Equity-enhanced glaucoma progression prediction from OCT with knowledge distillation.

Journal: NPJ digital medicine
Published Date: Jul 24, 2025

Abstract

Glaucoma is a progressive disease that can lead to permanent vision loss, making progression prediction vital for guiding effective treatment. Deep learning aids progression prediction but may yield unequal outcomes across demographic groups. We proposed a model called FairDist, which utilized baseline optical coherence tomography scans to predict glaucoma progression. An equity-aware EfficientNet was trained for glaucoma detection, which was then adapted for progression prediction with knowledge distillation. Model accuracy was measured by the AUC, Sensitivity, Specificity, and equity was assessed using equity-scaled AUC, which adjusts AUC by accounting for subgroup disparities. The mean deviation, fast progression, and total deviation pointwise progression were explored in this work. For both progression types, FairDist achieved the highest AUC and equity-scaled AUC for gender and racial groups, compared to methods with and without unfairness mitigation strategies. FairDist can be generalized to other disease progression prediction tasks to potentially achieve improved performance and fairness.

Authors

  • Sulaiman O Afolabi
    Medical AI Lab, School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, LA, USA.
  • Leila Gheisi
    Medical AI Lab, School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, LA, USA.
  • Jing Shan
    Harvard-MIT Division of Health Sciences and Technology, MIT, E25-518, 77 Massachusetts Ave, Cambridge, MA 02139, United States. Electronic address: js8686@mit.edu.
  • Lucy Q Shen
    Massachusetts Eye and Ear, Harvard Medical School, Boston, Massachusetts.
  • Mengyu Wang
    Schepens Eye Research Institute, Harvard Medical School, Boston, Massachusetts.
  • Min Shi
    School of Education, Fuzhou University of International Studies and Trade, 350000, China.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals