Follow-up Of Diabetic Retinopathy Research Articles

Potential Screening, Grading and Follow-Up of Diabetic Retinopathy in Primary Care Using Artificial Intelligence – How Hard Would It Be to Implement? An Ophthalmologist’s Perspective

Diabetic retinopathy (DR) is a microvascular disorder caused by the long-term effects of diabetes mellitus and among the primary causes of blindness worldwide. Early detection of DR is the key to its effective treatment and subsequent reduction of associated economic burden, but manual screening is time-consuming and of limited availability. A highly sensitive and specific automatic diagnostic tool would significantly improve screening programs and allow referring for further evaluation and treatment in an ophthalmology clinic only patients with significant lesions or with changes between two successive evaluations. Several deep learning-based automated diagnosis tools have been proposed to aid screening but their implementation with minimal costs is not accessible to physicians with no coding knowledge. We aimed to develop a fundus images classification model with no coding knowledge by using generative artificial intelligence (AI) implemented in Windows 11 operating system under subscription (Copilot Pro), a free image analysis tool (Fiji ImageJ2), and Vertex AI, a machine learning (ML) platform launched by Google in 2021. For this purpose, we selected a total of 2961 labelled cases from the APTOS 2019 database of DR fundus images. Images were batch segmented using a Java ImageJ script generated by Copilot Pro and based on the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm. Segmented images were used to train an automated ML classification model to detect DR severity (5 classes – no DR, mild non-proliferative DR, moderate DR, severe DR, proliferative DR). The model achieved an area under the precision-recall curve of 0.889, with a precision rate of 83.8% and a recall rate of 77%. In conclusion, generative AI implemented into Windows operating system together with a free imaging processing tool and Vertex AI allow ophthalmologists with no coding knowledge to benefit from publicly available image databases (thousands of cases) to develop accurate automated diagnostic tools. Such tools have the potential to facilitate screening especially in areas with few specialists.

Factors Associated with Non-compliance for Diabetic Retinopathy Follow-up in an Urban Safety-Net Hospital

ABSTRACTPurpose: Diabetic retinopathy (DR) is the leading cause of preventable blindness in working-aged adults, and compliance in ophthalmic follow-up appointments is critical to prevent vision loss. However, barriers to follow-up care have not been well studied, especially in socio-economically disadvantaged groups. We investigated the risk factors for non-compliance to DR follow-up appointments in a safety-net county hospital.Methods: Two hundred and nine patients who were treated for DR at the Zuckerberg San Francisco General Hospital retina clinic between 1 July 2015 and 30 January 2016 were enrolled in the study. Multivariate logistic regression analysis of demographic and medical information was used to determine independent risk factors for non-compliance to DR follow-up appointments.Results: The mean patient age was 58 years. Sixty-three percent (132/209) of patients were male; the mean haemoglobin A1c level was 8.5 (SD 0.14). Forty-six percent (97/209) of patients attended <80% of their DR follow-up appoinments. Independent risk factors for non-compliance after multivariate logistic regression analysis were diabetic foot involvement [OR: 2.40, 95% CI: (1.04–5.55)] and foot/kidney involvement [OR: 3.79 (1.35–10.5)], history of major depressive disorder (MDD) [OR: 2.11 (1.05–4.26), and having Medi-Cal [OR: 5.01 (2.00–12.5)] or SF Health insurance [OR: 6.79 (2.14–21.5)].Conclusions and Relevance: In conclusion, this is the first study to identify diabetic end organ damage and MDD as independent risk factors for non-compliance in DR follow-up appointments. It is important that health care providers identify these patient subsets and increase efforts to more deliberately encourage follow-up in these high-risk patient groups for DR.

An Update on Optical Coherence Tomography Angiography in Diabetic Retinopathy.

Optical coherence tomography angiography (OCTA) is a novel non-invasive imaging modality for 3-dimensional visualization of retinal and optic nerve capillary networks. In this article, a comprehensive review of relevant original articles in the PubMed database was performed using the search terms “diabetic retinopathy,” “diabetic macular edema,” “diabetes mellitus,” and “optical coherence tomography angiography.” OCTA was found to detect microvascular changes early in diabetes mellitus, even before they become clinically evident. Morphological and qualitative assessment of vascular changes can help to determine the pathophysiological processes, activity, treatment, and follow-up of diabetic retinopathy (DR). Vessel density and foveal avascular zone are the most investigated quantified indices shown to be early predictors of DR, correlated to DR severity and visual function, and useful in predicting response to treatment. OCTA has shown to be a promising alternative to fluorescein angiography in the management of DR. Further studies are warranted to determine the role of OCTA in the routine clinical management of DR.

Role of Electrophysiology in the Early Diagnosis and Follow-Up of Diabetic Retinopathy.

Retinopathy is a severe and common complication of diabetes, representing a leading cause of blindness among working-age people in developed countries. It is estimated that the number of people with diabetic retinopathy (DR) will increase from 126.6 million in 2011 to 191 million by 2030. The pathology seems to be characterized not only by the involvement of retinal microvessels but also by a real neuropathy of central nervous system, similar to what happens to the peripheral nerves, particularly affected by diabetes. The neurophysiological techniques help to assess retinal and nervous (optic tract) function. Electroretinography (ERG) and visual evoked potentials (VEP) allow a more detailed study of the visual function and of the possible effects that diabetes can have on the visual function. These techniques have an important role both in the clinic and in research: the central nervous system, in fact, has received much less attention than the peripheral one in the study of the complications of diabetes. These techniques are safe, repeatable, quick, and objective. In addition, both the ERG (especially the oscillatory potentials and the flicker-ERG) and VEP have proved to be successful tools for the early diagnosis of the disease and, potentially, for the ophthalmologic follow-up of diabetic patients.

Evaluation of Resistive Index by Color Doppler Imaging of Orbital Arteries in Type II Diabetes Mellitus Patients with Microalbuminuria

Objective: Resistive index (RI) is an indirect measurement of blood flow resistance that can be used to evaluate vascular damage in ophthalmologic diseases. The purpose of this study was to evaluate the association between RI values of orbital arteries by using the color Doppler imaging (CDI) in type II diabetes mellitus (DM) patients with microalbuminuria. Patients and methods: We evaluated 91 type II DM patients with microalbuminuria and 27 healthy subjects. The DM patients with microalbuminuria were grouped into two: group 1 consisted of patients with retinopathy (n = 51) and group 2 consisted of patients without retinopathy (n = 40). Healthy subjects constituted group 3 (n = 27). The mean RI values of ophthalmic artery (OA), central retinal artery (CRA), and posterior ciliary artery (PCA) were measured using CDI. Results: Compared to diabetic group 2, group 1 had significantly higher mean RIs of OA, CRA, PCA, and HbA1c levels (p < 0.001 for all). Besides, there were no statistical differences in mean RIs of OA, CRA, and PCA between the control group and group 2 (p = 1.0; p = 0.44; p = 0.67, respectively). Mean RIs of OA and PCA were significantly correlated with age in group 1 (r = 0.549, p < 0.001; r = 0.407, p = 0.003, respectively). Mean RI of CRA was significantly correlated with the duration of diabetes and age in group 1 (r = 0.296, p = 0.035; r = 0.486, p < 0.001, respectively). Conclusion: Our study indicates that RI might be a useful marker for early diagnosis and follow-up of diabetic retinopathy, and orbital RI assessment would be beneficial for diabetic patients with retinopathy.

TIMELY SCREENING AND FOLLOW FOR DIABETIC RETINOPATHY WITH FUNDUS PHOTOGRAPHY

Background. Punctual screening and follow-up of diabetic retinopathy is very important for successful treatment. The result is about 56% less patients with impaired vision or blindness. Patients and methods. With computerised fundus video camera are examined all newly registered diabetics and diabetics without diabetic retinopathy, who are registered at Outpatients Diabetic Clinic Ljubljana. Conclusions. For successful ophthalmologic screening we would need approximately 5.000 examinations with computerised fundus video camera for patients of Outpatients Diabetic Clinic Ljubljana.

Screening and follow-up of diabetic retinopathy using a new mosaic 9-field fundus photography system

Aim: To evaluate the clinical usefulness of a newly developed fundus photographing system and assess its applicability to telemedicine. Methods: Nine overlapping 45° fundus photographs were taken by a new camera equipped with nine internal fixation targets to provide standardized 9-field photographs. The digitally stored images were either edited in 3×3 form or reconstructed as collage (9F) and compared to the ophthalmological examination (OP) and single-field non-mydriatic photography (SC). In telemedicine, 9-field images derived from 61 adolescent diabetics were sent to ophthalmologists over an analog phone line. Results: The sensitivities of the examinations by 9F without and with mydriasis (78 and 82%) were equivalent to OP (84%) and superior to SC (64%). The diagnosis of severity by 9F was also comparable to those by OP, whereas SC tended to underestimate the severity. An average of 1 min 19 s was required to send one edited 9-field photography (average size 259±30 KB) over the Internet. Twelve of these eyes were diagnosed as diabetic retinopathy on a desktop monitor whereas SC gave only seven. Conclusion: This new 9-field fundus photography system can be appropriate for the screening and follow-up of diabetic retinopathy in adult and adolescent diabetic subjects, especially when appiled to telemedicine over the Internet.

Screening and follow-up of diabetic retinopathy by a new mosaic 9-field fundus photography system

Screening and follow-up of diabetic retinopathy by a new mosaic 9-field fundus photography system

Development of a multi-field fundus photographing system using a non-mydriatic camera for diabetic retinopathy

A new fundus photographing system was developed for diabetic subjects with or without simple diabetic retinopathy using a non-mydriatic fundus camera. Eight internal fixation targets were incorporated in a non-mydriatic fundus camera (TRC-NW5S; TOPCON, Tokyo, Japan), interfaced with a 3CCD color camera. Nine 45° fundus photographs were taken in 22 healthy volunteers and 16 diabetic subjects, and stored as digital images. Fundus images were reconstituted as collages on the monitor and printed out. The combined angle reached 94° in collage, and the average times required for photographing with and without mydriasis were 3 min 26 s and 4 min 36 s, respectively. The concordance of fundus images between the first and second photographs of healthy volunteers with and without mydriasis was 95.4% ( n=22). The quality of the photographs, graded on a five-point scale (5, full) by three doctors, was 4.3±0.6 in the volunteers without mydriasis, 4.7±0.4 in the diabetics without mydriasis, and 4.8±0.3 in the volunteers with mydriasis. In retinas with diabetic retinopathy, the system was able to depict microaneurysms, hemorrhages, hard exudates and soft exudates. This new system was satisfactory for the screening and follow-up of diabetic retinopathy.

Visual compromise in the diabetic patient

The importance of an aggressive approach to diagnosis, management, and follow-up of diabetic retinopathy cannot be overstated.