Diabetic Retinopathy Screening Model Research Articles

Diabetic retinopathy screening guidelines for Physicians in India: position statement by the Research Society for the Study of Diabetes in India (RSSDI) and the Vitreoretinal Society of India (VRSI)-2023

Diabetic retinopathy (DR) is a leading cause of blindness among working-age adults worldwide. India is the diabetes capital of the world and one in five adults is said to have diabetes in India. With the increase in diabetes, there is an increasing burden of diabetic retinopathy (DR). All patients with diabetes have a risk of losing vision due to DR. The prevalence of diabetic retinopathy is 12.5%; out of which, 4% are said to have vision-threatening diabetic retinopathy (VTDR) The early stages of DR are symptomless, necessitating a proactive screening for an early detection of DR in all people with diabetes before they develop VTDR. This is a position statement jointly developed by RSSDI (Research Society for the Study of Diabetes in India) and VRSI (Vitreo Retinal Society of India) to provide guidelines for Physicians on DR screening in India. These guidelines emphasize the need for regular DR screening of all people with diabetes. It is recommended that the Physicians establish an effective DR screening model in their clinics, eg., a non-mydriatic fundus camera utilizing artificial intelligence (AI) algorithms for fundus photography to identify referral or non-referral DR. This will facilitate early detection and timely referral to an ophthalmologist thereby preventing VTDR. The need to create public awareness regarding blindness due to DR and a collaboration between Physicians and ophthalmologists for the management of diabetes, opportunistic screening of DR, and timely management of DR may play a crucial role in decreasing the burden of blindness secondary to diabetes.

Development of a diabetic retinopathy screening model for a district health system in Limpopo Province, South Africa

Background: Diabetes mellitus (DM) and diabetic retinopathy (DR) are important issues in the district health system (DHS) of South Africa (SA). Guidelines for the management of DR in SA were developed more than a decade ago but not effectively implemented.Aim: The aim of this study was to develop a suitable model for DR that could be effectively implemented by a team of healthcare practitioners (HCPs) to co-manage DM and DR in the DHS of SA.Setting: The study was conducted through Voortrekker District Hospital, Limpopo Province, SA.Methods: A saturated strategy sample study was employed, and questionnaires were distributed to 24 endocrinologists in both private and public practices in Gauteng Province and to three ophthalmologists and 10 medical officers (MOs) in ophthalmology in health institutions in Waterberg and Capricorn districts of Limpopo Province. The questionnaires distributed included questions relating to the recommended roles of primary healthcare (PHC) nurses, MOs in general practice, MOs in ophthalmology, ophthalmic nurses, optometrists, and ophthalmologists to manage patients with DM in the public sector. The Delphi technique was employed requiring experts to comment qualitatively and quantitatively to elicit the required information.Results: At PHC level, PHC nurses are to document a comprehensive patient case history and assess vitals before referring to MOs in general practice. Medical officers in general practice are to assess DM control and screen for target organ disease. All patients with DM are to be referred to optometrists for retinal photography. Optometrists and ophthalmic nurses are to detect, grade and monitor pre-proliferative stages of DR, and refer to MOs in ophthalmology or ophthalmologists at district or tertiary hospitals for surgical intervention or treatment.Conclusion: Based on the expertise of the endocrinologists and ophthalmologists concerned, a DR screening model for a DHS was proposed, reflecting the role of HCPs in the management of DM and DR in the DHS of Limpopo Province, SA.

Development of a diabetic retinopathy screening model for a district health system in Limpopo Province, South Africa

Background: Diabetes mellitus (DM) and diabetic retinopathy (DR) are important issues in the district health system (DHS) of South Africa (SA). Guidelines for the management of DR in SA were developed more than a decade ago but not effectively implemented. Aim: The aim of this study was to develop a suitable model for DR that could be effectively implemented by a team of healthcare practitioners (HCPs) to co-manage DM and DR in the DHS of SA. Setting: The study was conducted through Voortrekker District Hospital, Limpopo Province, SA. Methods: A saturated strategy sample study was employed, and questionnaires were distributed to 24 endocrinologists in both private and public practices in Gauteng Province and to three ophthalmologists and 10 medical officers (MOs) in ophthalmology in health institutions in Waterberg and Capricorn districts of Limpopo Province. The questionnaires distributed included questions relating to the recommended roles of primary healthcare (PHC) nurses, MOs in general practice, MOs in ophthalmology, ophthalmic nurses, optometrists, and ophthalmologists to manage patients with DM in the public sector. The Delphi technique was employed requiring experts to comment qualitatively and quantitatively to elicit the required information. Results: At PHC level, PHC nurses are to document a comprehensive patient case history and assess vitals before referring to MOs in general practice. Medical officers in general practice are to assess DM control and screen for target organ disease. All patients with DM are to be referred to optometrists for retinal photography. Optometrists and ophthalmic nurses are to detect, grade and monitor pre-proliferative stages of DR, and refer to MOs in ophthalmology or ophthalmologists at district or tertiary hospitals for surgical intervention or treatment. Conclusion: Based on the expertise of the endocrinologists and ophthalmologists concerned, a DR screening model for a DHS was proposed, reflecting the role of HCPs in the management of DM and DR in the DHS of Limpopo Province, SA.

In-Person Verification of Deep Learning Algorithm for Diabetic Retinopathy Screening Using Different Techniques Across Fundus Image Devices.

PurposeTo evaluate the clinical performance of an automated diabetic retinopathy (DR) screening model to detect referable cases at Siriraj Hospital, Bangkok, Thailand.MethodsA retrospective review of two sets of fundus photographs (Eidon and Nidek) was undertaken. The images were classified by DR staging prior to the development of a DR screening model. In a prospective cross-sectional enrollment of patients with diabetes, automated detection of referable DR was compared with the results of the gold standard, a dilated fundus examination.ResultsThe study analyzed 2533 Nidek fundus images and 1989 Eidon images. The sensitivities calculated for the Nidek and Eidon images were 0.93 and 0.88 and the specificities were 0.91 and 0.85, respectively. In a clinical verification phase using 982 Nidek and 674 Eidon photographs, the calculated sensitivities and specificities were 0.86 and 0.92 for Nidek along with 0.92 and 0.84 for Eidon, respectively. The 60°-field images from the Eidon yielded a more desirable performance in differentiating referable DR than did the corresponding images from the Nidek.ConclusionsA conventional fundus examination requires intense healthcare resources. It is time consuming and possibly leads to unavoidable human errors. The deep learning algorithm for the detection of referable DR exhibited a favorable performance and is a promising alternative for DR screening. However, variations in the color and pixels of photographs can cause differences in sensitivity and specificity. The image angle and poor quality of fundus photographs were the main limitations of the automated method.Translational RelevanceThe deep learning algorithm, developed from basic research of image processing, was applied to detect referable DR in a real-word clinical care setting.

Training of nonophthalmologists in diabetic retinopathy screening.

The burden of diabetes mellitus (DM) and diabetic retinopathy (DR) is at alarming proportions in India and around the globe. The number of people with DM in India is estimated to increase to over 134 million by 2045. Screening and early identification of sight-threatening DR are proven ways of reducing DR-related blindness. An ideal DR screening model should include personalized awareness, targeted screening, integrated follow-up reminders, and capacity building. The DR screening technology is slowly shifting from direct examination by an ophthalmologist to remote screening using retinal photographs, including telescreening and automated grading of retinal images using artificial intelligence. The ophthalmologist-to-patient ratio is poor in India, and there is an urban–rural divide. The possibility of screening all people with diabetes by ophthalmologists alone is a remote possibility. It is prudent to use the available nonophthalmologist workforce for DR screening in tandem with the technological advances. Capacity-building efforts are based on the principle of task sharing, which allows for the training of a variety of nonophthalmologists in DR screening techniques and technology. The nonophthalmologist human resources for health include physicians, optometrists, allied ophthalmic personnel, nurses, and pharmacists, among others. A concurrent augmentation of health infrastructure, conducive health policy, improved advocacy, and increased people's participation are necessary requirements for successful DR screening. This perspective looks at the characteristics of various nonophthalmologist DR screening models and their applicability in addressing DR-related blindness in India.

Real-world\ufeff artificial intelligence-based opportunistic screening for diabetic retinopathy in endocrinology and indigenous healthcare settings in Australia

This study investigated the diagnostic performance, feasibility, and end-user experiences of an artificial intelligence (AI)-assisted diabetic retinopathy (DR) screening model in real-world Australian healthcare settings. The study consisted of two components: (1) DR screening of patients using an AI-assisted system and (2) in-depth interviews with health professionals involved in implementing screening. Participants with type 1 or type 2 diabetes mellitus attending two endocrinology outpatient and three Aboriginal Medical Services clinics between March 2018 and May 2019 were invited to a prospective observational study. A single 45-degree (macula centred), non-stereoscopic, colour retinal image was taken of each eye from participants and were instantly screened for referable DR using a custom offline automated AI system. A total of 236 participants, including 174 from endocrinology and 62 from Aboriginal Medical Services clinics, provided informed consent and 203 (86.0%) were included in the analysis. A total of 33 consenting participants (14%) were excluded from the primary analysis due to ungradable or missing images from small pupils (n = 21, 63.6%), cataract (n = 7, 21.2%), poor fixation (n = 2, 6.1%), technical issues (n = 2, 6.1%), and corneal scarring (n = 1, 3%). The area under the curve, sensitivity, and specificity of the AI system for referable DR were 0.92, 96.9% and 87.7%, respectively. There were 51 disagreements between the reference standard and index test diagnoses, including 29 which were manually graded as ungradable, 21 false positives, and one false negative. A total of 28 participants (11.9%) were referred for follow-up based on new ocular findings, among whom, 15 (53.6%) were able to be contacted and 9 (60%) adhered to referral. Of 207 participants who completed a satisfaction questionnaire, 93.7% specified they were either satisfied or extremely satisfied, and 93.2% specified they would be likely or extremely likely to use this service again. Clinical staff involved in screening most frequently noted that the AI system was easy to use, and the real-time diagnostic report was useful. Our study indicates that AI-assisted DR screening model is accurate and well-accepted by patients and clinicians in endocrinology and indigenous healthcare settings. Future deployments of AI-assisted screening models would require consideration of downstream referral pathways.

Implementation and evaluation of a team approach to managing diabetes mellitus and diabetic retinopathy in the South African district health system

Background: Diabetic retinopathy (DR) screening programmes have been developed and implemented in different countries based on availability of resources. Most protocols developed for DR have been solely dedicated to DR screening without involving systemic screening.Aim: To implement and evaluate a DR screening model utilising a team of healthcare practitioners (HCPs) to manage diabetes mellitus (DM) to reduce DR progression.Setting: Primary healthcare clinics and Voortrekker hospital in Waterberg district of Limpopo province.Methods: A cross-sectional study was conducted, in which a total of 107 patients with DM from seven clinics consented to participation. A proposed DR screening model was implemented where patients with DM were screened for systemic complications at clinics and referred to Voortrekker district hospital for retinal photography. Questionnaire responses evaluated the success of the screening process and operational challenges.Results: From the study population, 32 (29.1%) were male and 75 (70.1%) were female. The mean age of patients was 63.7 years with a mean weight of 80.69 kg. The mean duration of DM was 9.26 years and the mean haemoglobin A1c (HbA1c) level was 9.7%. From the 47 patients who had visual acuity less than 6/9, 74.5% had refractive error. About 10% (9.4%) had DR or diabetic macular oedema (DME) and 38.3% had other lesions. Referral to an ophthalmologist was necessary in 36.5% of cases.Conclusion: The implementation of a team approach to co-manage DM and DR utilising the developed protocol improved the quality of care for patients with DM in the district health system.

Competency level assessment of healthcare practitioners in managing diabetes and diabetic eye disease in the district health system of Limpopo province, South Africa

Background: There are many gaps in the management of diabetes mellitus (DM) and diabetic eye disease in the district health system (DHS) of South Africa (SA). National guidelines recommend annual eye examinations for patients with DM.Aim: The purpose of this study was to describe the self-reported skill levels of healthcare practitioners (HCPs) to conduct eye examination procedures required for a proposed diabetic retinopathy (DR) screening model.Setting: The study was conducted in public health institutions of Waterberg district and Mankweng Hospital complex (Capricorn district) in Limpopo province, SA.Methods: A cross-sectional design using purposive sampling was conducted, and questionnaires were distributed to a total of 74 HCPs. The questionnaires distributed included questions relating to the competency levels of primary healthcare nurses (PHC nurses), optometrists, ophthalmic nurses and medical officers (MOs) regarding examination procedures in the management of patients with DM and whether they agreed with the developed DR screening model.Results: All the PHC nurses had knowledge about all the examination procedures required in the proposed DR screening model, whilst 94.1% of MOs exhibited knowledge regarding the procedures required from them. Optometrists lacked knowledge of grading DR, and ophthalmic nurses were least knowledgeable about conducting internal and external eye examinations and in detecting and grading DR.Conclusion: The proposed DR screening model did not need modification. The involvement of dieticians and more ophthalmic nurses could be beneficial to the DR screening model.

Implementation and evaluation of a team approach to managing diabetes mellitus and diabetic retinopathy in the South African district health system

Background: Diabetic retinopathy (DR) screening programmes have been developed and implemented in different countries based on availability of resources. Most protocols developed for DR have been solely dedicated to DR screening without involving systemic screening. Aim: To implement and evaluate a DR screening model utilising a team of healthcare practitioners (HCPs) to manage diabetes mellitus (DM) to reduce DR progression. Setting: Primary healthcare clinics and Voortrekker hospital in Waterberg district of Limpopo province. Methods: A cross-sectional study was conducted, in which a total of 107 patients with DM from seven clinics consented to participation. A proposed DR screening model was implemented where patients with DM were screened for systemic complications at clinics and referred to Voortrekker district hospital for retinal photography. Questionnaire responses evaluated the success of the screening process and operational challenges. Results: From the study population, 32 (29.1%) were male and 75 (70.1%) were female. The mean age of patients was 63.7 years with a mean weight of 80.69 kg. The mean duration of DM was 9.26 years and the mean haemoglobin A1c (HbA1c) level was 9.7%. From the 47 patients who had visual acuity less than 6/9, 74.5% had refractive error. About 10% (9.4%) had DR or diabetic macular oedema (DME) and 38.3% had other lesions. Referral to an ophthalmologist was necessary in 36.5% of cases. Conclusion: The implementation of a team approach to co-manage DM and DR utilising the developed protocol improved the quality of care for patients with DM in the district health system.

A personalised screening strategy for diabetic retinopathy: a cost-effectiveness perspective

Aims/hypothesisIn this study we examined the cost-effectiveness of three different screening strategies for diabetic retinopathy: using a personalised adaptive model, annual screening (fixed intervals), and the current Dutch guideline (stratified based on previous retinopathy grade).MethodsFor each individual, optimal diabetic retinopathy screening intervals were determined, using a validated risk prediction model. Observational data (1998–2017) from the Hoorn Diabetes Care System cohort of people with type 2 diabetes were used (n = 5514). The missing values of retinopathy grades were imputed using two scenarios of slow and fast sight-threatening retinopathy (STR) progression. By comparing the model-based screening intervals to observed time to develop STR, the number of delayed STR diagnoses was determined. Costs were calculated using the healthcare perspective and the societal perspective. Finally, outcomes and costs were compared for the different screening strategies.ResultsFor the fast STR progression scenario, personalised screening resulted in 11.6% more delayed STR diagnoses and €11.4 less costs per patient compared to annual screening from a healthcare perspective. The personalised screening model performed better in terms of timely diagnosis of STR (8.8% less delayed STR diagnosis) but it was slightly more expensive (€1.8 per patient from a healthcare perspective) than the Dutch guideline strategy.Conclusions/interpretationThe personalised diabetic retinopathy screening model is more cost-effective than the Dutch guideline screening strategy. Although the personalised screening strategy was less effective, in terms of timely diagnosis of STR patients, than annual screening, the number of delayed STR diagnoses is low and the cost saving is considerable. With around one million people with type 2 diabetes in the Netherlands, implementing this personalised model could save €11.4 million per year compared with annual screening, at the cost of 658 delayed STR diagnoses with a maximum delayed time to diagnosis of 48 months.Graphical abstract

Telemedicine for Diabetic Retinopathy Screening in Croatia

Diabetic retinopathy (DR) is the leading cause of preventable blindness in working-age adults associated with devastating personal and socioeconomic consequences. The increasing use of anti-vascular endothelial growth factor (anti-VEGF) agents over the past decade and telemedicine implementation in systematic DR screening resulted in a decliningtrend of new blindness due to diabetes in several countries. Telemedicine is the remote delivery of healthcare services over the telecommunications infrastructure. It allows healthcare providers to evaluate, diagnose, and treat patients without the need for an in-person visit. Teleophthalmology is a telemedicine branch, mostly focused on diabetic retinopathy and retinopathy of prematurity. Screening for DR in Croatia is commonly performed annually, only by ophthalmologists using dilated slit-lamp biomicroscopic fundus examination. Due to the insufficient number of ophthalmologists and the lack of a formal call system, many diabetic patients do not perform annual screening. In an ideal DR screening model in Croatia, each diabetes center in university or general hospitals throughout Croatia (17 centers) would have one small digital fundus camera and an educated nurse who would perform dilated fundus photography. Electronic images from diabetes centers would be transferred for remote grading to the same hospitals’ ophthalmology departments or a central grading center for DR screening in Croatia. Grading for DR would be performed by an ophthalmologist, medical retina specialist. Patients would be annually invited by mail from the National Diabetes Registry to come to the nearest diabetes center for a fundus photographing and DR screening. Each patient with a positive result would be promptly referred to the medical retina specialist at the closest ophthalmology department for further examination and treatment.

Screening model for diabetic retinopathy among patients with type 1 diabetes attending a tertiary care setting in India.

Diabetic retinopathy (DR) is a common microvascular complication in young individuals with type 1 diabetes. It is recommended to implement structured screening programs and adopt an appropriate referral mechanism at all levels of the health system to prevent vision loss in this disease. We developed and pilot-tested the feasibility of a comprehensive DR screening model at a tertiary care diabetes clinic in India. The model comprised an affordable DR screening facility at the diabetes clinic, structured education sessions, and annual inhospital diabetes complication screening camps. Over the span of 2 years, we screened 413 eligible patients with type 1 diabetes and 17.4% (n = 72) had any form of DR in at least one eye. Half of the retinopathy positive patients had mild DR. However, only one-third of newly diagnosed patients reported to the eye care facility for DR management. Based on this study, it is feasible to screen all patients with type 1 diabetes for DR by increasing awareness and providing opportunities for DR screening at a tertiary care diabetes clinic. Our model combined with formal referral and follow-up systems would be a potentially scalable approach for DR prevention and management at diabetes care facilities in India.

PDB34 A PERSONALIZED SCREENING STRATEGY FOR DIABETIC RETINOPATHY: A COST-EFFECTIVENESS PERSPECTIVE

Objectives: Diabetic retinopathy (DR) is one of the leading causes of visual impairment and blindness. However, only a minority of the type 2 diabetes population is at risk of sight-threatening retinopathy (STR). Most current DR screening programs recommend that these patients should be screened annually or biennially. Recently, a prediction model for DR was developed. Combined with the appropriately chosen STR risk margin this resulted in personalized screening intervals. We examined the cost-effectiveness of using this personalized model compared with annual screening and the most recent Dutch guideline algorithm. Methods: DR screening intervals were determined for STR risk margins ranging from 0.0% to 4.0%, for each individual. Observational data (1998-2017) of the Diabetes Care System, a cohort of people with type 2 diabetes, were used (N=5,514). Missed cases were determined by comparing model based screening to observed grades of DR, then, costs were calculated based on screening and travel costs. Real time to develop STR was missing for 22 percent of STR cases, for these an optimistic and a pessimistic scenario were assumed. Finally, savings per missed case were determined, as compared with annual screening for finding the best risk margin and then this model was compared with the Dutch guideline algorithm. Results: The risk margins that maximized the savings per missed case compared to annual screening were 2.7% (€12,500) and 3.0% (€15,900) for the pessimistic and optimistic scenarios, respectively. Screening patients according to the Dutch guideline led to more missed cases (N=10) as well as higher costs compared to personalized screening (C=€2.1 per patient). Conclusions: A personalized DR screening model with a risk margin of around 3.0% is cheaper and more effective than the Dutch guideline. Assuming 800,000 diabetes patients in the Netherlands, implementing this personalized model could save 8.3 to 8.8 million euros annually.

Cost-effectiveness of a National Telemedicine Diabetic Retinopathy Screening Program in Singapore

To determine the incremental cost-effectiveness of a new telemedicine technician-based assessment relative to an existing model of family physician (FP)-based assessment of diabetic retinopathy (DR) in Singapore from the health system and societal perspectives. Model-based, cost-effectiveness analysis of the Singapore Integrated Diabetic Retinopathy Program (SiDRP). A hypothetical cohort of patients aged 55 years with type 2 diabetes previously not screened for DR. The SiDRP is a new telemedicine-based DR screening program using trained technicians to assess retinal photographs. We compared the cost-effectiveness of SiDRP with the existing model in which FPs assess photographs. We developed a hybrid decision tree/Markov model to simulate the costs, effectiveness, and incremental cost-effectiveness ratio (ICER) of SiDRP relative to FP-based DR screening over a lifetime horizon. We estimated the costs from the health system and societal perspectives. Effectiveness was measured in terms of quality-adjusted life-years (QALYs). Result robustness was calculated using deterministic and probabilistic sensitivity analyses. The ICER. From the societal perspective that takes into account all costs and effects, the telemedicine-based DR screening model had significantly lower costs (total cost savings of S$173 per person) while generating similar QALYs compared with the physician-based model (i.e., 13.1 QALYs). From the health system perspective that includes only direct medical costs, the cost savings are S$144 per person. By extrapolating these data to approximately 170 000 patients with diabetes currently being screened yearly for DR in Singapore's primary care polyclinics, the present value of future cost savings associated with the telemedicine-based model is estimated to be S$29.4 million over a lifetime horizon. While generating similar health outcomes, the telemedicine-based DR screening using technicians in the primary care setting saves costs for Singapore compared with the FP model. Our data provide a strong economic rationale to expand the telemedicine-based DR screening program in Singapore and elsewhere.

Analysis of a comprehensive diabetic retinopathy screening model for rural and urban diabetics in developing countries

Aim:To present an analysis of a screening model for diabetic retinopathy and compare the results of screening between rural and urban populations.Methods:Between June 2003 and September 2004, 51 diabetic retinopathy...

Diabetic retinopathy screening model for rural population: awareness and screening methodology

Worldwide, the prevalence of diabetic retinopathy is increasing at an alarming rate. WHO has predicted that in India the number of adults with diabetes will be the highest in the world: from 19 million in 1995 to 80 million in 2030. Although originally thought to be a disease of an urban population, the prevalence of diabetes mellitus is increasing in rural areas as well. The socioeconomic burden resulting from visual impairment or blindness caused by diabetic retinopathy, particularly in the working age group, is a serious concern. In order to combat diabetic retinopathy related blindness, Sankara Nethralaya, the premier eye institute of India, in collaboration with the Lions Clubs International Foundation (LCIF) and the RD Tata Trust, Mumbai, India launched a major diabetic retinopathy screening program in the rural community of South India. The objectives were to create awareness among the rural population of diabetic retinopathy with emphasis on early detection, to conduct diabetes and diabetic retinopathy screening camps, and to bring to the base hospital patients who have sight-threatening diabetic retinopathy, for ancillary investigations such as fluorescein angiography, ultrasound and to perform laser photocoagulation or vitreous surgery, or both. Other objectives included training general ophthalmologists and general physicians in order to develop an integrated diabetic retinopathy model. To address the question as to why certain individuals run the risk of developing sight threatening diabetic retinopathy, biochemical and genetic factors were also studied. The program was launched in June 2003 and 3 rural districts have been screened. To the time of writing, 128 screening camps had been organized, 103 awareness meetings conducted, 23 ophthalmologists trained and 43 general physicians attended the continuing medical education program on diabetic retinopathy. The key elements in the successful implementation of this program have been a team approach, involvement of community leaders and voluntary organizations, and support of the district and state administrators.