Search

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.

IMPORTANCE: Better understanding of primary open-angle glaucoma (POAG) genetics could enable timely screening and promote individualized disease risk prognostication. OBJECTIVE: To evaluate phenotypic features across genetic burden for POAG. DESIGN, SETTING, AND PARTICIPANTS: This was a cross-sectional, population-based study conducted from 2006 to 2010. Included participants were individuals from the UK Biobank aged 40 to 69 years. Individuals with non-POAG forms of glaucoma were excluded from the analysis. Data were statistically analyzed from October 2022 to January 2023. MAIN OUTCOMES AND MEASURES: POAG prevalence based on structural coding, self-reports, and glaucoma-related traits. RESULTS: Among 407 667 participants (mean [SD] age, 56.3 [8.1] years; 219 183 majority sex [53.8%]) were 14 171 POAG cases. Area under receiver operating characteristic curve for POAG detection was 0.748 in a model including polygenic risk score (PRS), age, sex, and ancestry. POAG prevalence in the highest decile of PRS was 7.4% (3005 of 40 644) vs 1.3% (544 of 40 795) in lowest decile (P < .001). A 1-SD increase in PRS was associated with 1.74 times higher odds of POAG (95% CI, 1.71-1.77), a 0.61-mm Hg increase in corneal-compensated intraocular pressure (IOP; 95% CI, 0.59-0.64), a −0.09-mm Hg decrease in corneal hysteresis (95% CI, −0.10 to −0.08), a 0.08-mm Hg increase in corneal resistance factor (95% CI, 0.06-0.09), and a −0.08-diopter decrease in spherical equivalent (95% CI, −0.11 to −0.07; P < .001 for all). A 1-SD increase in PRS was associated with a thinning of the macula-region retinal nerve fiber layer (mRNFL) of 0.14 μm and macular ganglion cell complex (GCC) of 0.26 μm (P < .001 for both). In the subset of individuals with fundus photographs, a 1-SD increase in PRS was associated with 1.42 times higher odds of suspicious optic disc features (95% CI, 1.19-1.69) and a 0.013 increase in cup-disc ratio (CDR; 95% CI, 0.012-0.014; P < .001 for both). A total of 22 of 5193 fundus photographs (0.4%) in decile 10 had disc hemorrhages, and 27 of 5257 (0.5%) had suspicious optic disc features compared with 9 of 5158 (0.2%) and 10 of 5219 (0.2%), respectively, in decile 1 (P < .001 for both). CDR in decile 10 was 0.46 compared with 0.41 in decile 1 (P < .001). CONCLUSION AND RELEVANCE: Results suggest that PRS identified a group of individuals at substantially higher risk for POAG. Higher genetic risk was associated with more advanced disease, namely higher CDR and corneal-compensated IOP, thinner mRNFL, and thinner GCC. Associations with POAG PRS and corneal hysteresis and greater prevalence of disc hemorrhages were identified. These results suggest that genetic risk is an increasingly important parameter for risk stratification to consider in clinical practice.

Background/objectives: This study aims to describe the grading methods and baseline characteristics for UK Biobank (UKBB) participants who underwent retinal imaging in 2009–2010, and to characterise individuals with retinal features suggestive of age-related macular degeneration (AMD), glaucoma and retinopathy. Methods: Non-mydriatic colour fundus photographs and macular optical coherence tomography (OCT) scans were manually graded by Central Administrative Research Facility certified graders and quality assured by clinicians of the Network of Ophthalmic Reading Centres UK. Captured retinal features included those associated with AMD (≥1 drusen, pigmentary changes, geographic atrophy or exudative AMD; either imaging modality), glaucoma (≥0.7 cup-disc ratio, ≥0.2 cup-disc ratio difference between eyes, other abnormal disc features; photographs only) and retinopathy (characteristic features of diabetic retinopathy with or without microaneurysms; either imaging modality). Suspected cases of these conditions were characterised with reference to diagnostic records, physical and biochemical measurements. Results: Among 68,514 UKBB participants who underwent retinal imaging, the mean age was 57.3 years (standard deviation 8.2), 45.7% were men and 90.6% were of White ethnicity. A total of 64,367 participants had gradable colour fundus photographs and 68,281 had gradable OCT scans in at least one eye. Retinal features suggestive of AMD and glaucoma were identified in 15,176 and 2184 participants, of whom 125 (0.8%) and 188 (8.6%), respectively, had a recorded diagnosis. Of 264 participants identified to have retinopathy with microaneurysms, 251 (95.1%) had either diabetes or hypertension. Conclusions: This dataset represents a valuable addition to what is currently available in UKBB, providing important insights to both ocular and systemic health.

Background: Diabetic eye screening programmes have been developed worldwide based on evidence that early detection and treatment of diabetic retinopathy are crucial to preventing sight loss. However, little is known about the decision-making processes and training needs of diabetic retinal graders, particularly in low- and middle-income countries. Objectives: To provide data for improving evidence-based diabetic retinopathy training to help novice graders process fundus images more like experts. Subjects/methods: This is a mixed-methods qualitative study conducted in southern Vietnam and Northern Ireland. Novice diabetic retinal graders in Vietnam (n= 18) and expert graders in Northern Ireland (n= 5) were selected through a purposive sampling technique. Data were collected from 21st February to 3rd September 2019. The interviewer used neutral prompts during think-aloud sessions to encourage participants to verbalise their thought processes while grading fundus images from anonymised patients, followed by semi-structured interviews. Thematic framework analysis was used to identify themes, supported by illustrative quotes from interviews. Mann–Whitney Utests were used to compare graders’ performance. Results: Expert graders used a more systematic approach when grading images, considered all four images per patient and used available software tools such as red-free filters prior to making a decision on management. The most challenging features for novice graders were intra-retinal microvascular abnormalities and new vessels, which were more accurately identified by experts. Conclusion: Taking more time to grade fundus images and adopting a protocol-driven “checklist” approach may help novice graders to function more like experts.

Purpose To evaluate the reproducibility of SIMPLE (Single field Image Multi Parameters defined Lesions Extent), a new Diabetic Retinopathy (DR) classification for screening of 45° single field fundus pictures of patients with diabetes (PwDM), assessing DR, Diabetic Maculopathy (DMac) and referral rate agreement and comparing it to current Italian Guidelines (IG).Materials and methods We conducted a retrospective, observational, multicentre study, collecting 1000 retinal 45° single field images of PwDM obtained during routine visits in two diabetes clinics. Three ophthalmologists evaluated each image, determining the presence and number of specific DR lesions and then assigning a stage according to the current IG for screening. SIMPLE staging was performed automatically via Excel software, based on the pre-specified DR characteristics observed by the graders. We analysed intra-centre, inter-centre and total inter-grader agreement for DR and DMac stage and referral rate of the two classifications.Results Agreement amongst the three graders was consistently higher when using SIMPLE classification than when using current IG classification. For DR, kappa (k) was 0.86 with IG and 0.95 with SIMPLE classification; for DMac, k-IG was 0.78, while k-SIMPLE was 0.96; concordance on the referral rate was 0.91 with IG and 0.99 with SIMPLE. Similar results were obtained in sub-analyses for the evaluation of intra-centre and inter-centre concordance.Conclusions Our results suggest that the new SIMPLE classification has an excellent reproducibility amongst graders, comparable or superior to the current IG for DR screening proposed in 2015, improving the standardisation of the decision on referability.

Out-standing! art by Katie Curran, 7 What do baseball players do when they get hot? They stand by their fans! Andrew Forsberg, 7 Cape Cod, [...]

What place loves tennis the most? Tennessee! Renee Murray Merrimack, New Hampshire What do you call a seagull flying over a bay? A bay-gull (bagel)! Liana Slomka, 7 Atlanta, Georgia [...]

The article discusses the significance of goal setting and hope theory among school-age children. Choosing goals that are essential to the individual and one that he or she can readily achieve is critical in and outside the classroom. Goals may lead to positive outcomes since they are energizing and they tend to increase the effort toward performance. Hope theory is considered fundamental to goal accomplishment.

The article offers the author's views about Travel for Teens summer program for students.

Comments on the finding that most New Hampshire voters and politicians do not want to hear negative advertising about their opponents. New Hampshire politicians' decision not to use negative advertising; Effectiveness of a positive approach in dealing with the competition; Arguments against negative advertising.