Dataset Information

Quantification of Fluid Resolution and Visual Acuity Gain in Patients With Diabetic Macular Edema Using Deep Learning: A Post Hoc Analysis of a Randomized Clinical Trial.

ABSTRACT:

Importance

Large amounts of optical coherence tomographic (OCT) data of diabetic macular edema (DME) are acquired, but many morphologic features have yet to be identified and quantified.

Objective

To examine the volumetric change of intraretinal fluid (IRF) and subretinal fluid (SRF) in DME during anti-vascular endothelial growth factor treatment using deep learning algorithms.

Design, setting, and participants

This post hoc analysis of a randomized clinical trial, the Diabetic Retinopathy Clinical Research Network (protocol T), assessed 6945 spectral-domain OCT volume scans of 570 eyes from 570 study participants with DME. The original trial was performed from August 21, 2012, to October 18, 2018. This analysis was performed from December 7, 2017, to January 15, 2020.

Interventions

Participants were treated according to a predefined, standardized protocol with aflibercept, ranibizumab, or bevacizumab with or without deferred laser.

Main outcomes and measures

The association of treatment with IRF and SRF volumes and best-corrected visual acuity (BCVA) during 12 months using deep learning algorithms.

Results

Among the 570 study participants (302 [53%] male; 369 [65%] white; mean [SD] age, 43.4 [12.6] years), the mean fluid volumes in the central 3 mm were 448.6 nL (95% CI, 412.3-485.0 nL) of IRF and 36.9 nL (95% CI, 27.0-46.7 nL) of SRF at baseline and 161.2 nL (95% CI, 135.1-187.4 nL) of IRF and 4.4 nL (95% CI, 1.7-7.1 nL) of SRF at 12 months. The presence of SRF at baseline was associated with a worse baseline BCVA Early Treatment Diabetic Retinopathy Study (ETDRS) score of 63.2 (95% CI, 60.2-66.1) (approximate Snellen equivalent of 20/63 [95% CI, 20/50-20/63]) in eyes with SRF vs 66.9 (95% CI, 65.7-68.1) (approximate Snellen equivalent, 20/50 [95% CI, 20/40-20/50]) without SRF (P < .001) and a greater gain in ETDRS score (0.5; 95% CI, 0.3-0.8) every 4 weeks during follow-up in eyes with SRF at baseline vs 0.4 (95% CI, 0.3-0.5) in eyes without SRF at baseline (P = .02) when adjusted for baseline BCVA. Aflibercept was associated with greater reduction of IRF volume compared with bevacizumab after the first injection (difference, 79.8 nL; 95% CI, 5.3-162.5 nL; P < .001) and every 4 weeks thereafter (difference, 10.4 nL; 95% CI, 0.7-20.0 nL; P = .004). Ranibizumab was associated with a greater reduction of IRF after the first injection compared with bevacizumab (difference, 75.2 nL; 95% CI, 1.4-154.7 nL; P < .001).

Conclusions and relevance

Automated segmentation of fluid in DME revealed that the presence of SRF was associated with lower baseline BCVA but with good response to anti-vascular endothelial growth factor therapy. These automated spectral-domain OCT analyses may be used clinically to assess anatomical change during therapy.

Trial registration

ClinicalTrials.gov Identifier: NCT01627249.

SUBMITTER: Roberts PK

PROVIDER: S-EPMC7378869 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ObjectiveTo compare visual acuity (VA) scores after autorefraction vs manual refraction in eyes of patients with diabetes mellitus and a wide range of VAs.MethodsThe letter score from the Electronic Visual Acuity (EVA) test from the electronic Early Treatment Diabetic Retinopathy Study was measured after autorefraction (AR-EVA score) and after manual refraction (MR-EVA score), which is the research protocol of the Diabetic Retinopathy Clinical Research Network. Testing order was randomized, study participants and VA examiners were masked to refraction source, and a second EVA test using an identical supplemental manual refraction (MR-EVAsuppl score) was performed to determine test-retest variability.ResultsIn 878 eyes of 456 study participants, the median MR-EVA score was 74 (Snellen equivalent, approximately 20/32). The spherical equivalent was often similar for manual refraction and autorefraction (median difference, 0.00; 5th-95th percentile range, -1.75 to 1.13 diopters). However, on average, the MR-EVA scores were slightly better than the AR-EVA scores, across the entire VA range. Furthermore, the variability between the AR-EVA scores and the MR-EVA scores was substantially greater than the test-retest variability of the MR-EVA scores (P < .001). The variability of differences was highly dependent on the autorefractor model.ConclusionsAcross a wide range of VAs at multiple sites using a variety of autorefractors, VA measurements tend to be worse with autorefraction than manual refraction. Differences between individual autorefractor models were identified. However, even among autorefractor models that compare most favorably with manual refraction, VA variability between autorefraction and manual refraction is higher than the test-retest variability of manual refraction. The results suggest that, with current instruments, autorefraction is not an acceptable substitute for manual refraction for most clinical trials with primary outcomes dependent on best-corrected VA.

Project description:ImportanceComparisons of the relative effect of 3 anti-vascular endothelial growth factor agents to treat diabetic macular edema warrant further assessment.ObjectiveTo provide additional outcomes from a randomized trial evaluating 3 anti-vascular endothelial growth factor agents for diabetic macular edema within subgroups based on baseline visual acuity (VA) and central subfield thickness (CST) as evaluated on optical coherence tomography.Design, setting, and participantsPost hoc exploratory analyses were conducted of randomized trial data on 660 adults with diabetic macular edema and decreased VA (Snellen equivalent, approximately 20/32 to 20/320). The original study was conducted between August 22, 2012, and August 28, 2013. Analysis was conducted from January 7 to June 2, 2015.InterventionsRepeated 0.05-mL intravitreous injections of 2.0 mg of aflibercept (224 eyes), 1.25 mg of bevacizumab (218 eyes), or 0.3 mg of ranibizumab (218 eyes) as needed per protocol.Main outcomes and measuresOne-year VA and CST outcomes within prespecified subgroups based on both baseline VA and CST thresholds, defined as worse (20/50 or worse) or better (20/32 to 20/40) VA and thicker (≥400 µm) or thinner (250 to 399 µm) CST.ResultsIn the subgroup with worse baseline VA (n = 305), irrespective of baseline CST, aflibercept showed greater improvement than bevacizumab or ranibizumab for several VA outcomes. In the subgroup with better VA and thinner CST at baseline (61-73 eyes across 3 treatment groups), VA outcomes showed little difference between groups; mean change was +7.2, +8.4, and +7.6 letters in the aflibercept, bevacizumab, and ranibizumab groups, respectively. However, in the subgroup with better VA and thicker CST at baseline (31-43 eyes), there was a suggestion of worse VA outcomes in the bevacizumab group; mean change from baseline to 1 year was +9.5, +5.4, and +9.5 letters in the aflibercept, bevacizumab, and ranibizumab groups, respectively, and VA letter score was greater than 84 (approximately 20/20) in 21 of 33 (64%), 7 of 31 (23%), and 21 of 43 (49%) eyes, respectively. The adjusted differences and 95% CIs were 39% (17% to 60%) for aflibercept vs bevacizumab, 25% (5% to 46%) for ranibizumab vs bevacizumab, and 13% (-8% to 35%) for aflibercept vs ranibizumab.Conclusions and relevanceThese post hoc secondary findings suggest that for eyes with better initial VA and thicker CST, some VA outcomes may be worse in the bevacizumab group than in the aflibercept and ranibizumab groups. Given the exploratory nature of these analyses and the small sample size within subgroups, caution is suggested when using the data to guide treatment considerations for patients.Trial registrationclinicaltrials.gov Identifier: NCT01627249.