Disparities Between Teleretinal Imaging Findings and Patient-Reported Diabetic Retinopathy Status and Follow-up Eye Care Interval: A 10-Year Prospective Study.

OBJECTIVE: To assess self-reported awareness of diabetic retinopathy (DR) and concordance of eye examination follow-up compared with findings from concurrent retinal images. RESEARCH DESIGN AND METHODS: We conducted a prospective observational 10-year study of 26,876 consecutive patients with diabetes who underwent retinal imaging during an endocrinology visit. Awareness and concordance were evaluated using questionnaires and retinal imaging. RESULTS: Awareness information and gradable images were available in 25,360 patients (94.3%). Severity of DR by imaging was as follows: no DR (n = 14,317; 56.5%), mild DR (n = 6,805; 26.8%), or vision-threatening DR (vtDR; n = 4,238; 16.7%). In the no, mild, and vtDR groups, 96.7%, 88.5%, and 54.9% of patients, respectively, reported being unaware of any prior DR. When DR was present, reporting no prior DR was associated with shorter diabetes duration, milder DR, last eye examination >1 year before, no dilation, no scheduled appointment, and less specialized provider (all P < 0.001). Among patients with vtDR, 41.2%, 58.1%, and 64.2% did not report being aware of any DR and follow-up was concordant with current DR severity in 66.7%, 41.3%, and 25.4% (P < 0.001) of patients when prior examination was performed by a retinal specialist, nonretinal ophthalmologist, or optometrist (P < 0.001), respectively. CONCLUSIONS: Substantial discrepancies exist between DR presence, patient awareness, and concordance of follow-up across all DR severity levels. These discrepancies are present across all eye care provider types, with the magnitude influenced by provider type. Therefore, patient self-report should not be relied upon to reflect DR status. Modification of medical care and education models may be necessary to enhance retention of ophthalmic knowledge in patients with diabetes and ensure accurate communication between all health care providers.

Macula vs periphery in diabetic retinopathy: OCT-angiography and ultrawide field fluorescein angiography imaging of retinal non perfusion.

OBJECTIVES: To investigate the association between peripheral non-perfusion index (NPI) on ultrawide-field fluorescein angiography (UWF-FA) and quantitative OCT-Angiography (OCT-A) metrics in the macula. METHODS: In total, 48 eyes with UWF-colour fundus photos (CFP), UWF-FA (California, Optos) and OCT-A (Spectralis, Heidelberg) were included. OCT-A (3 × 3 mm) was used to determine foveal avascular zone (FAZ) parameters and vessel density (VD), perfusion density (PD), fractal dimension (FD) on superficial capillary plexus (SCP). NPI's extent and distribution was determined on UWF-FA within fovea centred concentric rings corresponding to posterior pole (<10 mm), mid-periphery (10-15 mm), and far-periphery (>15 mm) and within the total retinal area, the central macular field (6×6 mm), ETDRS fields and within each extended ETDRS field (P3-P7). RESULTS: Macular PD was correlated to NPI in total area of retina (Spearman ρ = 0.69, p < 0.05), posterior pole (ρ = 0.48, p < 0.05), mid-periphery (ρ = 0.65, p < 0.05), far-periphery (ρ = 0.59, p < 0.05), P3-P7 (ρ = 0,55 at least, p < 0.05 for each), central macula (ρ = 0.47, p < 0.05), total area in ETDRS (ρ = 0.55, p < 0.05). Macular VD and FD were correlated to NPI of total area of the retina (ρ = 0.60 and 0.61, p < 0.05), the mid-periphery (ρ = 0.56, p < 0.05) and far-periphery (ρ = 0.60 and ρ = 0.61, p < 0.05), and in P3-P7 (p < 0.05). FAZ perimeter was significantly corelated to NPI at posterior pole and central macular area (ρ = 0.37 and 0.36, p < 0.05), and FAZ area to NPI in central macular area (ρ = 0.36, p < 0.05). CONCLUSIONS: Perfusion macular metrics on OCT-A correlated with UWF-FA's non-perfusion (NP), particularly in the retina's mid and far periphery, suggesting that OCT-A might be a useful non-invasive method to estimate peripheral retinal NP.

Automated Machine Learning for Predicting Diabetic Retinopathy Progression From Ultra-Widefield Retinal Images.

Importance: Machine learning (ML) algorithms have the potential to identify eyes with early diabetic retinopathy (DR) at increased risk for disease progression. Objective: To create and validate automated ML models (autoML) for DR progression from ultra-widefield (UWF) retinal images. Design, Setting and Participants: Deidentified UWF images with mild or moderate nonproliferative DR (NPDR) with 3 years of longitudinal follow-up retinal imaging or evidence of progression within 3 years were used to develop automated ML models for predicting DR progression in UWF images. All images were collected from a tertiary diabetes-specific medical center retinal image dataset. Data were collected from July to September 2022. Exposure: Automated ML models were generated from baseline on-axis 200° UWF retinal images. Baseline retinal images were labeled for progression based on centralized reading center evaluation of baseline and follow-up images according to the clinical Early Treatment Diabetic Retinopathy Study severity scale. Images for model development were split 8-1-1 for training, optimization, and testing to detect 1 or more steps of DR progression. Validation was performed using a 328-image set from the same patient population not used in model development. Main Outcomes and Measures: Area under the precision-recall curve (AUPRC), sensitivity, specificity, and accuracy. Results: A total of 1179 deidentified UWF images with mild (380 [32.2%]) or moderate (799 [67.8%]) NPDR were included. DR progression was present in half of the training set (590 of 1179 [50.0%]). The model's AUPRC was 0.717 for baseline mild NPDR and 0.863 for moderate NPDR. On the validation set for eyes with mild NPDR, sensitivity was 0.72 (95% CI, 0.57-0.83), specificity was 0.63 (95% CI, 0.57-0.69), prevalence was 0.15 (95% CI, 0.12-0.20), and accuracy was 64.3%; for eyes with moderate NPDR, sensitivity was 0.80 (95% CI, 0.70-0.87), specificity was 0.72 (95% CI, 0.66-0.76), prevalence was 0.22 (95% CI, 0.19-0.27), and accuracy was 73.8%. In the validation set, 6 of 9 eyes (75%) with mild NPDR and 35 of 41 eyes (85%) with moderate NPDR progressed 2 steps or more were identified. All 4 eyes with mild NPDR that progressed within 6 months and 1 year were identified, and 8 of 9 (89%) and 17 of 20 (85%) with moderate NPDR that progressed within 6 months and 1 year, respectively, were identified. Conclusions and Relevance: This study demonstrates the accuracy and feasibility of automated ML models for identifying DR progression developed using UWF images, especially for prediction of 2-step or greater DR progression within 1 year. Potentially, the use of ML algorithms may refine the risk of disease progression and identify those at highest short-term risk, thus reducing costs and improving vision-related outcomes.

Accuracy of Integrated Artificial Intelligence Grading Using Handheld Retinal Imaging in a Community Diabetic Eye Screening Program.

Purpose: To evaluate mydriatic handheld retinal imaging performance assessed by point-of-care (POC) artificial intelligence (AI) as compared with retinal image graders at a centralized reading center (RC) in identifying diabetic retinopathy (DR) and diabetic macular edema (DME). Design: Prospective, comparative study. Subjects: Five thousand five hundred eighty-five eyes from 2793 adult patients with diabetes. Methods: Point-of-care AI assessment of disc and macular handheld retinal images was compared with RC evaluation of validated 5-field handheld retinal images (disc, macula, superior, inferior, and temporal) in identifying referable DR (refDR; defined as moderate nonproliferative DR [NPDR], or worse, or any level of DME) and vision-threatening DR (vtDR; defined as severe NPDR or worse, or any level of center-involving DME [ciDME]). Reading center evaluation of the 5-field images followed the international DR/DME classification. Sensitivity (SN) and specificity (SP) for ungradable images, refDR, and vtDR were calculated. Main Outcome Measures: Agreement for DR and DME; SN and SP for refDR, vtDR, and ungradable images. Results: Diabetic retinopathy severity by RC evaluation: no DR, 67.3%; mild NPDR, 9.7%; moderate NPDR, 8.6%; severe NPDR, 4.8%; proliferative DR, 3.8%; and ungradable, 5.8%. Diabetic macular edema severity by RC evaluation was as follows: no DME (80.4%), non-ciDME (7.7%), ciDME (4.4%), and ungradable (7.5%). Referable DR was present in 25.3% and vtDR was present in 17.5% of eyes. Images were ungradable for DR or DME in 7.5% by RC evaluation and 15.4% by AI. There was substantial agreement between AI and RC for refDR (κ = 0.66) and moderate agreement for vtDR (κ = 0.54). The SN/SP of AI grading compared with RC evaluation was 0.86/0.86 for refDR and 0.92/0.80 for vtDR. Conclusions: This study demonstrates that POC AI following a defined handheld retinal imaging protocol at the time of imaging has SN and SP for refDR that meets the current United States Food and Drug Administration thresholds of 85% and 82.5%, but not for vtDR. Integrating AI at the POC could substantially reduce centralized RC burden and speed information delivery to the patient, allowing more prompt eye care referral. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

INTEGRATING MACULAR OPTICAL COHERENCE TOMOGRAPHY WITH ULTRAWIDE-FIELD IMAGING IN A DIABETIC RETINOPATHY TELEMEDICINE PROGRAM USING A SINGLE DEVICE.

PURPOSE: To determine the effect of combined macular spectral-domain optical coherence tomography (SD-OCT) and ultrawide field retinal imaging (UWFI) within a telemedicine program. METHODS: Comparative cohort study of consecutive patients with both UWFI and SD-OCT. Ultrawide field retinal imaging and SD-OOCT were independently evaluated for diabetic macular edema (DME) and nondiabetic macular abnormality. Sensitivity and specificity were calculated with SD-OCT as the gold standard. RESULTS: Four hundred twenty-two eyes from 211 diabetic patients were evaluated. Diabetic macular edema severity by UWFI was as follows: no DME 93.4%, noncenter involved DME (nonciDME) 5.1%, ciDME 0.7%, ungradable DME 0.7%. SD-OCT was ungradable in 0.5%. Macular abnormality was identified in 34 (8.1%) eyes by UWFI and in 44 (10.4%) eyes by SD-OCT. Diabetic macular edema represented only 38.6% of referable macular abnormality identified by SD-OCT imaging. Sensitivity/specificity of UWFI compared with SD-OCT was 59%/96% for DME and 33%/99% for ciDME. Sensitivity/specificity of UWFI compared with SDOCT was 3%/98% for epiretinal membrane. CONCLUSION: Addition of SD-OCT increased the identification of macular abnormality by 29.4%. More than 58.3% of the eyes believed to have any DME on UWF imaging alone were false-positives by SD-OCT. The integration of SD-OCT with UWFI markedly increased detection and reduced false-positive assessments of DME and macular abnormality in a teleophthalmology program.

Artificial intelligence for telemedicine diabetic retinopathy screening: a review.

PURPOSE: This study aims to compare artificial intelligence (AI) systems applied in diabetic retinopathy (DR) teleophthalmology screening, currently deployed systems, fairness initiatives and the challenges for implementation. METHODS: The review included articles retrieved from PubMed/Medline/EMBASE literature search strategy regarding telemedicine, DR and AI. The screening criteria included human articles in English, Portuguese or Spanish and related to telemedicine and AI for DR screening. The author's affiliations and the study's population income group were classified according to the World Bank Country and Lending Groups. RESULTS: The literature search yielded a total of 132 articles, and nine were included after full-text assessment. The selected articles were published between 2004 and 2020 and were grouped as telemedicine systems, algorithms, economic analysis and image quality assessment. Four telemedicine systems that perform a quality assessment, image preprocessing and pathological screening were reviewed. A data and post-deployment bias assessment are not performed in any of the algorithms, and none of the studies evaluate the social impact implementations. There is a lack of representativeness in the reviewed articles, with most authors and target populations from high-income countries and no low-income country representation. CONCLUSIONS: Telemedicine and AI hold great promise for augmenting decision-making in medical care, expanding patient access and enhancing cost-effectiveness. Economic studies and social science analysis are crucial to support the implementation of AI in teleophthalmology screening programs. Promoting fairness and generalizability in automated systems combined with telemedicine screening programs is not straightforward. Improving data representativeness, reducing biases and promoting equity in deployment and post-deployment studies are all critical steps in model development.

Molecular Signatures of Glomerular Neovascularization in a Patient with Diabetic Kidney Disease.

The Kidney Precision Medicine Project (KPMP) aims to create a kidney tissue atlas, define disease subgroups, and identify critical cells, pathways, and targets for novel therapies through molecular investigation of human kidney biopsies obtained from participants with acute kidney injury (AKI) or chronic kidney disease (CKD). We present the case of a 66-year-old woman with diabetic kidney disease who underwent a protocol KPMP kidney biopsy. Her clinical history included diabetes mellitus complicated by neuropathy and eye disease, increased insulin resistance, hypertension, albuminuria, and relatively preserved glomerular filtration rate (early CKD stage 3a). The patient's histopathology was consistent with diabetic nephropathy and arterial and arteriolar sclerosis. Three-dimensional, immunofluorescence imaging of the kidney biopsy specimen revealed extensive peri-glomerular neovascularization that was underestimated by standard histopathologic approaches. Spatial transcriptomics was performed to obtain gene expression signatures at discrete areas of the kidney biopsy. Gene expression in the areas of glomerular neovascularization revealed increased expression of genes involved in angiogenic signaling, proliferation and survival of endothelial cells, as well as new vessel maturation and stability. This molecular correlation provides additional insights into the development of kidney disease in patients with diabetes and spotlights how novel molecular techniques employed by the KPMP can supplement and enrich the histopathologic diagnosis obtained from a kidney biopsy.

Comparison of Diabetic Retinopathy Lesions Identified Using Ultrawide Field Imaging and Optical Coherence Tomography Angiography.

INTRODUCTION: Optical coherence tomography (OCT) angiography (OCTA) has the potential to influence the diagnosis and management of diabetic eye disease. This study aims to determine the correlation between diabetic retinopathy (DR) findings on ultrawide field (UWF) color photography (UWF-CP), UWF fluorescein angiography (UWF-FA), and OCTA. METHODS: This is a cross-sectional, prospective study. One hundred and fourteen eyes from 57 patients with diabetes underwent mydriatic UWF-CP, UWF-FA, and OCTA. DR severity was assessed. Ischemic areas were identified on UWF-FA using ImageJ and the nonperfusion index (NPI) was calculated. Diabetic macular edema (DME) was assessed using OCT. Superficial capillary plexus vessel density (VD), vessel perfusion (VP), and foveal avascular zone (FAZ) area were automatically measured on OCTA. Pearson correlation coefficient between the imaging modalities was determined. RESULTS: Forty-five eyes were excluded due to non-DR findings or prior laser photocoagulation; 69 eyes were analyzed. DR severity was associated with larger NPI (r = 0.55944, p < 0.0001) even after distinguishing between cones (Cone Nonperfusion Index [CPI]: r = 0.55617, p < 0.0001) and rods (Rod Nonperfusion Index [RPI]: r = 0.55285, p < 0.0001). In eyes with nonproliferative DR (NPDR), NPI is correlated with DME (r = 0.51156, p = 0.0017) and central subfield thickness (CST) (r = 0.67496, p < 0.0001). UWF-FA macular nonperfusion correlated with NPI (r = 0.42899, p = 0.0101), CPI (r = 0.50028, p = 0.0022), and RPI (r = 0.49027, p = 0.0028). Central VD and VP correlated with the DME presence (r = 0.52456, p < 0.0001; r = 0.51952, p < 0.0001) and CST (r = 0.50133, p < 0.0001; r = 0.48731, p < 0.0001). Central VD and VP were correlated with macular nonperfusion (r = 0.44503, p = 0.0065; r = 0.44239, p = 0.0069) in eyes with NPDR. Larger FAZ was correlated with decreased central VD (r = -0.60089, p = 0.0001) and decreased central VP (r = -0.59224, p = 0.0001). CONCLUSION: UWF-CP, UWF-FA, and OCTA findings provide relevant clinical information on diabetic eyes. Nonperfusion on UWF-FA is correlated with DR severity and DME. OCTA metrics of the superficial capillary plexus correlate with the incidence of DME and macular ischemia.

Comparison of 2-Field and 5-Field Mydriatic Handheld Retinal Imaging in a Community-Based Diabetic Retinopathy Screening Program.

INTRODUCTION: The purpose of this study was to compare 2-field (2F) and 5-field (5F) mydriatic handheld retinal imaging for the assessment of diabetic retinopathy (DR) severity in a community-based DR screening program (DRSP). METHODS: This was a prospective, cross-sectional diagnostic study, evaluating images of 805 eyes from 407 consecutive patients with diabetes acquired from a community-based DRSP. Mydriatic standardized 5F imaging (macula, disc, superior, inferior, temporal) with handheld retinal camera was performed. 2F (disc, macula), and 5F images were independently assessed using the International DR classification at a centralized reading center. Simple (K) and weighted (Kw) kappa statistics were calculated for DR. Sensitivity and specificity for referable DR ([refDR] moderate nonproliferative DR [NPDR] or worse) and vision-threatening DR ([vtDR] severe NPDR or worse) for 2F compared to 5F imaging were calculated. RESULTS: Distribution of DR severity by 2F/5F images (%): no DR 66.0/61.7, mild NPDR 10.7/14.4, moderate NPDR 7.9/8.1, severe NPDR 3.3/5.6, proliferative DR 5.6/4.6, ungradable 6.5/5.6. Exact agreement of DR grading between 2F and 5F was 81.7%, within 1-step 97.1% (K = 0.64, Kw = 0.78). Sensitivity/specificity for 2F compared 5F was refDR 0.80/0.97, vtDR 0.73/0.98. The ungradable images rate with 2F was 16.1% higher than with 5F (6.5 vs. 5.6%, p < 0.001). CONCLUSIONS: Mydriatic 2F and 5F handheld imaging have substantial agreement in assessing severity of DR. However, the use of mydriatic 2F handheld imaging only meets the minimum standards for sensitivity and specificity for refDR but not for vtDR. When using handheld cameras, the addition of peripheral fields in 5F imaging further refines the referral approach by decreasing ungradable rate and increasing sensitivity for vtDR.

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/AIMS: To 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 (DR) as compared with standard seven-field Early Treatment Diabetic Retinopathy Study (ETDRS) photography. METHODS: Prospective, comparative instrument validation study. Mydriatic retinal images were taken using three handheld retinal cameras: Aurora (AU; 50° field of view (FOV), 5F), Smartscope (SS; 40° FOV, 5F), and RetinaVue (RV; 60° FOV, 2F) followed by ETDRS photography. Images were evaluated at a centralised reading centre using the international DR classification. Each field protocol (1F, 2F and 5F) was graded independently by masked graders. Weighted kappa (Kw) statistics assessed agreement for DR. Sensitivity (SN) and specificity (SP) for referable diabetic retinopathy (refDR; moderate non-proliferative diabetic retinopathy (NPDR) or worse, or ungradable images) were calculated. RESULTS: Images from 225 eyes of 116 patients with diabetes were evaluated. Severity by ETDRS photography: no DR, 33.3%; mild NPDR, 20.4%; moderate, 14.2%; severe, 11.6%; proliferative, 20.4%. Ungradable rate for DR: ETDRS, 0%; AU: 1F 2.23%, 2F 1.79%, 5F 0%; SS: 1F 7.6%, 2F 4.0%, 5F 3.6%; RV: 1F 6.7%, 2F 5.8%. Agreement rates of DR grading between handheld retinal imaging and ETDRS photography were (Kw, SN/SP refDR) AU: 1F 0.54, 0.72/0.92; 2F 0.59, 0.74/0.92; 5F 0.75, 0.86/0.97; SS: 1F 0.51, 0.72/0.92; 2F 0.60, 0.75/0.92; 5F 0.73, 0.88/0.92; RV: 1F 0.77, 0.91/0.95; 2F 0.75, 0.87/0.95. CONCLUSION: When using handheld devices, the addition of peripheral fields decreased the ungradable rate and increased SN and SP for refDR. These data suggest the benefit of additional peripheral fields in DR screening programmes that use handheld retinal imaging.

Comparisons of Handheld Retinal Imaging with Optical Coherence Tomography for the Identification of Macular Pathology in Patients with Diabetes.

INTRODUCTION: Handheld retinal imaging cameras are relatively inexpensive and highly portable devices that have the potential to significantly expand diabetic retinopathy (DR) screening, allowing a much broader population to be evaluated. However, it is essential to evaluate if these devices can accurately identify vision-threatening macular diseases if DR screening programs will rely on these instruments. Thus, the purpose of this study was to evaluate the detection of diabetic macular pathology using monoscopic macula-centered images using mydriatic handheld retinal imaging compared with spectral domain optical coherence tomography (SDOCT). METHODS: Mydriatic 40°-60° macula-centered images taken with 3 handheld retinal imaging devices (Aurora [AU], SmartScope [SS], RetinaVue 700 [RV]) were compared with the Cirrus 6000 SDOCT taken during the same visit. Images were evaluated for the presence of diabetic macular edema (DME) on monoscopic fundus photographs adapted from Early Treatment Diabetic Retinopathy Study (ETDRS) definitions (no DME, noncenter-involved DME [non-ciDME], and center-involved DME [ciDME]). Sensitivity, specificity, positive predictive value, and negative predictive value were calculated for each device with SDOCT as gold standard. RESULTS: Severity by ETDRS photos: no DR 33.3%, mild NPDR 20.4%, moderate 14.2%, severe 11.6%, proliferative 20.4%, and ungradable for DR 0%; no DME 83.1%, non-ciDME 4.9%, ciDME 12.0%, and ungradable for DME 0%. Gradable images by SDOCT (N = 217, 96.4%) showed no DME in 75.6%, non-ciDME in 9.8%, and ciDME in 11.1%. The ungradable rate for images (poor visualization in >50% of the macula) was AU: 0.9%, SS: 4.4%, and RV: 6.2%. For DME, sensitivity and specificity were similar across devices (0.5-0.64, 0.93-0.97). For nondiabetic macular pathology (ERM, pigment epithelial detachment, traction retinal detachment) across all devices, sensitivity was low to moderate (0.2-0.5) but highly specific (0.93-1.00). CONCLUSIONS: Compared to SDOCT, handheld macular imaging attained high specificity but low sensitivity in identifying macular pathology. This suggests the importance of SDOCT evaluation for patients suspected to have DME on fundus photography, leading to more appropriate referral refinement.

Performance of Automated Machine Learning for Diabetic Retinopathy Image Classification from Multi-field Handheld Retinal Images.

PURPOSE: To create and validate code-free automated deep learning models (AutoML) for diabetic retinopathy (DR) classification from handheld retinal images. DESIGN: Prospective development and validation of AutoML models for DR image classification. PARTICIPANTS: A total of 17 829 deidentified retinal images from 3566 eyes with diabetes, acquired using handheld retinal cameras in a community-based DR screening program. METHODS: AutoML models were generated based on previously acquired 5-field (macula-centered, disc-centered, superior, inferior, and temporal macula) handheld retinal images. Each individual image was labeled using the International DR and diabetic macular edema (DME) Classification Scale by 4 certified graders at a centralized reading center under oversight by a senior retina specialist. Images for model development were split 8-1-1 for training, optimization, and testing to detect referable DR ([refDR], defined as moderate nonproliferative DR or worse or any level of DME). Internal validation was performed using a published image set from the same patient population (N = 450 images from 225 eyes). External validation was performed using a publicly available retinal imaging data set from the Asia Pacific Tele-Ophthalmology Society (N = 3662 images). MAIN OUTCOME MEASURES: Area under the precision-recall curve (AUPRC), sensitivity (SN), specificity (SP), positive predictive value (PPV), negative predictive value (NPV), accuracy, and F1 scores. RESULTS: Referable DR was present in 17.3%, 39.1%, and 48.0% of the training set, internal validation, and external validation sets, respectively. The model's AUPRC was 0.995 with a precision and recall of 97% using a score threshold of 0.5. Internal validation showed that SN, SP, PPV, NPV, accuracy, and F1 scores were 0.96 (95% confidence interval [CI], 0.884-0.99), 0.98 (95% CI, 0.937-0.995), 0.96 (95% CI, 0.884-0.99), 0.98 (95% CI, 0.937-0.995), 0.97, and 0.96, respectively. External validation showed that SN, SP, PPV, NPV, accuracy, and F1 scores were 0.94 (95% CI, 0.929-0.951), 0.97 (95% CI, 0.957-0.974), 0.96 (95% CI, 0.952-0.971), 0.95 (95% CI, 0.935-0.956), 0.97, and 0.96, respectively. CONCLUSIONS: This study demonstrates the accuracy and feasibility of code-free AutoML models for identifying refDR developed using handheld retinal imaging in a community-based screening program. Potentially, the use of AutoML may increase access to machine learning models that may be adapted for specific programs that are guided by the clinical need to rapidly address disparities in health care delivery. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found after the references.

Effect of Accessible Nonmydriatic Retinal Imaging on Diabetic Retinopathy Surveillance Rates.

Purpose: To evaluate the impact on surveillance rates for diabetic retinopathy (DR) by providing nonmydriatic retinal imaging as part of comprehensive diabetes care at no cost to patients or insurers. Methods: A retrospective comparative cohort study was designed. Patients were imaged from April 1, 2016 to March 31, 2017 at a tertiary diabetes-specific academic medical center. Retinal imaging was provided without additional cost beginning October 16, 2016. Images were evaluated for DR and diabetic macular edema using standard protocol at a centralized reading center. Diabetes surveillance rates before and after no-cost imaging were compared. Results: A total of 759 and 2,080 patients respectively were imaged before and after offering no-cost retinal imaging. The difference represents a 274% increase in the number of patients screened. Furthermore, there was a 292% and 261% increase in the number of eyes with mild DR and referable DR, respectively. In the comparative 6-month period, 92 additional cases of proliferative DR were identified, estimated to prevent 6.7 cases of severe visual loss with annual cost savings of $180,230 (estimated yearly cost of severe vision loss per person: $26,900). In patients with referable DR, self-awareness was low, with no significant difference in the before and after groups (39.4% vs. 43.8%, p = 0.3725). Conclusions: Providing retinal imaging as part of comprehensive diabetes care substantially increased the number of patients identified by nearly threefold. The data suggest that the removal of out-of-pocket costs substantially increased patient surveillance rates, which may translate to improved long-term patient outcomes.

Using Ultrawide Field-Directed Optical Coherence Tomography for Differentiating Nonproliferative and Proliferative Diabetic Retinopathy.

Purpose: To evaluate the ability of ultrawide field (UWF)-directed optical coherence tomography (OCT) to detect retinal neovascularization in eyes thought to have severe nonproliferative diabetic retinopathy (NPDR). Methods: Retrospective study of 20 consecutive patients diagnosed with severe NPDR by clinical examination. All patients underwent UWF color imaging (UWF-CI) and UWF-directed OCT following a prespecified imaging protocol to assess the mid periphery, 15/32 (46.9%) eyes underwent UWF-fluorescein angiography (FA). On OCT, new vessels elsewhere (NVE) were defined when vessels breached the internal limiting membrane. Results: A total of 32 eyes of 20 patients were evaluated. Of the 45 suspected areas of intraretinal microvascular abnormalities (IRMA) on UWF-CI, 38 (84.4%) were imaged by UWF-directed OCT, and 9/38 IRMA (23.7%) were NVE by OCT. Furthermore, UWF-directed OCT identified seven additional NVE in three eyes not seen on UWF-CI. This resulted in a change in diabetic retinopathy (DR) severity from severe NPDR to PDR in 8/32 eyes (25.0%). Among the 46.9% of eyes with UWF-FA, UWF-directed OCT agreed with the UWF-FA findings in 80% (12/15 eyes), missing only one peripheral NVE outside the UWF-OCT scanning area. Two eyes had subtle NVD that were not evident on UWF-directed OCT. Conclusions: This pilot study suggests that UWF-directed OCT may help differentiate IRMA from NVE and detect unrecognized NVE in eyes with advanced DR in a clinical practice setting. Future prospective studies in larger cohorts could determine whether this rapid and noninvasive method is clinically relevant in determining NVE presence or retinopathy progression and complication risk. Translational Relevance: UWF-directed OCT may offer a noninvasive alternative to detect NVE in eyes with DR.

Comparisons of handheld retinal imaging devices with ultrawide field images for determining diabetic retinopathy severity.

PURPOSE: To compare diabetic retinopathy (DR) severity identified on handheld retinal imaging with ultrawide field (UWF) images. METHODS: Mydriatic images of 225 eyes of 118 diabetic patients were prospectively imaged with the Aurora (AU) handheld retinal camera [5-field protocol (macula-centred, disc-centred, temporal, superior, inferior)] and compared with UWF images. Images were classified based on the international classification for DR. Sensitivity, specificity, kappa statistics (K/Kw) were calculated on an eye and person-level. RESULTS: Distribution of DR severity by AU/UWF images (%) by eye was no DR 41.3/36.0, mild non-proliferative DR (NPDR) 18.7/17.8, moderate 10.2/10.7, severe 16.4/15.1, proliferative DR (PDR) 13.3/20.4. Agreement between UWF and AU was exact in 64.4%, within 1-step 90.7%, k = 0.55 (95% CI:0.45-0.65), and kw = 0.79 (95% CI:0.73-0.85) by eye, and exact in 68%, within 1-step 92.9%, k = 0.58 (95% CI:0.50-0.66), and kw = 0.76 (95% CI:0.70-0.81) by person. Sensitivity/specificity for any DR, refDR, vtDR and PDR were as follows: 0.90/0.83, 0.90/0.97, 0.82/0.95 and 0.69/1.00 by person and 0.86/0.90, 0.84/0.98, 0.75/0.95 and 0.63/0.99 by eye. Handheld imaging missed 37% (17/46) eyes and 30.8% (8/26) persons with PDR. Only 3.9% (1/26) persons or 6.5% (3/46) eyes with PDR were missed if a referral threshold of moderate NPDR was used. CONCLUSIONS: Data from this study show that comparing UWF and handheld images, when PDR was the referral threshold for handheld devices, 37.0% of eyes or 30.8% of patients with PDR were missed. Due to the identification of neovascular lesions outside of the handheld fields, lower referral thresholds are needed if handheld devices are used.

Evaluation of diabetic retinopathy severity on ultrawide field colour images compared with ultrawide fluorescein angiograms.

PURPOSE: To compare Early Treatment Diabetic Retinopathy Study (ETDRS) diabetic retinopathy (DR) severity on ultrawide field (UWF) colour imaging (CI) and UWF fluorescein angiography (FA). DESIGN: Cross-sectional retrospective review. SUBJECTS: Patients with diabetes mellitus and at least mild non-proliferative DR on UWF-CI. METHODS: UWF-CI and UWF-FA images acquired within 1 month of each other were evaluated independently using ETDRS DR Severity Scale (DRSS) for colour photography adapted for UWF-CI and UWF-FA. Extent of non-perfusion (NP, mm2) was determined from UWF-FA images. MAIN OUTCOME MEASURES: Agreement rate between DRSS on UWF-CI and UWF-FA. RESULTS: Images from 218 eyes of 137 patients with diabetes were evaluated. Agreement rate for DRSS between UWF-CI and UWF-FA was moderate to substantial (K=0.46, Kw=0.65). Over-all, DRSS was worse in 73 (33.5%) eyes on UWF-FA and in 16 (7.3%) on UWF-CI. Compared to UWF-CI, UWF-FA identified more severe DRSS in 26.5% (1 step) and 7.34% (≥2 steps) of eyes. DRSS was worse than UWF-FA in 56 (51.4%) in early DR (ETDRS levels 20-47, N=109) and 17 (15.6%) in eyes with severe DR (53 and higher, N=109). In this cohort, the extent of NP significantly increased as eyes approach moderate non-proliferative DR (levels 43-47, p=0.0065). CONCLUSION: When evaluating UWF-FA images using the ETDRS colour severity scale, DRSS is graded as more severe in a substantial number of eyes than when evaluating UWF-CI. It is uncertain how the DRSS levels using UWF-FA translate to clinical outcomes, but the additional lesions detected might provide added prognostic value. These and other recent data emphasise the need of obtaining outcome data based on UWF-FA and the potential need to develop DRSS specifically tailored for UWF-FA images.

Bias and Non-Diversity of Big Data in Artificial Intelligence: Focus on Retinal Diseases.

Artificial intelligence (AI) applications in healthcare will have a potentially far-reaching impact on patient care, however issues regarding algorithmic bias and fairness have recently surfaced. There is a recognized lack of diversity in the available ophthalmic datasets, with 45% of the global population having no readily accessible representative images, leading to potential misrepresentations of their unique anatomic features and ocular pathology. AI applications in retinal disease may show less accuracy with underrepresented populations that may further widen the gap of health inequality if left unaddressed. Beyond disease symptomatology, social determinants of health must be integrated into our current paradigms of disease understanding, with the goal of more personalized care. AI has the potential to decrease global healthcare inequality, but it will need to be based on a more diverse, transparent and responsible use of healthcare data.

Association of Diabetic Retinopathy with Chronic Kidney Disease Progression in Latinos with Type 2 Diabetes.

Aims: Diabetes remains a leading cause of blindness and kidney failure in the United States. Latinos are at increased risk for type 2 diabetes, and microvascular complications such as diabetic retinopathy (DR) and chronic kidney disease (CKD). We evaluated the association of DR with decline in kidney function in Latinos with type 2 diabetes with or without CKD in a multispecialty clinic. Methods: This is a retrospective cohort study of 351 self-identified Latino individuals with type 2 diabetes enrolled in the Latino Diabetes Initiative at Joslin Diabetes Center. Baseline demographic factors including age, sex, comorbidities, and laboratory values such as A1c and albuminuria were evaluated as predictors of kidney outcomes. The annualized change in estimated glomerular filtration rate (eGFR) was evaluated with a linear regression model. We used logistic regression to evaluate whether DR was associated with development of rapid progressors (>3 mL/min/y eGFR loss) and 30% change in eGFR per year. Results: DR was present in 39.2% of the cohort with mild nonproliferative DR (NPDR) in 57.1%, moderate to severe NPDR in 27.8%, and proliferative DR in 15.0%. Those with DR had a longer duration of type 2 diabetes (P<.001), higher albuminuria (P=.003), and lower baseline eGFR (P=.001). We found that individuals with moderate to severe NPDR and proliferative DR had a significant decline in GFR (coefficient -6.32; 95% CI, -11.40 to -1.23) and -7.82 (-14.99 to -0.65), compared with individuals without DR. Conclusions: The presence of DR is a marker for increased eGFR loss, emphasizing the need for routine retinal examinations as part of comprehensive diabetes care. Individuals with DR should be considered at high risk for GFR loss.