Deep learning versus ophthalmologists for screening for glaucoma on fundus examination: A systematic review and meta-analysis - PubMed Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Meta-Analysis
. 2021 Dec;49(9):1027-1038.
doi: 10.1111/ceo.14000. Epub 2021 Sep 22.

Deep learning versus ophthalmologists for screening for glaucoma on fundus examination: A systematic review and meta-analysis

Mathieu Buisson  1 , Valentin Navel  1   2 , Antoine Labbé  3   4   5 , Stephanie L Watson  6   7 , Julien S Baker  8 , Patrick Murtagh  9 , Frédéric Chiambaretta  1   2 , Frédéric Dutheil  10
Affiliations
Meta-Analysis

Deep learning versus ophthalmologists for screening for glaucoma on fundus examination: A systematic review and meta-analysis

Mathieu Buisson et al. Clin Exp Ophthalmol. 2021 Dec.

Abstract

Background: In this systematic review and meta-analysis, we aimed to compare deep learning versus ophthalmologists in glaucoma diagnosis on fundus examinations.

Method: PubMed, Cochrane, Embase, ClinicalTrials.gov and ScienceDirect databases were searched for studies reporting a comparison between the glaucoma diagnosis performance of deep learning and ophthalmologists on fundus examinations on the same datasets, until 10 December 2020. Studies had to report an area under the receiver operating characteristics (AUC) with SD or enough data to generate one.

Results: We included six studies in our meta-analysis. There was no difference in AUC between ophthalmologists (AUC = 82.0, 95% confidence intervals [CI] 65.4-98.6) and deep learning (97.0, 89.4-104.5). There was also no difference using several pessimistic and optimistic variants of our meta-analysis: the best (82.2, 60.0-104.3) or worst (77.7, 53.1-102.3) ophthalmologists versus the best (97.1, 89.5-104.7) or worst (97.1, 88.5-105.6) deep learning of each study. We did not retrieve any factors influencing those results.

Conclusion: Deep learning had similar performance compared to ophthalmologists in glaucoma diagnosis from fundus examinations. Further studies should evaluate deep learning in clinical situations.

Keywords: artificial intelligence; deep learning; glaucoma; machine learning; screening.

PubMed Disclaimer

Similar articles

See all similar articles

Cited by

References

REFERENCES

    1. Tham Y-C, Li X, Wong TY, Quigley HA, Aung T, Cheng C-Y. Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis. Ophthalmology. 2014;121(11):2081-2090.
    1. Hood DC, Raza AS, De Moraes CGV, Liebmann JM, Ritch R. Glaucomatous damage of the macula. Progress Retinal Eye Res. 2013;32:1-21.
    1. Giangiacomo A, Coleman A. The epidemiology of glaucoma. 2009. p. 13-21.
    1. Michelson G, Wärntges S, Hornegger J, Lausen B. The papilla as screening parameter for early diagnosis of glaucoma. Dtsch Arztebl Int août. 2008;105(34-35):583-589.
    1. Weinreb RN, Aung T, Medeiros FA. The pathophysiology and treatment of glaucoma: a review. JAMA. 2014;311(18):1901-1911.

LinkOut - more resources