality for diabetic retinopathy screening even in resource limited environments like Vanuatu. Among this cohort, a relatively high (24%) prevalence of referral-warranted diabetic retinopathy was found in Vanuatu.

Aims/hypothesisThe aims of this study were to identify all published prognostic models predicting retinopathy risk applicable to people with type 2 diabetes, to assess their quality and accuracy, and to validate their predictive accuracy in a head-to-head comparison using an independent type 2 diabetes cohort.MethodsA systematic search was performed in PubMed and Embase in December 2019. Studies that met the following criteria were included: (1) the model was applicable in type 2 diabetes; (2) the outcome was retinopathy; and (3) follow-up was more than 1 year. Screening, data extraction (using the checklist for critical appraisal and data extraction for systemic reviews of prediction modelling studies [CHARMS]) and risk of bias assessment (by prediction model risk of bias assessment tool [PROBAST]) were performed independently by two reviewers. Selected models were externally validated in the large Hoorn Diabetes Care System (DCS) cohort in the Netherlands. Retinopathy risk was calculated using baseline data and compared with retinopathy incidence over 5 years. Calibration after intercept adjustment and discrimination (Harrell’s C statistic) were assessed.ResultsTwelve studies were included in the systematic review, reporting on 16 models. Outcomes ranged from referable retinopathy to blindness. Discrimination was reported in seven studies with C statistics ranging from 0.55 (95% CI 0.54, 0.56) to 0.84 (95% CI 0.78, 0.88). Five studies reported on calibration. Eight models could be compared head-to-head in the DCS cohort (N = 10,715). Most of the models underestimated retinopathy risk. Validating the models against different severities of retinopathy, C statistics ranged from 0.51 (95% CI 0.49, 0.53) to 0.89 (95% CI 0.88, 0.91).Conclusions/interpretationSeveral prognostic models can accurately predict retinopathy risk in a population-based type 2 diabetes cohort. Most of the models include easy-to-measure predictors enhancing their applicability. Tailoring retinopathy screening frequency based on accurate risk predictions may increase the efficiency and cost-effectiveness of diabetic retinopathy care.RegistrationPROSPERO registration ID CRD42018089122

Purpose of Review The purpose of this study is to review the evidence that lower risk groups who could safely be screened less frequently for sight-threatening diabetic retinopathy (DR) than annually. Recent Findings Data have demonstrated that people with no DR in either eye are at a low risk of progression to sight-threatening DR over a 2-year period (event rate 4.8 per 1000 person years), irrespective of whether the screening method is one-field non-mydriatic or two-field mydriatic digital photography. Low risk has been defined as no retinopathy on two consecutive screening episodes or no retinopathy on one screening episode combined with risk factor data. Summary The risk of an extension to 2 years is less than 5 per 1000 person years in a population with a national screening programme, and the general standard of diabetes care is relatively good, whether low risk is defined as no retinopathy on two consecutive screening episodes or no retinopathy on one screening episode combined with other risk factor data. The definition used in different populations is likely to depend on the availability of data.

Diabetic retinopathy (DR) is a chronic complication of diabetes in which the retinal damage may cause vision impairment or blindness if left untreated. The challenges in DR detection are mostly due to the morphological variations of retinal lesions, e.g., microaneurysms, hemorrhages, and exudates, and the imaging condition variability between different clinical environments. Current state of the art deep learning models like convolutional neural network (CNN), recurrent neural network (RNN) and transformer-based architectures are computationally expensive, not robust to noisy datasets and have limitation on interpretability, which makes them difficult to deploy in real world clinical settings. This research offers HyperGraph Capsule Temporal Network (HGCTN), a deep learning framework to address these limitations and to create an accurate, scalable, and interpretable DR detection. Combining hypergraph neural networks for strong modeling of higher order spatial relationships between retinal lesions, capsule networks for permitting hierarchical structuring of feature and memorizing distributed routing place into temporal capsular memory unit (TCMU) for maintaining both long term and short termed temporal dependencies we propose HGCTN, a model that integrates all the methodologies to efficaciously track disease progression. Meta learning techniques and noise injection strategies are used to improve adaptability of the model and thus make the model more resilient to real world image variations. On DRIVE and Diabetic Retinopathy datasets, HGCTN is validated experimentally, and the best accuracy is 99.0% (HDCTN) and 98.8% (ADTATC), while existing models like TAHDL (96.7%) and ADTATC (98.2%) are outperformed. Furthermore, the model has a recall of 100% and 99.8% on DRIVE and the Diabetic Retinopathy dataset, respectively, with a specificity of 99.7% and 99.6%, respectively, and thus has almost no false negatives and a high reliability in identifying DR cases. Hypergraph attention maps and capsule activation images are additionally relied on to validate the model’s interpretability as they offer explainable predictions to a clinical audience. HGCTN has high classification accuracy, reduced computational complexity and better generalization than the existing models, which makes it a new benchmark for DR detection, solving the key deficiency of the existing models and laying the foundation for the real-world deployment of the automated ophthalmic diagnosis systems.

Background ‘Implementation interventions’ refer to methods used to enhance the adoption and implementation of clinical interventions such as diabetic retinopathy screening (DRS). DRS is effective, yet uptake is often suboptimal. Despite most routine management taking place in primary care and the central role of health care professionals (HCP) in referring to DRS, few interventions have been developed for primary care. We aimed to develop a multifaceted intervention targeting both professionals and patients to improve DRS uptake as an example of a systematic development process combining theory, stakeholder involvement, and evidence. Methods First, we identified target behaviours through an audit in primary care of screening attendance. Second, we interviewed patients ( n = 47) and HCP ( n = 30), to identify determinants of uptake using the Theoretical Domains Framework, mapping these to behaviour change techniques (BCTs) to develop intervention content. Thirdly, we conducted semi-structured consensus groups with stakeholders, specifically users of the intervention, i.e. patients ( n = 15) and HCPs ( n = 16), regarding the feasibility, acceptability, and local relevance of selected BCTs and potential delivery modes. We consulted representatives from the national DRS programme to check intervention ‘fit’ with existing processes. We applied the APEASE criteria (affordability, practicability, effectiveness, acceptability, side effects, and equity) to select the final intervention components, drawing on findings from the previous steps, and a rapid evidence review of operationalised BCT effectiveness. Results We identified potentially modifiable target behaviours at the patient (consent, attendance) and professional (registration) level. Patient barriers to consent/attendance included confusion between screening and routine eye checks, and fear of a negative result. Enablers included a recommendation from friends/family or professionals and recognising screening importance. Professional barriers to registration included the time to register patients and a lack of readily available information on uptake in their local area/practice. Most operationalised BCTs were acceptable to patients and HCPs while the response to feasibility varied. After considering APEASE, the core intervention, incorporating a range of BCTs, involved audit/feedback, electronic prompts targeting professionals, HCP-endorsed reminders (face-to-face, by phone and letter), and an information leaflet for patients. Conclusions Using the example of an intervention to improve DRS uptake, this study illustrates an approach to integrate theory with user involvement. This process highlighted tensions between theory-informed and stakeholder suggestions, and the need to apply the Theoretical Domains Framework (TDF)/BCT structure flexibly. The final intervention draws on the trusted professional-patient relationship, leveraging existing services to enhance implementation of the DRS programme. Intervention feasibility in primary care will be evaluated in a randomised cluster pilot trial.

Diabetic retinopathy (DR) is a leading cause of vision loss among working-age adults. However, the prevalence of DR among patients with diabetic foot disease-a signal of advanced systemic diabetes complications-is underexplored. Additionally, the substantial comorbidity burden associated with diabetic foot disease may result in a higher incidence of or distinct barriers to ophthalmic care, including structural (access to healthcare), behavioral (prioritization of care), and economic (cost of care) factors, compounding risk of vision loss. This study assesses the prevalence of DR in a podiatric clinic while also investigating participant-reported barriers to routine ophthalmic follow-up. We conducted a cross-sectional study that included patients age ≥18 (n=62) receiving diabetic foot care at an outpatient podiatric clinic in 2021 and 2022. DR status was determined through point-of-care digital retinal images or prior DR diagnosis documented in the electronic medical record. Retinal images were interpreted remotely by a board-certified ophthalmologist. Self-reported barriers to regular ophthalmic care were recorded among participants who were lost to follow-up ophthalmic care. Participants were also surveyed for favorable incentives to promote ophthalmic follow-up. Our findings revealed a high prevalence of DR, with 32 (54%) participants diagnosed with DR and 10 (17%) participants having sight-threatening DR. Notably, 17 (29%) participants were newly diagnosed with DR as a direct result of this study. Of the 62 participants enrolled, 29 (47%) were lost to ophthalmic care. All of these participations reported one or more barriers to receiving ophthalmic care, predominantly related to competing social, economic, and medical challenges, with ophthalmic care being chronically underprioritized. Financial incentives were most favored by participants as an effective means to promote ophthalmic follow-up. The high prevalence of DR, especially undiagnosed DR, in conjunction with significant barriers to ophthalmic care highlights a critical need for improved screening in outpatient podiatric settings. Integrating digital fundus cameras into outpatient podiatric clinic workflow may enhance DR detection and prevent vision loss in this high-risk population. Addressing identified barriers to routine ophthalmic care may further improve the rate of follow-up care and reduce the burden of DR-related vision loss among patients with diabetic foot disease.

Aims/hypothesis The aim of our study was to identify subgroups of patients attending the Scottish Diabetic Retinopathy Screening (DRS) programme who might safely move from annual to two yearly retinopathy screening. Methods This was a retrospective cohort study of screening data from the DRS programme collected between 2005 and 2011 for people aged ≥12 years with type 1 or type 2 diabetes in Scotland. We used hidden Markov models to calculate the probabilities of transitions to referable diabetic retinopathy (referable background or proliferative retinopathy) or referable maculopathy. Results The study included 155,114 individuals with no referable diabetic retinopathy or maculopathy at their first DRS examination and with one or more further DRS examinations. There were 11,275 incident cases of referable diabetic eye disease (9,204 referable maculopathy, 2,071 referable background or proliferative retinopathy). The observed transitions to referable background or proliferative retinopathy were lower for people with no visible retinopathy vs mild background retinopathy at their prior examination (respectively, 1.2% vs 8.1% for type 1 diabetes and 0.6% vs 5.1% for type 2 diabetes). The lowest probability for transitioning to referable background or proliferative retinopathy was among people with two consecutive screens showing no visible retinopathy, where the probability was <0.3% for type 1 and <0.2% for type 2 diabetes at 2 years. Conclusions/interpretation Transition rates to referable diabetic eye disease were lowest among people with type 2 diabetes and two consecutive screens showing no visible retinopathy. If such people had been offered two yearly screening the DRS service would have needed to screen 40% fewer people in 2009.

Ideally, to carry out screening for eye diseases, it is expected to use specialized medical equipment to capture retinal fundus images. However, since this kind of equipment is generally expensive and has low portability, and with the development of technology and the emergence of smartphones, new portable and cheaper screening options have emerged, one of them being the D-Eye device. When compared to specialized equipment, this equipment and other similar devices associated with a smartphone present lower quality and less field-of-view in the retinal video captured, yet with sufficient quality to perform a medical pre-screening. Individuals can be referred for specialized screening to obtain a medical diagnosis if necessary. Two methods were proposed to extract the relevant regions from these lower-quality videos (the retinal zone). The first one is based on classical image processing approaches such as thresholds and Hough Circle transform. The other performs the extraction of the retinal location by applying a neural network, which is one of the methods reported in the literature with good performance for object detection, the YOLO v4, which was demonstrated to be the preferred method to apply. A mosaicing technique was implemented from the relevant retina regions to obtain a more informative single image with a higher field of view. It was divided into two stages: the GLAMpoints neural network was applied to extract relevant points in the first stage. Some homography transformations are carried out to have in the same referential the overlap of common regions of the images. In the second stage, a smoothing process was performed in the transition between images.