June 2017
Volume 58, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2017
Predicting Age-related Changes with High Accuracy using a Pattern Recognition Derived Retinal Ganglion Cell Regression Model
Author Affiliations & Notes
  • Nayuta Yoshioka
    Centre for Eye Health, University of New South Wales Australia, Kensington, New South Wales, Australia
    School of Optometry and Vision Science, University of New South Wales Australia, Sydney, New South Wales, Australia
  • Barbara Zangerl
    Centre for Eye Health, University of New South Wales Australia, Kensington, New South Wales, Australia
    School of Optometry and Vision Science, University of New South Wales Australia, Sydney, New South Wales, Australia
  • Lisa Nivison-Smith
    Centre for Eye Health, University of New South Wales Australia, Kensington, New South Wales, Australia
    School of Optometry and Vision Science, University of New South Wales Australia, Sydney, New South Wales, Australia
  • Sieu Khuu
    School of Optometry and Vision Science, University of New South Wales Australia, Sydney, New South Wales, Australia
  • Bryan W Jones
    Department of Ophthalmology, Moran Eye Center, University of Utah, Salt Lake City, Utah, United States
  • Rebecca L Pfeiffer
    Department of Ophthalmology, Moran Eye Center, University of Utah, Salt Lake City, Utah, United States
  • Robert E Marc
    Department of Ophthalmology, Moran Eye Center, University of Utah, Salt Lake City, Utah, United States
  • Michael Kalloniatis
    Centre for Eye Health, University of New South Wales Australia, Kensington, New South Wales, Australia
    School of Optometry and Vision Science, University of New South Wales Australia, Sydney, New South Wales, Australia
  • Footnotes
    Commercial Relationships   Nayuta Yoshioka, None; Barbara Zangerl, None; Lisa Nivison-Smith, None; Sieu Khuu, None; Bryan Jones, None; Rebecca Pfeiffer, None; Robert Marc, None; Michael Kalloniatis, None
  • Footnotes
    Support  NHMRC 1033224; UNSW ECR Grant 2016 P535430; Australian Postgraduate Award; Guide Dogs NSW/ACT is a partner in the NHMRC grant and also provided a supplementary PhD scholarship for NY and support for LN-S; NIH EY02576, EY015128, EY014800, to Prevent Blindness Unrestricted Grant
Investigative Ophthalmology & Visual Science June 2017, Vol.58, 658. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to Subscribers Only
      Sign In or Create an Account ×
    • Get Citation

      Nayuta Yoshioka, Barbara Zangerl, Lisa Nivison-Smith, Sieu Khuu, Bryan W Jones, Rebecca L Pfeiffer, Robert E Marc, Michael Kalloniatis; Predicting Age-related Changes with High Accuracy using a Pattern Recognition Derived Retinal Ganglion Cell Regression Model. Invest. Ophthalmol. Vis. Sci. 2017;58(8):658.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : We recently used pattern recognition analysis to show macula areas can be classified into statistically distinct clusters in accordance to their age-related retinal ganglion cell layer (RGCL) thickness change in a normal population. The aim of this study was to perform a retrospective cross-sectional analysis utilizing a large cohort of patients to establish accuracy of this model and to develop a normative dataset using a 50-year-old equivalent cohort.

Methods : Data was collected from patients seen at the Centre for Eye Health for optic nerve assessment without posterior pole disease. The grid-wise RGCL thickness was obtained from a single eye of each patient via Spectralis OCT macular scan over an 8×8 measurement grid. Measurements for patients outside the 45-54 age range (training cohort) were converted to 50-year-old equivalent value utilizing pattern recognition derived regression model which, in brief, consists of 8×8 grid clustered into 8 distinct classes according to the pattern of RGCL thickness change with age. Accuracy of the predictions was assessed by comparing the training cohort’s measurements to the 45-54 year reference cohort using t-test and one-way ANOVA.

Results : Data were collected from a total 248 patients aged 20 to 78.1 years. 80 patients within this group were aged 45 – 54 and formed the reference cohort (average±SD 49.6±2.83) and the remaining 168 eyes formed the training cohort (average age±SD 50.7±17.34). Converted values for the training set matched those of the reference cohort (average disparity±SD 0.10±0.42µm, range -0.74-1.34µm) and were not significantly different (p > 0.9). Most variability was observed with patients above 70 years of age (average disparity±SD -0.09±1.73µm, range -3.67 to 6.16µm) and central grids corresponding to the fovea (average disparity±SD 0.47±0.72µm, range -0.22 to 1.34µm).

Conclusions : Our regression model for normal age-related RGCL change can accurately convert and/or predict RGCL thickness for individuals in comparison to 50-year-equivalent reference cohort and could allow for more accurate assessment of RGCL thickness and earlier detection of significant loss in the future. Caution may be needed when applying the model in the foveal area or for patients older than 70 years.

This is an abstract that was submitted for the 2017 ARVO Annual Meeting, held in Baltimore, MD, May 7-11, 2017.

×
×

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.

×