Retrospective Evaluation of a Teleretinal Screening Program in Detecting Multiple Nondiabetic Eye Diseases

Maa, April Y.; Patel, Shivangi; Chasan, Joel E.; Delaune, William; Lynch, Mary G.

doi:10.1089/tmj.2016.0039

Cited by 26 publications

(25 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the past two decades, nonmydriatic fundus photographs have been widely and effectively employed to screen for diabetic retinopathy via teleophthalmology. 6,7 However, the use of optic disc photos for glaucoma screening has been limited by the dependence on human graders. Manual review of disc photographs is not only time-consuming, but also highly subjective.…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning Algorithm to Quantify Neuroretinal Rim Loss From Optic Disc Photographs

Thompson

Jammal

Medeiros

2019

American Journal of Ophthalmology

View full text Add to dashboard Cite

Purpose: To train a deep learning (DL) algorithm that quantifies glaucomatous neuroretinal damage on fundus photographs using the minimum rim width relative to Bruch's membrane opening (BMO-MRW) from spectral domain-optical coherence tomography (SDOCT). Design: Cross-sectional study Methods: 9,282 pairs of optic disc photographs and SDOCT optic nerve head scans from 927 eyes of 490 subjects were randomly divided into the validation plus training (80%) and test sets (20%). A DL convolutional neural network was trained to predict the SDOCT BMO-MRW global and sector values when evaluating optic disc photographs. The predictions of the DL network were compared to the actual SDOCT measurements. The area under the receiver operating curve (AUC) was used to evaluate the ability of the network to discriminate glaucomatous visual field loss from normal eyes. Results: The DL predictions of global BMO-MRW from all optic disc photos in the test set (mean ± standard deviation [SD]: 228.8±63.1μm) were highly correlated with the observed values from SDOCT (mean ± SD: 226.0±73.8μm) (Pearson's r=0.88; R 2 =77%; P<0.001), with mean absolute error of the predictions of 27.8μm. The AUCs for discriminating glaucomatous from healthy eyes with the DL predictions and actual SDOCT global BMO-MRW measurements were 0.945 (95% CI:0.874-0.980) and 0.933 (95% CI:0.856-0.975), respectively (P=0.587). Conclusions: A DL network can be trained to quantify the amount of neuroretinal damage on optic disc photographs using SDOCT BMO-MRW as a reference. This algorithm showed high accuracy for glaucoma detection, and may potentially eliminate the need for human gradings of disc photos.

show abstract

Section: Introductionmentioning

confidence: 99%

A Deep Learning Algorithm to Quantify Neuroretinal Rim Loss From Optic Disc Photographs

Thompson

Jammal

Medeiros

2019

American Journal of Ophthalmology

View full text Add to dashboard Cite

show abstract

“…Furthermore, teleophthalmology can provide significant savings in time and travel expenses for patients, which could be the reason why it was mostly preferred by the younger population of patients, who may have busier schedules. Previous studies found good agreement between the diagnosis and management decisions by teleophthalmology compared to the diagnosis and management decisions in eye clinics 2,5,6,11,12. This is mostly because diagnostic imaging and measurements play an important role in ophthalmology4 and these can be easily transferred via telemedicine and help in making a diagnosis or deciding on the suitability of candidates for surgery.…”

Section: Discussionmentioning

confidence: 91%

Informed consent in refractive surgery: in-person vs telemedicine approach

Schallhorn

Hannan²,

Teenan³

et al. 2018

OPTH

View full text Add to dashboard Cite

PurposeThe aim of this study was to compare the quality of consent process in refractive surgery between patients who had a preoperative consent discussion with the surgeon using a telemedicine approach and those who had a face-to-face discussion.MethodsPatients treated between January and December 2017 (8,184 laser vision correction [LVC] and 3,754 refractive lens exchange [RLE] patients) that attended day 1 and 1-month postoperative visit were retrospectively reviewed. Preoperative consent preparation included a consultation with an optometrist, observation of an educational video, and written information. Patients then selected either a face-to-face appointment with their surgeon (in-clinic group) or a telemedicine appointment (remote group) for their consent discussion, according to their preference. Patient experience questionnaire and clinical data were included in a multivariate model to explore factors associated with consent quality.ResultsPrior to surgery, 80.1% of LVC and 47.9% of RLE patients selected remote consent. Of all LVC patients, 97.5% of in-clinic and 98.3% of remote patients responded that they were adequately consented for surgery (P=0.04). Similar percentages in the RLE group were 97.6% for in-clinic and 97.9% for remote patients (P=0.47). In a multivariate model, the major predictor of patient’s satisfaction with the consent process was postoperative satisfaction with visual acuity, responsible for 80.4% of variance explained by the model. Other significant contributors were postoperative visual phenomena and dry eyes, difficulty with night driving, close-up and distance vision, postoperative uncorrected distance visual acuity, change in corrected distance visual acuity, and satisfaction with the surgeon’s approach. The type of consent (remote or in-clinic) had no impact on patient’s perception of consent quality in the regression model.ConclusionThe majority of patients opted for telemedicine-assisted consent. Those who chose it were equally satisfied as those who had a face-to-face meeting with their surgeon. Dissatisfaction with surgical outcome was the major factor affecting patient’s perception of consent quality, regardless of the method of their consent.

show abstract

“…Unlike DR, there is no consensus about the utility of population screening for AMD. 288 Some groups have found value by adding screening for AMD to existing DR screening programs, 289,290 but others have not found screening programs for AMD to be cost-effective. 291 Several groups have investigated the feasibility and validity of telehealth programs for AMD.…”

Section: Discussionmentioning

confidence: 99%

Practice Guidelines for Ocular Telehealth-Diabetic Retinopathy, Third Edition

Horton

Brady

Cavallerano

et al. 2020

Telemedicine and e-Health

View full text Add to dashboard Cite

The following document and appendices represent the third edition of the Practice Guidelines for Ocular Telehealth-Diabetic Retinopathy. These guidelines were developed by the Diabetic Retinopathy Telehealth Practice Guidelines Working Group. This working group consisted of a large number of subject matter experts in clinical applications for telehealth in ophthalmology. The editorial committee consisted of Mark B. Horton, OD, MD, who served as working group chair and Christopher J. Brady, MD, MHS, and Jerry Cavallerano, OD, PhD, who served as cochairs. The writing committees were separated into seven different categories. They are as follows:

show abstract

Retrospective Evaluation of a Teleretinal Screening Program in Detecting Multiple Nondiabetic Eye Diseases

Abstract: It may be feasible to use diabetic teleretinal photographs to screen patients for other potential eye diseases. Additional elements of the eye workup may be added to enhance accuracy of disease detection. Further study is necessary to confirm this initial retrospective review.

Cited by 26 publications

References 34 publications

A Deep Learning Algorithm to Quantify Neuroretinal Rim Loss From Optic Disc Photographs

A Deep Learning Algorithm to Quantify Neuroretinal Rim Loss From Optic Disc Photographs

Informed consent in refractive surgery: in-person vs telemedicine approach

Practice Guidelines for Ocular Telehealth-Diabetic Retinopathy, Third Edition

Contact Info

Product

Resources

About