Deep learning algorithm detects biomarkers of progression in dry AMD

Key Takeaways

  • A deep learning algorithm showed superior performance compared with other algorithms and human graders in detecting early biomarkers of dry age-related macular degeneration (AMD) progression.
  • The new algorithm may be useful in drug development and clinical trial recruitment.

SLIViT, short for Slice Integration by Vision Transformers, is a deep learning framework developed at the University of California, Los Angeles, that can measure disease-related risk factors in various medical imaging modalities, such as magnetic resonance imaging, optical coherence tomography and ultrasound. In a study presented at the FLORetina-ICOOR meeting, SLIViT was evaluated for the ability to detect high-risk biomarkers for dry AMD progression. When compared with other deep learning algorithms, SLIViT showed greater performance in the identification of each biomarker. When compared with seven human graders, it performed equally well but was significantly faster.

“It is important to define and detect early biomarkers for AMD progression because we want to develop drugs targeting earlier stages of non-neovascular [dry] AMD,” Giulia Corradetti, MD, said at the meeting. In addition, identifying the subset of population with high risk for developing late AMD is important for recruitment in clinical trials, she said. The algorithm can also be employed in underserved populations, increasing diversity in recruitment for clinical trials.

Edited by Miriam Kaplan, PhD

Source: Michela Cimberle, Healio Ocular Surgery News, January 10, 2024; see source article