SMOTE-Enhanced Explainable Artificial Intelligence Model for Predicting Visual Field Progression in Myopic Normal Tension Glaucoma.

Journal: Journal of glaucoma
Published Date:

Abstract

PRCIS: The AI model, enhanced by SMOTE to balance data classes, accurately predicted visual field deterioration in patients with myopic normal tension glaucoma. Using SHAP analysis, the key variables driving disease progression were identified.

Authors

  • So Yeon Kim
  • Jung Jong Jin
    Kim's Eye Hospital.
  • Ahnul Ha
    Department of Ophthalmology, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Korea.
  • Chae Hyun Song
    Department of Ophthalmology, Seoul National University Hospital.
  • Se Hie Park
    Department of Ophthalmology, Seoul National University Hospital.
  • Kyoung Hae Kang
    Department of Ophthalmology, Seoul National University Hospital.
  • Jaekyoung Lee
    Department of Ophthalmology, Seoul National University Hospital.
  • Min Gu Huh
    Department of Ophthalmology, Yeungnam University Medical Center, Daegu, Korea.
  • Jin Wook Jeoung
    Department of Ophthalmology, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Korea.
  • Ki Ho Park
    Department of Ophthalmology.
  • Young Kook Kim
    Department of Ophthalmology, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Korea.