Artificial intelligence framework for multi-pathology risk assessment from retinal fundus images: deep learning approach to 15-disease screening - Summary - MDSpire

Artificial intelligence framework for multi-pathology risk assessment from retinal fundus images: deep learning approach to 15-disease screening

  • By

  • Robert Vasilev

  • Andrey Savchenko

  • Pavel Blinov

  • Tadej Svetina

  • Stepan Kudin

  • Nikolay Romanenko

  • Yuliya Sarana

  • Gleb Khizhnyak

  • Andrey Demchinsky

  • Taisia Shcheglova

  • May 25, 2026

  • 0 min

Share

Objective:

To develop and evaluate a comprehensive AI framework for simultaneous risk stratification of 15 distinct pathological conditions from retinal fundus images.

Key Findings:
  • Achieved ROC AUC of 0.9524–0.9971 and F1 scores of 0.8968–0.9649 across all 15 pathological classes.
  • Demonstrated robust risk stratification performance for rare conditions with fewer than 100 training examples.
  • In a single-site evaluation of 68 cases, overall accuracy was 64.7% (95% CI: 52.9–76.5%).
Interpretation:

Limitations:
  • Small cohort size in the exploratory evaluation.
  • Wide confidence intervals for sensitivity estimates of rare conditions.
Conclusion:

Original Source(s)

Artificial intelligence framework for multi-pathology risk assessment from retinal fundus images: deep learning approach to 15-disease screening

  • by Robert Vasilev, Andrey Savchenko, Pavel Blinov, Tadej Svetina, Stepan Kudin, Nikolay Romanenko, Yuliya Sarana, Gleb Khizhnyak, Andrey Demchinsky, Taisia Shcheglova

  • May 25, 2026

Related Content

Mirvetuximab Soravtansine Exposure and Incidence of Cataract Surgery

Advocacy Pays Off for ASCs

At the Outpatient Ophthalmic Surgery Society’s “OOSS Perspective 2026” symposium in Washington, DC, the organization's Washington counsel, Michael Romansky, JD, delivered an update on reimbursement, regulatory developments, and advocacy priorities affecting ophthalmic ambulatory surgery centers (ASCs).

Evaluating the effect of a new myopia control spectacle lens among children in Israel: 24-month results