Machine learning models based on the dimensionality reduction of standard automated perimetry data for glaucoma diagnosis.

Journal: Artificial intelligence in medicine
Published Date:

Abstract

INTRODUCTION: Visual field testing via standard automated perimetry (SAP) is a commonly used glaucoma diagnosis method. Applying machine learning techniques to the visual field test results, a valid clinical diagnosis of glaucoma solely based on the SAP data is provided. In order to reflect structural-functional patterns of glaucoma on the automated diagnostic models, we propose composite variables derived from anatomically grouped visual field clusters to improve the prediction performance. A set of machine learning-based diagnostic models are designed that implement different input data manipulation, dimensionality reduction, and classification methods.

Authors

  • Su-Dong Lee
    Department of Industrial & Management Engineering, POSTECH, Pohang, South Korea.
  • Ji-Hyung Lee
    Department of Industrial & Management Engineering, POSTECH, Pohang, South Korea.
  • Young-Geun Choi
    Department of Industrial & Management Engineering, POSTECH, Pohang, South Korea.
  • Hee-Cheon You
    Department of Industrial & Management Engineering, POSTECH, Pohang, South Korea.
  • Ja-Heon Kang
    Kyung Hee University Hospital at Gangdong, College of Medicine, Kyung Hee University, Seoul, South Korea.
  • Chi-Hyuck Jun
    Department of Industrial & Management Engineering, POSTECH, Pohang, South Korea. Electronic address: chjun@postech.ac.kr.