Investigative Ophthalmology & Visual Science Cover Image for Volume 65, Issue 7
June 2024
Volume 65, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2024
Machine Learning Identifies Visual Disparities in Non-Arteritic Anterior Ischemic Optic Neuropathy at Presentation Between White and Asian Populations
Author Affiliations & Notes
  • Joseph Branco
    Ophthalmology, New York Medical College, Valhalla, New York, United States
  • David Szanto
    Neurology, Icahn School of Medicine at Mount Sinai, New York City, New York, United States
  • Brian Woods
    Irish Clinical Academic Programme, Galway University Hospitals, Galway, Ireland
  • Jui-Kai Wang
    Iowa City VA Center for the Prevention and Treatment of Visual Loss, Iowa City, Iowa, United States
  • Tobias Elze
    Schepens Eye Research Institute of Massachusetts Eye and Ear, Boston, Massachusetts, United States
  • Mona K Garvin
    Department of Electrical and Computer Engineering, University of Iowa Center for the Prevention and Treatment of Visual Loss, Iowa City, Iowa, United States
    Iowa City VA Center for the Prevention and Treatment of Visual Loss, Iowa City, Iowa, United States
  • Louis R. Pasquale
    Icahn School of Medicine at Mount Sinai Department of Ophthalmology, New York, New York, United States
  • Randy H Kardon
    Iowa City VA Center for the Prevention and Treatment of Visual Loss, Iowa City, Iowa, United States
    Ophthalmology and Visual Sciences, University of Iowa Hospitals and Clinics, University Of Iowa, Iowa City, Iowa, United States
  • Mark J Kupersmith
    Neurology, Icahn School of Medicine at Mount Sinai, New York City, New York, United States
  • Asala Erekat
    Neurology, Icahn School of Medicine at Mount Sinai, New York City, New York, United States
  • Footnotes
    Commercial Relationships   Joseph Branco None; David Szanto None; Brian Woods None; Jui-Kai Wang None; Tobias Elze Genentech Inc. , Code F (Financial Support); Mona Garvin University of Iowa, Code P (Patent); Louis Pasquale Twenty Twenty Inc., Code C (Consultant/Contractor), Skye Biosciences, Code C (Consultant/Contractor); Randy Kardon None; Mark Kupersmith None; Asala Erekat None
  • Footnotes
    Support  New York Eye and Ear Infirmary Foundation, Shulman Family, NAION Fund
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 6178. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Joseph Branco, David Szanto, Brian Woods, Jui-Kai Wang, Tobias Elze, Mona K Garvin, Louis R. Pasquale, Randy H Kardon, Mark J Kupersmith, Asala Erekat; Machine Learning Identifies Visual Disparities in Non-Arteritic Anterior Ischemic Optic Neuropathy at Presentation Between White and Asian Populations. Invest. Ophthalmol. Vis. Sci. 2024;65(7):6178.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : Non-arteritic anterior ischemic optic neuropathy (NAION) causes patterns of visual field (VF) loss typical of anterior optic nerve injury. Recently, archetypal analysis (AA) showed quantification of these patterns (archetypes, AT) is possible, providing a potential to monitor changes and compare group data. Due to potential differences in the optic nerve head structure, we hypothesize that AA may show a difference in the patterns of NAION VF loss between White and Asian races.

Methods : We created an AA model from 3157 VFs (24-2, stimuli size III and V) from 728 study eyes from participants of all races aged 50-80 across eight countries in the QRK 207 NAION study. We cross-sectionally analyzed the 716 study eyes with stimulus size III VFs at presentation by self-reported race, examining AT relative weights (RW, total weight = 100%) of 567 White and 149 Asian participants. We compared differences in RW between the two groups with a Mann-Whitney U-test.

Results : At presentation, Asians had worse best corrected visual acuity (letter score, 58.2 ± 19.9, p < 0.001) than Whites (68.6 ± 21.1) and worse average total deviation (TD) for stimulus size III VFs (-20.9 ± 6.4, p < 0.001) than Whites (-15.5 ± 6.7). We found significant differences in the RWs of six ATs, with Asians having a higher RW for more severe ATs. AT1, a pattern of severe diffuse loss, was greater in Asians than Whites (RW 24% vs.12%, (p < 0.001), as were AT2, a pattern of inferior altitudinal loss (RW 26% vs 19%, p < 0.001) and AT4, a pattern of severe loss outside of the blind spot (RW 7.3% vs 5.6%, p = 0.01). Conversely, Asians had a lower RW for ATs with less severe loss including AT3, a pattern of mild diffuse loss (RW 5.5% vs. 13%, p < 0.001), AT5, a pattern of partial inferior altitudinal loss (RW 5.0% vs. 10%, p < 0.001), and AT8, a pattern of inferonasal quadrantanopia (RW 5.5% vs. 7.8%, p = 0.02).

Conclusions : AA revealed significant differences in VF patterns at presentation between White and Asian patients with NAION. VFs of Asian patients at presentation are likely to have higher RWs for AT patterns of more severe loss.

This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.

 

Figure 1. Ten archetypes for combined stimuli III and V visual fields. The average total deviation and relative weight values are shown. The color-coded scale represents total deviation.

Figure 1. Ten archetypes for combined stimuli III and V visual fields. The average total deviation and relative weight values are shown. The color-coded scale represents total deviation.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×