Diabetic Retinopathy Screening Research Articles

Deep learning detection of diabetic retinopathy in Scotland’s diabetic eye screening programme

Background/AimsSupport vector machine-based automated grading (known as iGradingM) has been shown to be safe, cost-effective and robust in the diabetic retinopathy (DR) screening (DES) programme in Scotland. It triages screening...

Improving diabetic retinopathy screening at the point of care: integrating telemedicine to overcome current challenges

ObjectiveTo investigate the utility of point of care screening of diabetic retinopathy (DR) and the impact of a telemedicine program to overcome current challenges.MethodsThis was a retrospective study on people with type 2 diabetes mellitus (T2DM) who were screened for DR using the single-field non-mydriatic fundus photography at the point of care during routine follow-up visits at endocrinology clinic. Retinal images were uploaded and sent to a retina specialist for review. Reports indicating retinopathy status and the need for direct retinal examination were transmitted back to the endocrinology clinic. All patients were informed about DR status and, if needed, referred to the retina specialist for direct retinal examination.ResultsOf the 1159 individuals screened for DR, 417 persons (35.98%) were screen-positive and referred to the retina specialist for direct retinal examination. A total of 121 individuals (29.01%) underwent direct retinal examination by the specialist. Diabetes macular edema (DME) was detected in 12.1%. In addition, non-proliferative diabetic retinopathy (NPDR) and proliferative diabetic retinopathy (PDR) were detected in 53.4% and 2.6% of the patients, respectively.ConclusionIntegrating DR screening program at the point of care at the secondary care services improves the rate of DR screening as well as detection of sight threatening retinopathy and provides the opportunity for timely intervention in order to prevent advanced retinopathy in people with T2DM.

1810-LB: Diagnostic Accuracy of Automated Pupillometry for Diabetic Retinopathy Screening

1810-LB: Diagnostic Accuracy of Automated Pupillometry for Diabetic Retinopathy Screening

Identification of Risk Factors for the Development of Diabetic Retinopathy Among Palestinian Adults With Type 2 Diabetes Mellitus: A Cross-Sectional Study.

Although risk factors linked to diabetic retinopathy (DR) among patients with Type 2 diabetes mellitus (T2DM) have been extensively studied globally, the specific determinants of these factors in relation to DR in Palestine are presently not well understood. This retrospective cross-sectional study included patients who underwent DR screening with a fundus camera (VersaCam a). The study included patients aged ≥18 with T2DM, excluding those with other types of diabetes or a history of malignancies. Univariable and multivariable logistic regressions were used to identify factors associated with DR. A total of 1163 patients with T2DM were included in this study. Of these, 211 (18.1%) patients were classified in the DR group, 761 (65.4%) in the no DR group and 191 (16.4%) were ungradable. Among the included patients, 434 (37.3%) were male. A secondary level of education or higher and a BMI ≥30 kg/m2, compared with <25 kg/m2, were independently and inversely associated with DR, with odds ratios (ORs) of 0.46 (p < 0.001) and 0.58 (p = 0.046), respectively. A 5-year increase in the duration of T2DM correlated with 45% higher odds of having DR (p < 0.001). Patients with DR were more likely to have HbA1c >7%, be physically inactive and use insulin, with ORs of 1.63 (p = 0.02), 2.05 (p < 0.001) and 1.53 (p = 0.03), respectively. Age, gender, occupational status, hypertension and hyperlipidaemia were not independent predictors of DR (p < 0.05). Longer duration of T2DM, HbA1c >7%, physical inactivity and insulin use were all independently associated with the presence of DR. Furthermore, a secondary or higher educational level and obesity demonstrated independent and inverse associations with the development of DR.

Longitudinal Trends and Disparities in Diabetic Retinopathy Within an Aggregate Health Care Network

Diabetic retinopathy (DR) is a leading cause of blindness in the US, warranting updates on its prevalence and incidence in the setting of advancements in diabetic care over recent years. To determine recent trends in DR prevalence stratified by baseline demographics to identify those populations at greater risk. This was a cross-sectional epidemiologic evaluation conducted using deidentified data from the large federated TriNetX Analytics health research network composed of 56 health care organizations in the US. Patients from 2015 to 2022 who had an International Statistical Classification of Diseases and Related Health Problems, Tenth Revision code of type 1 DR (T1DR) or type 2 DR (T2DR) were included in this analysis. Patients were further stratified by age cohorts (20-29 years, 30-39 years, 40-49 years, 50-59 years, 60-69 years, and 70 years or older), race and ethnicity, and sex. Prevalence per 100 000 patients and prevalence odds ratios (ORs) were calculated in Microsoft Excel and Posit (formerly RStudio). A total of 359 126 patients with T1DR or T2DR (mean [SD] age, 67 [14] years; 52% female) were included in this study between January 1, 2015, and December 21, 2022. T1DR increased in prevalence from 2015 to 2022, with T1DR increasing 1.15-fold affecting 70.4 patients per 100 000 in 2022. T2DR increased 1.07-fold affecting 461.7 patients per 100 000 in 2022. For T1DR, the cohort aged 20 to 39 years had the most substantial increase at 4.7 and 1.96 fold. Overall, White males had the largest prevalence ORs of T1DR at 1.41 (95% CI, 1.36-1.47) compared with White females (reference group). In T2DR, patients aged 20 to 39 years again had a 2.5- and 1.6-fold prevalence increase from 2015 to 2022. Regardless of age group, Hispanic males demonstrated larger prevalence OR at 4.08 (95% CI, 3.97-4.19) compared with White females followed by Hispanic females at 2.49 (95% CI, 2.42-2.56), Black males at 2.23 (95% CI, 2.17-2.29), and Black females at 2.00 (95% CI, 1.95-2.05). The prevalence of both T1DR and T2DR increased in this network from 2015 to 2022, with individuals aged 20 to 39 years showing large increases. Additionally, T2DR was associated with greater increases in both Hispanic and Black communities. These findings support DR screening in young adults and for T2DR interventions specifically designed for racial and ethnic minoritized patients most affected by disease. Future investigations are warranted to further investigate these trends among young adults.

Retinal image quality assessment in diabetic-retinopathy screening: Real world evidence from a lower-middle income country

Objectives: Sight loss due to diabetic retinopathy (DR) is preventable by early detection and treatment. Digital retinal imaging is the most widely practiced method of screening of DR. Poor quality of images is a major hinder to implement systematic DR screening using digital retinal imaging in low- and middle-income countries with a high prevalence of lens opacities. We aimed to identify the proportion of ungradable images using hand-held retinal imaging and predictors of image gradability in a DR screening feasibility study conducted in Sri Lanka. Material and Methods: The present study is a retrospective data analysis of a validation study conducted to assess the diagnostic test accuracy of a held-held digital retinal imaging model integrated into a tertiary level medical clinic. Two selected physician graders underwent formal training to assess retinal image quality using a “four-quadrant method of assessing gradability.” The procedure was a subjective image quality assessment performed by the physician graders manually, that is, images with more than 50% of the field with poor clarity and not suitable for retinopathy grading were classified as ungradable. Two-field (Field-1: macula centered, Field-2: disc centered) non-mydriatic and mydriatic retinal images were captured (Type of camera: Zeiss-Visuscout 100®, Germany) in a consecutive sample of people with diabetes attended for routine medical care and assessed for quality and graded by two independent physician graders on-site. The reference test was a mydriatic biomicroscopic examination conducted at a separate eye clinic by an experienced specialist retinologist. Mixed model regression analysis was conducted to assess the predictors of gradability. Results: A total of 700 individuals (5508 gradability data points) were included in the study. The proportion of ungradable images in non-mydriatic imaging was 30% for Grader 1 and 24% for Grader 2 and went down to 7% and 5%, respectively, for Grader 1 and 2 after dilating the pupils using mydriatic agents. Non-mydriatic images had almost 20 times higher odds (odds ratio [OR] 19.7, 95% confidence interval [CI] 15.1–25.8) of being rated as ungradable compared to mydriatic images. With the increase of each year in age, the odds of having ungradable digital retinal images in a patient increased by 7% (OR 1.07, 95% CI 1.05–1.09). For visual acuity increase in each level of the Log-MAR scale, the odds of having ungradable images increased by 40% (OR 1.40, 95% CI 1.30–1.51). In lens opacity, 54% higher odds of ungradability were observed when present nuclear opalescence (OR 1.54, 95% CI 1.39–1.70) and posterior subcapsular opacity (OR 1.54, 95% CI 1.24–1.92). Conclusion: Non-mydriatic methods may not be suitable as a primary DR screening strategy in countries with a high prevalence of cataracts. Increasing age, poor visual acuity, and the presence of lens opacity are factors that would affect image quality. The capacity to deliver services for managing cataracts may be an important determinant in achieving effective coverage of digital surveillance of DR in low- and middle-income countries.

Sociodemography, diabetes mellitus clinical parameters, and retinal morphology as predictors of neurodegeneration in preclinical diabetic retinopathy

Abstract PURPOSE: The current prediction of preclinical diabetic retinopathy (DR) in asymptomatic patients with diabetes mellitus (DM) is limited due to a lack of suitable indicators. This study aimed to identify the predictors of neurodegenerative changes in type 2 DM patients during the preclinical stage of DR using sociodemographic and DM clinical parameters and retinal morphology. METHODS: Fifty-six adult DM participants (mean age: 40.41 ± 7.281 years) were classified into three groups: DM without DR, DM with mild nonproliferative DR (NPDR), and DM with moderate-to-severe NPDR. Demographic data, including age, gender, race, DM duration, glycated hemoglobin levels, household income, comorbidities, and insulin dependency, were collected. Retinal morphology, including macular retinal layer thickness, peripapillary retinal nerve fiber layer, and vascular caliber, were analyzed. Multinomial logistic regression models explored these factors’ influence on NPDR prediction. RESULTS: Participants with moderate-to-severe NPDR were less likely to have DM without comorbidities (odds ratio [OR]: 0.048, 95% confidence interval [CI]: 0.003–0.823, P = 0.036). Those with longer DM duration were 27% more likely to develop moderate-to-severe NPDR (OR: 1.272, 95% CI: 1.035–1.564, P = 0.022). Retinal morphology parameters did not predict NPDR risk and severity levels in DM patients, except for mild NPDR, which had a 1.05 times higher risk of wider central retinal arteriolar equivalent (CRAE) (OR: 1.052, 95% CI: 1.002–1.105, P = 0.043). CONCLUSION: DM duration, comorbidity presence, and widened CRAE are critical parameters for assessing neurodegenerative changes in preclinical DR. These parameters could be incorporated into DR screening programs to mitigate NPDR progression and enhance long-term visual outcomes of DM patients.

Advances in teleophthalmology and artificial intelligence for diabetic retinopathy screening: a narrative review

Advances in teleophthalmology and artificial intelligence for diabetic retinopathy screening: a narrative review

Development and validation of a simple and practical model for early detection of diabetic macular edema in patients with type 2 diabetes mellitus using easily accessible systemic variables

ObjectiveDiabetic macular edema (DME) is the leading cause of visual impairment in patients with diabetes mellitus (DM). The goal of early detection has not yet achieved due to a lack of fast and convenient methods. Therefore, we aim to develop and validate a prediction model to identify DME in patients with type 2 diabetes mellitus (T2DM) using easily accessible systemic variables, which can be applied to an ophthalmologist-independent scenario.MethodsIn this four-center, observational study, a total of 1994 T2DM patients who underwent routine diabetic retinopathy screening were enrolled, and their information on ophthalmic and systemic conditions was collected. Forward stepwise multivariable logistic regression was performed to identify risk factors of DME. Machine learning and MLR (multivariable logistic regression) were both used to establish prediction models. The prediction models were trained with 1300 patients and prospectively validated with 104 patients from Guangdong Provincial People’s Hospital (GDPH). A total of 175 patients from Zhujiang Hospital (ZJH), 115 patients from the First Affiliated Hospital of Kunming Medical University (FAHKMU), and 100 patients from People’s Hospital of JiangMen (PHJM) were used as external validation sets. Area under the receiver operating characteristic curve (AUC), accuracy (ACC), sensitivity, and specificity were used to evaluate the performance in DME prediction.ResultsThe risk of DME was significantly associated with duration of DM, diastolic blood pressure, hematocrit, glycosylated hemoglobin, and urine albumin-to-creatinine ratio stage. The MLR model using these five risk factors was selected as the final prediction model due to its better performance than the machine learning models using all variables. The AUC, ACC, sensitivity, and specificity were 0.80, 0.69, 0.80, and 0.67 in the internal validation, and 0.82, 0.54, 1.00, and 0.48 in prospective validation, respectively. In external validation, the AUC, ACC, sensitivity and specificity were 0.84, 0.68, 0.90 and 0.60 in ZJH, 0.89, 0.77, 1.00 and 0.72 in FAHKMU, and 0.80, 0.67, 0.75, and 0.65 in PHJM, respectively.ConclusionThe MLR model is a simple, rapid, and reliable tool for early detection of DME in individuals with T2DM without the needs of specialized ophthalmologic examinations.

Deep Learning Enabled Diabetic Retinopathy Diagnosis Using Retinal Fundus Images

Abstract: This paper pivots on (DR) is a leading cause of blindness worldwide. Early detection and effective management are crucial in preventing damage to the retina. In recent years, (DL) techniques have shown promise in aiding the DR. This paper aims to investigate the diagnosis of using (CNNs) for automated DR screening. The study utilized a available patient dataset of retinal images to train and testing CNN model for DR detection and classification. Results showed that given (DL) techniques achieved with accurately in both tasks, outperforming existing state-of-the-art methods. The findings suggest the (DL) algorithms can aid in the early detection and management of DR, potentially reducing the burden of the condition on healthcare systems and improving patient outcomes

Evaluation of Artificial Intelligence Algorithms for Diabetic Retinopathy Detection: Protocol for a Systematic Review and Meta-Analysis.

Diabetic retinopathy (DR) is one of the most common complications of diabetes mellitus. The global burden is immense with a worldwide prevalence of 8.5%. Recent advancements in artificial intelligence (AI) have demonstrated the potential to transform the landscape of ophthalmology with earlier detection and management of DR. This study seeks to provide an update and evaluate the accuracy and current diagnostic ability of AI in detecting DR versus ophthalmologists. Additionally, this review will highlight the potential of AI integration to enhance DR screening, management, and disease progression. A systematic review of the current landscape of AI's role in DR will be undertaken, guided by the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) model. Relevant peer-reviewed papers published in English will be identified by searching 4 international databases: PubMed, Embase, CINAHL, and the Cochrane Central Register of Controlled Trials. Eligible studies will include randomized controlled trials, observational studies, and cohort studies published on or after 2022 that evaluate AI's performance in retinal imaging detection of DR in diverse adult populations. Studies that focus on specific comorbid conditions, nonimage-based applications of AI, or those lacking a direct comparison group or clear methodology will be excluded. Selected papers will be independently assessed for bias by 2 review authors (JS and DM) using the Quality Assessment of Diagnostic Accuracy Studies tool for systematic reviews. Upon systematic review completion, if it is determined that there are sufficient data, a meta-analysis will be performed. Data synthesis will use a quantitative model. Statistical software such as RevMan and STATA will be used to produce a random-effects meta-regression model to pool data from selected studies. Using selected search queries across multiple databases, we accumulated 3494 studies regarding our topic of interest, of which 1588 were duplicates, leaving 1906 unique research papers to review and analyze. This systematic review and meta-analysis protocol outlines a comprehensive evaluation of AI for DR detection. This active study is anticipated to assess the current accuracy of AI methods in detecting DR. DERR1-10.2196/57292.

HbA1c changes in a deprived population who followed or not a diabetes self-management programme, organised in a multi-professional primary care practice: a historical cohort study on 207 patients between 2017 and 2019

BackgroundDiabetes self-management (DSM) helps people with diabetes to become actors in their disease. Deprived populations are particularly affected by diabetes and are less likely to have access to these programmes. DSM implementation in primary care, particularly in a multi-professional primary care practice (MPCP), is a valuable strategy to promote care access for these populations. In Rennes (Western France), a DSM programme was designed by a MPCP in a socio-economically deprived area. The study objective was to compare diabetes control in people who followed or not this DSM programme.MethodThe historical cohort of patients who participated in the DSM programme at the MPCP between 2017 and 2019 (n = 69) was compared with patients who did not participate in the programme, matched on sex, age, diabetes type and place of the general practitioner’s practice (n = 138). The primary outcome was glycated haemoglobin (HbA1c) change between 12 months before and 12 months after the DSM programme. Secondary outcomes included modifications in diabetes treatment, body mass index, blood pressure, dyslipidaemia, presence of microalbuminuria, and diabetes retinopathy screening participation.ResultsHbA1c was significantly improved in the exposed group after the programme (p < 0.01). The analysis did not find any significant between-group difference in socio-demographic data, medical history, comorbidities, and treatment adaptation.ConclusionsThese results, consistent with the international literature, promote the development of DSM programmes in primary care settings in deprived areas. The results of this real-life study need to be confirmed on the long-term and in different contexts (rural area, healthcare organisation).

Measuring Outcomes of Diabetic Retinopathy Screening: What Is Important?

Measuring Outcomes of Diabetic Retinopathy Screening: What Is Important?

Comparison of 21 artificial intelligence algorithms in automated diabetic retinopathy screening using handheld fundus camera

Background Diabetic retinopathy (DR) is a common complication of diabetes and may lead to irreversible visual loss. Efficient screening and improved treatment of both diabetes and DR have amended visual prognosis for DR. The number of patients with diabetes is increasing and telemedicine, mobile handheld devices and automated solutions may alleviate the burden for healthcare. We compared the performance of 21 artificial intelligence (AI) algorithms for referable DR screening in datasets taken by handheld Optomed Aurora fundus camera in a real-world setting. Patients and methods Prospective study of 156 patients (312 eyes) attending DR screening and follow-up. Both papilla- and macula-centred 50° fundus images were taken from each eye. DR was graded by experienced ophthalmologists and 21 AI algorithms. Results Most eyes, 183 out of 312 (58.7%), had no DR and mild NPDR was noted in 21 (6.7%) of the eyes. Moderate NPDR was detected in 66 (21.2%) of the eyes, severe NPDR in 1 (0.3%), and PDR in 41 (13.1%) composing a group of 34.6% of eyes with referable DR. The AI algorithms achieved a mean agreement of 79.4% for referable DR, but the results varied from 49.4% to 92.3%. The mean sensitivity for referable DR was 77.5% (95% CI 69.1–85.8) and specificity 80.6% (95% CI 72.1–89.2). The rate for images ungradable by AI varied from 0% to 28.2% (mean 1.9%). Nineteen out of 21 (90.5%) AI algorithms resulted in grading for DR at least in 98% of the images. Conclusions Fundus images captured with Optomed Aurora were suitable for DR screening. The performance of the AI algorithms varied considerably emphasizing the need for external validation of screening algorithms in real-world settings before their clinical application.

Deep learning-driven automated quality assessment of ultra-widefield optical coherence tomography angiography images for diabetic retinopathy

AbstractImage quality assessment (IQA) of fundus images constitutes a foundational step in automated disease analysis. This process is pivotal in supporting the automation of screening, diagnosis, follow-up, and related academic research for diabetic retinopathy (DR). This study introduced a deep learning-based approach for IQA of ultra-widefield optical coherence tomography angiography (UW-OCTA) images of patients with DR. Given the novelty of ultra-widefield technology, its limited prevalence, the high costs associated with equipment and operational training, and concerns regarding ethics and patient privacy, UW-OCTA datasets are notably scarce. To address this, we initially pre-train a vision transformer (ViT) model on a dataset comprising 6 mm × 6 mm OCTA images, enabling the model to acquire a fundamental understanding of OCTA image characteristics and quality indicators. Subsequent fine-tuning on 12 mm × 12 mm UW-OCTA images aims to enhance accuracy in quality assessment. This transfer learning strategy leverages the generic features learned during pre-training and adjusts the model to evaluate UW-OCTA image quality effectively. Experimental results demonstrate that our proposed method achieves superior performance compared to ResNet18, ResNet34, and ResNet50, with an AUC of 0.9026 and a Kappa value of 0.7310. Additionally, ablation studies, including the omission of pre-training on 6 mm × 6 mm OCTA images and the substitution of the backbone network with the ViT base version, resulted in varying degrees of decline in AUC and Kappa values, confirming the efficacy of each module within our methodology.

Cost-effectiveness of diabetic retinopathy screening for newly diagnosed type 2 diabetic patients: A nationwide population-based propensity score-matched cohort study

AimsThis study investigated the association between the frequency of screening for diabetic retinopathy (DR) versus the development of DR and corresponding medical expenses among patients newly diagnosed with type 2 diabetes mellitus (T2DM). MethodsThis longitudinal, population-based study used the Taiwan National Health Insurance Research Database (2004 to 2020) as a data source. Propensity score matching (PSM) (sex, age, comorbidities and concurrent medication use) was employed in the grouping of T2DM patients according to different frequency of DR screening. Outcome measures included the proportion of patients who developed DR, who received DR treatment, and the associated medical expenses and hospitalizations. ResultsThe 17-year cohort included 337,046 patients. After PSM, three groups each containing 35,739 patients were assembled and analyzed. Compared to low-frequency screening, high-frequency screening was more effective in detecting patients requiring treatment; however, the net cost for treatment was significantly lower. Standard-frequency screening appears to provide the best balance in terms of DR detection, diagnosis interval, the risk of DR-related hospitalization, and DR treatment costs. ConclusionsIn this real-world cohort study covering all levels of the healthcare system, infrequent screening was associated with delayed diagnosis and elevated treatment costs, while a fundus screening interval of 1–2 years proved optimal in terms of detection and medical expenditures.

Transition probabilities of diabetic retinopathy and death in an Asian population with diabetes

PurposeTo evaluate the dynamic transitions in diabetic retinopathy (DR) severity over time and associated risk factors in an Asian population with diabetes. DesignLongitudinal cohort study MethodsWe analyzed data from 9481 adults in the Singapore Integrated Diabetic Retinopathy Screening Program (2010–2015) with linkage to death registry. A multistate Markov model adjusted for age, sex, systolic blood pressure (SBP), diabetes duration, HbA1c, and body mass index (BMI) was applied to estimate annual transition probabilities between four DR states (no, mild, moderate, and severe/proliferative) and death, and the mean sojourn time in each state. ResultsThe median assessment interval was 12 months, with most patients having 3 assessments. Annual probabilities for DR progression (no-to-mild, mild-to-moderate and moderate-to-severe/proliferative) were 6.1 %, 7.0 % and 19.3 %, respectively; and for regression (mild-to-no, moderate-to-mild and severe-to-moderate) were 55.4 %, 17.3 % and 4.4 %, respectively. Annual mortality rates from each DR state were 1.2 %, 2.0 %, 18.7 %, and 30.0 %. The sojourn time in each state were 8.2, 0.8, 0.8 and 2.2 years. Higher HbA1c and SBP levels were associated with progression of no-mild and mild-moderate DR, and diabetes duration with no-to-mild and moderate-to-severe/proliferative DR. Lower HbA1c levels were associated with regression from mild-to-no and moderate-to-mild, and higher BMI with mild-to-no DR. ConclusionsOur results suggest a prolonged duration (∼8 years) in developing mild DR, with faster transitions (within a year) from mild or moderate states. Moderate/above DR greatly increases the probability of progression and death as compared to mild DR/below. HbA1c was associated with both progression as well as regression.

One-field, two-field and five-field handheld retinal imaging compared with standard seven-field Early Treatment Diabetic Retinopathy Study photography for diabetic retinopathy screening

Background/aimsTo determine agreement of one-field (1F, macula-centred), two-field (2F, disc–macula) and five-field (5F, macula, disc, superior, inferior and nasal) mydriatic handheld retinal imaging protocols for the assessment of diabetic retinopathy...

Validation of using smartphone based non-mydriatic camera for retinal photography to diagnose diabetic retinopathy

Purpose: To assess the sensitivity and specificity of retinal imaging captured by portable non-mydriatic ‘fundus on phone’ camera as a screening tool against the conventional seven field digital fundus photography. Design: Prospective comparative study design. Methods: Study was performed over 300 diabetic patients (600 eyes). First fundus pictures were taken with non-mydriatic ‘fundus-on-phone’ camera and then with Zeiss seven field fundus camera after pupillary dilation. Images were analysed and compared by two observers. Results: Out of all the 600 undilated fundus images, 15.5% were ungradable, 76% were graded as poor and average quality by both observers. From the dilated fundus images taken using Zeiss camera, only 0.8% images were found ungradable by both observers. The sensitivity and specificity for detecting any diabetic retinopathy changes and its severity by using ‘fundus-on-phone’ camera against Zeiss fundus camera were found to be 54.92% and 85.5%, respectively, by observer one and 56.48% and 85.5%, respectively, by observer two. Conclusion: Non-mydriatic retinal imaging using fundus-on-phone camera is not a feasible method for screening diabetic retinopathy due to low sensitivity and high number of poor-quality images.

Synchronous Diagnosis of Diabetic Retinopathy by a Handheld Retinal Camera, Artificial Intelligence, and Simultaneous Specialist Confirmation

PurposeDiabetic retinopathy (DR) is a leading cause of preventable blindness, particularly in underserved regions where access to ophthalmic care is limited. This study presents a proof of concept for utilizing a portable handheld retinal camera with an embedded artificial intelligence (AI) platform, complemented by a synchronous remote confirmation by retina specialists, for DR screening in an underserved rural area. DesignRetrospective cohort study Subjects1,115 individuals with diabetes. MethodsA retrospective analysis of a screening initiative conducted in four municipalities in Northeastern Brazil, targeting the diabetic population. A portable handheld retinal camera captured macula-centered and disc-centered images, which were analyzed by the AI system. Immediate push notifications were sent out to retina specialists upon the detection of significant abnormalities, enabling synchronous verification and confirmation, with on-site patient feedback within minutes. Referral criteria were established, and all referred patients underwent a complete ophthalmic work-up and subsequent treatment. Main outcome measuresProof-of-concept implementation success. ResultsOut of 2,052 invited individuals, 1,115 participated, with a mean age of 60.93 years and diabetes duration of 7.52 years, of whom 66.03% were women. The screening covered 2,222 eyes, revealing various retinal conditions. Referable eyes for DR were 11.84%, with an additional 13% for other conditions (diagnoses included various stages of DR, media opacity, nevus, drusen, enlarged cup-to-disc ratio, pigmentary changes, and other). AI performance for overall detection of referable cases (both DR and other conditions) was: sensitivity- 84.23% (95% CI- 82.63-85.84), specificity- 80.79% (95% CI- 79.05- 82.53). When we assessed whether AI matched any clinical diagnosis, be it referable or not, sensitivity was 85.67% (95% CI- 84.12-87.22), specificity was 98.86 (95% CI- 98.39-99.33), and AUC was 0.92 (95% CI- 0.91-0.94). ConclusionsThe integration of a portable device, AI analysis, and synchronous medical validation has the potential to play a crucial role in preventing blindness from DR, especially in socially unequal scenarios.