You are here

Article Text

Article menu
Download PDFPDF
Glaucoma
Prediction of visual field progression with serial optic disc photographs using deep learning
  1. Vahid Mohammadzadeh1,
  2. Sean Wu2,
  3. Tyler Davis3,
  4. Arvind Vepa3,
  5. Esteban Morales1,
  6. Sajad Besharati1,
  7. Kiumars Edalati1,4,
  8. Jack Martinyan1,5,
  9. Mahshad Rafiee1,
  10. Arthur Martynian1,
  11. Fabien Scalzo3,
  12. Joseph Caprioli1,
  13. Kouros Nouri-Mahdavi1,6
  1. 1 Department of Ophthalmology, Jules Stein Eye Institute, UCLA, Los Angeles, California, USA
  2. 2 Department of Computer Science, Pepperdine University, Malibu, California, USA
  3. 3 Department of Computer Science, University of California Los Angeles, Los Angeles, California, USA
  4. 4 Department of Ophthalmology, Jules Stien Eye Institute, UCLA, Los Angeles, California, USA
  5. 5 University of California Los Angeles, Sherman Oaks, California, USA
  6. 6 Ophthalmology, UCLA Jules Stein Eye Institute, Los Angeles, California, USA
  1. Correspondence to Dr Kouros Nouri-Mahdavi, Ophthalmology, UCLA Jules Stein Eye Institute, Los Angeles, CA 90095, USA; nouri-mahdavi{at}jsei.ucla.edu

Abstract

Aim We tested the hypothesis that visual field (VF) progression can be predicted with a deep learning model based on longitudinal pairs of optic disc photographs (ODP) acquired at earlier time points during follow-up.

Methods 3919 eyes (2259 patients) with ≥2 ODPs at least 2 years apart, and ≥5 24–2 VF exams spanning ≥3 years of follow-up were included. Serial VF mean deviation (MD) rates of change were estimated starting at the fifth visit and subsequently by adding visits until final visit. VF progression was defined as a statistically significant negative slope at two consecutive visits and final visit. We built a twin-neural network with ResNet50-backbone. A pair of ODPs acquired up to a year before the VF progression date or the last VF in non-progressing eyes were included as input. Primary outcome measures were area under the receiver operating characteristic curve (AUC) and model accuracy.

Results The average (SD) follow-up time and baseline VF MD were 8.1 (4.8) years and –3.3 (4.9) dB, respectively. VF progression was identified in 761 eyes (19%). The median (IQR) time to progression in progressing eyes was 7.3 (4.5–11.1) years. The AUC and accuracy for predicting VF progression were 0.862 (0.812–0.913) and 80.0% (73.9%–84.6%). When only fast-progressing eyes were considered (MD rate < –1.0 dB/year), AUC increased to 0.926 (0.857–0.994).

Conclusions A deep learning model can predict subsequent glaucoma progression from longitudinal ODPs with clinically relevant accuracy. This model may be implemented, after validation, for predicting glaucoma progression in the clinical setting.

  • Glaucoma
  • Field of vision
  • Optic Nerve
  • Imaging

Data availability statement

No data are available.

https://doi.org/10.1136/bjo-2023-324277

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    Data availability statement

    No data are available.

    View Full Text

    Footnotes

    • Presented at Presented as a paper at the American Glaucoma Society Annual meeting, March 2–5, 2023 (Austin TX) and the World Glaucoma Congress meeting, Rome, Italy, June 2023.

    • Contributors VM: involved in design and conduct of study, data collection, analysis and interpretation of data, writing, critical revision, approval of the manuscript. SW: involved in design and conduct of study, analysis and interpretation of data, writing, critical revision. TD: involved in design and conduct of study, analysis and interpretation of data, writing, critical revision. AV: involved in design and conduct of study, writing, critical revision. EM: data collection, writing. SB: data collection, writing. KE: data collection, writing. JM: data collection, writing. MR: data collection, writing. AM: data collection, writing. FS: involved in design and conduct of study, analysis and interpretation of data, writing, critical revision, approval of the manuscript. JC: involved in design and conduct of study, analysis and interpretation of data, writing, critical revision, approval of the manuscript. KNM: involved in design and conduct of study, data collection, analysis and interpretation of data, writing, critical revision, approval of the manuscript, guarantor of work.

    • Funding This work was supported by an NIH R01 grant (R01-EY029792, KNM) and an unrestricted Departmental Grant from Research to Prevent Blindness.

    • Disclaimer The funding organisations had no role in the design or conduct of this research.

    • Competing interests None declared.

    • Provenance and peer review Not commissioned; externally peer reviewed.

    • Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.

    Linked Articles

    • Highlights from this issue
      At a glance
      Frank Larkin
      British Journal of Ophthalmology 2024; 108 i-ii Published Online First: 23 Jul 2024. doi: 10.1136/bjo-2024-326086