Explore the vast range of titles available.

Diabetic retinopathy can be prevented with screening and early detection. We hypothesized that autonomous artificial intelligence (AI) diabetic eye exams at the point-of-care would increase diabetic eye exam completion rates in a racially and ethnically diverse youth population. AI for Children’s diabetiC Eye ExamS (NCT05131451) is a parallel randomized controlled trial that randomized youth (ages 8-21 years) with type 1 and type 2 diabetes to intervention (autonomous artificial intelligence diabetic eye exam at the point of care), or control (scripted eye care provider referral and education) in an academic pediatric diabetes center. The primary outcome was diabetic eye exam completion rate within 6 months. The secondary outcome was the proportion of participants who completed follow-through with an eye care provider if deemed appropriate. Diabetic eye exam completion rate was significantly higher (100%, 95%CI: 95.5%, 100%) in the intervention group ( n  = 81) than the control group ( n  = 83) (22%, 95%CI: 14.2%, 32.4%)(p < 0.001). In the intervention arm, 25/81 participants had an abnormal result, of whom 64% (16/25) completed follow-through with an eye care provider, compared to 22% in the control arm (p < 0.001). Autonomous AI increases diabetic eye exam completion rates in youth with diabetes. Diabetic retinopathy is a complication of diabetes that can be prevented through screening, yet adherence is low. Here, the authors show that autonomous AI increases diabetic eye exam completion in a diverse cohort of youth with diabetes.

Diabetes is a global eye health issue. Given the rising in diabetes prevalence and ageing population, this poses significant challenge to perform diabetic retinopathy (DR) screening for these patients. Artificial intelligence (AI) using machine learning and deep learning have been adopted by various groups to develop automated DR detection algorithms. This article aims to describe the state-of-art AI DR screening technologies that have been described in the literature, some of which are already commercially available. All these technologies were designed using different training datasets and technical methodologies. Although many groups have published robust diagnostic performance of the AI algorithms for DR screening, future research is required to address several challenges, for examples medicolegal implications, ethics, and clinical deployment model in order to expedite the translation of these novel technologies into the healthcare setting.

Diabetic retinal neurodegeneration (DRN) has been demonstrated in eyes of patients with diabetes mellitus (DM), even in the absence of diabetic retinopathy (DR). However, no studies have looked at the rate of change in retinal layers and presence/development of DR over time per quadrant of the macula. In this longitudinal study, we aimed to clarify whether the rate of DRN is associated with the development/presence of DR within 4 different quadrants of the retina. 80 eyes of 40 patients with type 1 DM and no/minimal DR were included. At 4 visits over 6 years, SD-OCT and fundus images were acquired. Thickness of the Retinal Nerve Fiber Layer (RNFL), Ganglion Cell Layer (GCL) and Inner Plexiform Layer (IPL) was measured in a 1-6mm circle around the fovea overall and for each quadrant (superior, nasal, inferior, temporal). Fundus images were scored for the presence/absence of DR in these areas. Multilevel analyses were performed to determine the rate of change for each layer overall and per quadrant for eyes/quadrants without and with DR during the follow-up period. RNFL and GCL showed significant thinning over time, IPL significant thickening. These changes were more pronounced for GCL and IPL in eyes/quadrants with DR during the follow-up period. RNFL and GCL both showed thinning over time, which was more pronounced in eyes with DR for GCL. This holds true even in regional parts of the retina, as quadrant analyses showed similar results, showing that structural DRN is associated with DR per quadrant independently.

The separation of the retinal vessel network into distinct arterial and venous vessel trees is of high interest. We propose an automated method for identification and separation of retinal vessel trees in a retinal color image by converting a vessel segmentation image into a vessel segment map and identifying the individual vessel trees by graph search. Orientation, width, and intensity of each vessel segment are utilized to find the optimal graph of vessel segments. The separated vessel trees are labeled as primary vessel or branches. We utilize the separated vessel trees for arterial-venous (AV) classification, based on the color properties of the vessels in each tree graph. We applied our approach to a dataset of 50 fundus images from 50 subjects. The proposed method resulted in an accuracy of 91.44% correctly classified vessel pixels as either artery or vein. The accuracy of correctly classified major vessel segments was 96.42%.

Efforts are underway to incorporate retinal neurodegeneration in the diabetic retinopathy severity scale. However, there is no established measure to quantify diabetic retinal neurodegeneration (DRN). We compared total retinal, macular retinal nerve fiber layer (mRNFL) and ganglion cell-inner plexiform layer (GC-IPL) thickness among participants with and without diabetes (DM) in a population-based cohort. Cross-sectional analysis, using the UK Biobank data resource. Separate general linear mixed models (GLMM) were created using DM and glycated hemoglobin as predictor variables for retinal thickness. Sub-analyses included comparing thickness measurements for patients with no/mild diabetic retinopathy (DR) and evaluating factors associated with retinal thickness in participants with and without diabetes. Factors found to be significantly associated with DM or thickness were included in a multiple GLMM. Diagnosis of DM was determined via self-report of diagnosis, medication use, DM-related complications or glycated hemoglobin level of ≥ 6.5%. Total retinal, mRNFL and GC-IPL thickness. 74,422 participants (69,985 with no DM; 4,437 with DM) were included. Median age was 59 years, 46% were men and 92% were white. Participants with DM had lower total retinal thickness (-4.57 μm, 95% CI: -5.00, -4.14; p<0.001), GC-IPL thickness (-1.73 μm, 95% CI: -1.86, -1.59; p<0.001) and mRNFL thickness (-0.68 μm, 95% CI: -0.81, -0.54; p<0.001) compared to those without DM. After adjusting for co-variates, in the GLMM, total retinal thickness was 1.99 um lower (95% CI: -2.47, -1.50; p<0.001) and GC-IPL was 1.02 μm lower (95% CI: -1.18, -0.87; p<0.001) among those with DM compared to without. mRNFL was no longer significantly different (p = 0.369). GC-IPL remained significantly lower, after adjusting for co-variates, among those with DM compared to those without DM when including only participants with no/mild DR (-0.80 μm, 95% CI: -0.98, -0.62; p<0.001). Total retinal thickness decreased 0.40 μm (95% CI: -0.61, -0.20; p<0.001), mRNFL thickness increased 0.20 μm (95% CI: 0.14, 0.27; p<0.001) and GC-IPL decreased 0.26 μm (95% CI: -0.33, -0.20; p<0.001) per unit increase in A1c after adjusting for co-variates. Among participants with diabetes, age, DR grade, ethnicity, body mass index, glaucoma, spherical equivalent, and visual acuity were significantly associated with GC-IPL thickness. GC-IPL was thinner among participants with DM, compared to without DM. This difference persisted after adjusting for confounding variables and when considering only those with no/mild DR. This confirms that GC-IPL thinning occurs early in DM and can serve as a useful marker of DRN.

Diabetic retinopathy (DR) has long been recognized as a microvasculopathy, but retinal diabetic neuropathy (RDN), characterized by inner retinal neurodegeneration, also occurs in people with diabetes mellitus (DM). We report that in 45 people with DM and no to minimal DR there was significant, progressive loss of the nerve fiber layer (NFL) (0.25 μm/y) and the ganglion cell (GC)/inner plexiform layer (0.29 μm/y) on optical coherence tomography analysis (OCT) over a 4-y period, independent of glycated hemoglobin, age, and sex. The NFL was significantly thinner (17.3 μm) in the eyes of six donors with DM than in the eyes of six similarly aged control donors (30.4 μm), although retinal capillary density did not differ in the two groups. We confirmed significant, progressive inner retinal thinning in streptozotocin-induced “type 1” and B6.BKS(D)-Leprdb/J “type 2” diabetic mouse models on OCT; immunohistochemistry in type 1 mice showed GC loss but no difference in pericyte density or acellular capillaries. The results suggest that RDN may precede the established clinical and morphometric vascular changes caused by DM and represent a paradigm shift in our understanding of ocular diabetic complications.

Autonomous artificial intelligence (AI) promises to increase healthcare productivity, but real-world evidence is lacking. We developed a clinic productivity model to generate testable hypotheses and study design for a preregistered cluster-randomized clinical trial, in which we tested the hypothesis that a previously validated US FDA-authorized AI for diabetic eye exams increases clinic productivity (number of completed care encounters per hour per specialist physician) among patients with diabetes. Here we report that 105 clinic days are cluster randomized to either intervention (using AI diagnosis; 51 days; 494 patients) or control (not using AI diagnosis; 54 days; 499 patients). The prespecified primary endpoint is met: AI leads to 40% higher productivity (1.59 encounters/hour, 95% confidence interval [CI]: 1.37–1.80) than control (1.14 encounters/hour, 95% CI: 1.02–1.25), p < 0.00; the secondary endpoint (productivity in all patients) is also met. Autonomous AI increases healthcare system productivity, which could potentially increase access and reduce health disparities. ClinicalTrials.gov NCT05182580.

Healthcare is a large contributor to greenhouse gas (GHG) emissions around the world, given current power generation mix. Telemedicine, with its reduced travel for providers and patients, has been proposed to reduce emissions. Artificial intelligence (AI), and especially autonomous AI, where the medical decision is made without human oversight, has the potential to further reduce healthcare GHG emissions, but concerns have also been expressed about GHG emissions from digital technology, and AI training and inference. In a real-world example, we compared the marginal GHG contribution of an encounter performed by an autonomous AI to that of an in-person specialist encounter. Results show that an 80% reduction may be achievable, and we conclude that autonomous AI has the potential to reduce healthcare GHG emissions.

Autonomous artificial intelligence (AI) for pediatric diabetic retinal disease (DRD) screening has demonstrated safety, effectiveness, and the potential to enhance health equity and clinician productivity. We examined the cost-effectiveness of an autonomous AI strategy versus a traditional eye care provider (ECP) strategy during the initial year of implementation from a health system perspective. The incremental cost-effectiveness ratio (ICER) was the main outcome measure. Compared to the ECP strategy, the base-case analysis shows that the AI strategy results in an additional cost of $242 per patient screened to a cost saving of $140 per patient screened, depending on health system size and patient volume. Notably, the AI screening strategy breaks even and demonstrates cost savings when a pediatric endocrine site screens 241 or more patients annually. Autonomous AI-based screening consistently results in more patients screened with greater cost savings in most health system scenarios.