Diagnostic accuracy of a remote eye exam in measuring refractive errors and detecting cataract, glaucoma, and diabetic retinopathy
Moreira, T. D. C.; Pagano, C. G. M.; Chagas, M. E. V.; Falavigna, M.; Rados, D. R. V.; Silva, R. S.; Harzheim, E.; Goncalves, M. R.; Umpierre, R. N.; de Azevedo, P. B.; Waquil, A. P.; Fabris, C.; Lang, M. P. L.; Szortika, A. D.; Szortyka, A.; de Araujo, A. L.; Cabral, F. C.
Show abstract
PorpuseApproximately 2.2 billion people worldwide have some type of visual impairment and among these, many could have been avoided or solved if adequate care had been provided in a timely manner. In these cases, telemedicine can assist in solving the problems of many ophthalmological conditions by providing support, performing screening, telediagnosis or supervision of distant appointments. The use of telemedicine for eye health is well established for some eye diseases, such as diabetic retinopathy, macular diseases and strabismus, however, there is a lack of information on diagnostic accuracy for other ophthalmological pathologies prevalent in the world population, such as refractive errors. To evaluate the reliability of the diagnosis made through teleophthalmology, using the ophthalmologists face-to-face diagnosis as the gold standard. MethodsA diagnostic accuracy study was carried out, with 216 patients assessed by the TeleOftalmo project who underwent eye examinations both on-site and through telemedicine. The patients underwent refraction tests, intraocular pressure measurement, photodocumentation in the slit-lamp and subjective refraction using the visual acuity screen and the digital refractor. ResultsThe conditions evaluated were refractive errors, cataracts, diabetic retinopathy and suspected glaucoma. Kappa values, sensitivity, specificity, positive predictive value and negative predictive value were calculated. Approximately, 61.6% of the sample were women, with mean age of 47 years old. Kappa values show strong reliability regarding the diagnosis of cataracts (k = 0.86) and diabetic retinopathy (k = 0.79). Regarding refractive errors and suspected glaucoma, the kappa values were considered moderate (k = 0.598 and 0.478, respectively). ConclusionThe use of telemedicine has shown favorable results regarding the diagnosis of refractive errors, cataracts and diabetic retinopathy, as well as moderate reliability for suspected glaucoma.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Risk Model for Intraoperative Complication during Cataract Surgery Based on Data from 900,000 Eyes – Previous Intravitreal Injection is a Risk Factor 95%
- Evaluation of the Nallasamy Formula: A Stacking Ensemble Machine Learning Method for Refraction Prediction in Cataract Surgery 95%
- Unveiling the Clinical Incapabilities: A Benchmarking Study of GPT-4V(ision) for Ophthalmic Multimodal Image Analysis 95%
Similar papers in this journal
- Visual field evaluation using Zippy Adaptive Threshold Algorithm (ZATA) Standard and ZATA Fast in patients with glaucoma and healthy individuals 95%
- Visible light optical coherence tomography of peripapillary retinal nerve fiber layer reflectivity in glaucoma 95%
- Low-cost, Smartphone-based Specular Imaging and Automated Analysis of the Corneal Endothelium 95%
Similar papers in this journal
- Prevalence, incidence and risk factors for myopia among urban and rural children in southern China: protocol for a school-based cohort study 96%
- Prevalence and causes of vision impairment in Norwest Portugal: a capture and recapture study 95%
- Functional changes of visual cortex in pre- and post- operative intermittent exotropia patients: study protocol for a non-randomized case-control clinical trial 94%
Similar papers in this journal
- Automated vision screening of children using a mobile graphic device 95%
- Association of renal function with diabetic retinopathy and macular edema among patients with type 2 diabetes mellitus 93%
- An Open-Source Dataset Of Anti-Vegf Therapy In Diabetic Macular Oedema Patients Over Four Years & Their Visual Outcomes 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.