Lucy Mudie

Crowdsourcing: an overview and applications to ophthalmology

Purpose of review Crowdsourcing involves the use of the collective intelligence of online communities to produce solutions and outcomes for defined objectives. The use of crowdsourcing is growing in many scientific areas. Crowdsourcing in ophthalmology has been used in basic science and clinical research; however, it also shows promise as a method with wide-ranging applications. This review presents current findings on the use of crowdsourcing in ophthalmology and potential applications in the future. Recent findings Crowdsourcing has been used to distinguish normal retinal images from images with diabetic retinopathy; the collective intelligence of the crowd was able to correctly classify 81% of 230 images (19 unique) for US

Optimizing glaucoma screening in high risk population: design and 1-year findings of the Screening to Prevent (SToP) Glaucoma study

1.10/eye in 20u200amin. Crowdsourcing has also been used to distinguish normal optic discs from abnormal ones with reasonable sensitivity (83–88%), but low specificity (35–43%). Another study used crowdsourcing for quick and reliable manual segmentation of optical coherence tomography images. Outside of ophthalmology, crowdsourcing has been used for text and image interpretation, language translation, and data analysis. Summary Crowdsourcing has the potential for rapid and economical data processing. Among other applications, it could be used in research settings to provide the ‘ground-truth’ data, and in the clinical settings to relieve the burden of image processing on experts.

Crowdsourcing and Automated Retinal Image Analysis for Diabetic Retinopathy

PURPOSEnTo develop, implement, and evaluate a replicable community-based screening intervention designed to improve glaucoma and other eye disease detection and follow-up care in high-risk populations in the United States. We present the design of the study and describe the findings of the first year of the program.nnnDESIGNnProspective study to evaluate screening and follow-up.nnnMETHODSnThis is an ongoing study to develop an eye screening program using trained personnel to identify individuals with ophthalmic needs, focusing on African Americans ≥50 years of age at multiple inner-city community sites in Baltimore, Maryland. The screening examination uses a sequential referral approach and assesses presenting visual acuity (VA), best-corrected VA, digital fundus imaging, visual field testing, and measurement of intraocular pressure.nnnRESULTSnWe screened 901 individuals between January 2015 and October 2015. Subjects were mostly African Americans (94.9%) with a mean (standard deviation) age of 64.3 (9.9) years. Among them, 356 (39.5%) participants were referred for a definitive eye examination and 107 (11.9%) only needed prescription glasses. The most common reasons for referral were ungradable fundus image (39.3% of those referred), best-corrected VA < 20/40 (14.6%), and ungradable autorefraction (11.8%). Among people referred for definitive examination, 153 (43%) people attended their scheduled examination. The most common diagnoses at the definitive examination were glaucoma and cataract (51% and 40%, respectively).nnnCONCLUSIONSnA large proportion of individuals screened required ophthalmic services, particularly those who were older and less well educated. To reach and encourage these individuals to attend screenings and follow-up examinations, programs could develop innovative strategies and approaches.

Uncontrolled Hypertension Is Common in Glaucoma Clinics

Purpose of ReviewAs the number of people with diabetic retinopathy (DR) in the USA is expected to increase threefold by 2050, the need to reduce health care costs associated with screening for this treatable disease is ever present. Crowdsourcing and automated retinal image analysis (ARIA) are two areas where new technology has been applied to reduce costs in screening for DR. This paper reviews the current literature surrounding these new technologies.Recent FindingsCrowdsourcing has high sensitivity for normal vs abnormal images; however, when multiple categories for severity of DR are added, specificity is reduced. ARIAs have higher sensitivity and specificity, and some commercial ARIA programs are already in use. Deep learning enhanced ARIAs appear to offer even more improvement in ARIA grading accuracy.SummaryThe utilization of crowdsourcing and ARIAs may be a key to reducing the time and cost burden of processing images from DR screening.

Baltimore Reading and Eye Disease Study (BREDS): two-year results on compliance with eyeglass usage

BACKGROUNDnTo determine the magnitude of uncontrolled hypertension and smoking among patients visiting an eye clinic, and ascertain if referral to care providers is effective.nnnMETHODSnInformation on smoking status and blood pressure (BP) was collected among patients ≥18 years visiting an eye clinic. Those with high BP (systolic: ≥140 mm Hg and/or diastolic: ≥90 mm Hg) received a pamphlet on harms of hypertension on vision and were referred to a primary care physician. Smokers received a pamphlet on negative effects of smoking on vision and were offered referral to a tobacco quitline. Patients were followed up for referral outcome within 10 weeks from screening.nnnRESULTSnScreening: A total of participants screened included 140 (29.5%) with high BP and 31 (6.6%) current smokers. In the high BP group, 92 (66%) subjects were previously diagnosed with hypertension. Follow-up: Of the 140 participants with elevated BP, 84 (60%) responded to follow-up. Among these 84 participants, 57 (67.9%) had consulted primary care, of whom 5 (8.8%) reported being newly diagnosed with hypertension, and 11 (19.3%) reported a change in their antihypertensive prescription. Among the 31 smokers, 24 (77.4%) were willing for quitline referral. Sixteen (66.7%) of these patients responded to follow-up, 8 (50%) of whom reported participation in a smoking-cessation program with 1 patient (6.3%) successfully quitting smoking.nnnCONCLUSIONSnNearly one-third of patients attending an eye clinic had elevated BP, and a smaller, but substantial, number of patients were current smokers. Eye clinics may serve as point for identification and referral of these patients with unmet needs.