Article Text

Download PDFPDF
Predicting Humphrey 10-2 visual field from 24-2 visual field in eyes with advanced glaucoma
  1. Kenji Sugisaki1,
  2. Ryo Asaoka2,
  3. Toshihiro Inoue3,
  4. Keiji Yoshikawa4,
  5. Akiyasu Kanamori5,
  6. Yoshio Yamazaki6,
  7. Shinichiro Ishikawa7,
  8. Hodaka Nemoto8,
  9. Aiko Iwase9,
  10. Makoto Araie10
  1. 1Ophthalmology, International University of Health and Welfare Mita Hospital, Tokyo, Japan
  2. 2Department of Ophthalmology, University of Tokyo Graduate School of Medicine, Tokyo, Japan
  3. 3Ophthalmology and Visual Science, Kumamoto University, Kumamoto, Japan
  4. 4Ophthalmology, Yoshikawa Eye Clinics, Hashimoto, Japan
  5. 5Division of Ophthalmology, Kobe University Graduate School of Medicine, Kobe, Japan
  6. 6Ophthalmology, Tokai University Tokyo Hospital, Shibuya-ku, Japan
  7. 7Department of Ophthalmology, Saga University Faculty of Medicine, Saga, Japan
  8. 8Department of Ophthalmology, Tokyo Teishin Hospital, Chiyoda-ku, Japan
  9. 9Tajimi Iwase Eye Clinic, Tajimi, Japan
  10. 10Department of Ophthalmology, Kanto Central Hospital of the Mutual Aid Association of Public School Teachers, Setagaya-ku, Japan
  1. Correspondence to Dr Kenji Sugisaki, Ophthalmology, International University of Health and Welfare Mita Hospital, Tokyo 108-8329, Japan; sugisaktky{at}gmail.com

Abstract

Aims To predict Humphrey Field Analyzer Central 10-2 Swedish Interactive Threshold Algorithm-Standard test (HFA 10-2) results (Carl Zeiss Meditec, San Leandro, CA) from HFA 24-2 results of the same eyes with advanced glaucoma.

Methods Training and testing HFA 24-2 and 10-2 data sets, respectively, consisted of 175 eyes (175 patients) and 44 eyes (44 patients) with open advanced glaucoma (mean deviation of HFA 24-2 ≤−20 dB). Using the training data set, the 68 total deviation (TD) values of the HFA 10-2 test points were predicted from those of the innermost 16 HFA 24-2 test points in the same eye, using image processing or various machine learning methods including bilinear interpolation (IP) as a standard for comparison. The absolute prediction error (PredError) was calculated by applying each method to the testing data set.

Results The mean (SD) test–retest variability of the HFA 10-2 results in the testing data set was 2.1±1.0 dB, while the IP method yielded a PredError of 5.0±1.7 dB. Among the methods tested, support vector regression (SVR) provided a smallest PredError (4.0±1.5 dB). SVR predicted retinal sensitivity at HFA 10-2 test points in the preserved ‘central isle’ of advanced glaucoma from HFA 24-2 results of the same eye within an error range of about 25%, while error range was approximately twice of the test–retest variability.

Conclusion Applying SVR to HFA 24-2 results allowed us to predict TD values at HFA 10-2 test points of the same eye with advanced glaucoma with an error range of about 25%.

  • glaucoma
  • field of vision
View Full Text

Statistics from Altmetric.com

Footnotes

  • Contributors KS acquired and analysed data and wrote the manuscript. RA designed the study and analysed data and helped write the manuscript. TI, KY, YY, SI and HN acquired data of each facility. AI is cosupervisor and edited the manuscript. MA is supervisor and edited the manuscript.

  • Funding The authors have not declared a specific grant for this research from any funding agency in the public, commercial or not-for-profit sectors.

  • Competing interests None declared.

  • Patient consent for publication Not required.

  • Ethics approval The study protocol was approved by the ethical review committees of the individual institutes of the authors, registered as UMIN000001004, and adhered to the tenets of the Declaration of Helsinki.

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

  • Data availability statement No data are available.

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.