EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Evaluating an AI-assisted triage workflow for retinal diseases

Doohyun Park iD, Richul Oh, Jihyeon Baek iD, Kunho Bae iD

PLOS Digital Health · 15.09.2026 · 5 (9) · e0001700

DOI: 10.1371/journal.pdig.0001700 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 15.09.2026. Verfasst von Doohyun Park und 3 weiteren Autor:innen. Beteiligte Einrichtung: VUNO Inc., Seoul, Korea. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: VUNO Inc., Korea Medical Institute.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The clinical value of artificial intelligence (AI) in fundus photography depends on workflow efficiency as well as diagnostic performance. We evaluated an AI-assisted negative-screening workflow for diabetic retinopathy (DR), retinal vein occlusion (RVO), and age-related macular degeneration (AMD) using 6,904 color fundus photographs independently graded by three retina specialists. In this workflow, AI-negative images were classified as negative without ophthalmologist review, whereas AI-positive images were referred for human interpretation. For each reader–disease pair, the reference standard was agreement between the other two readers; discordant cases were excluded (DR, 1.2%–2.3%; RVO, 0.3%–0.6%; AMD, 6.1%–11.6%). The workflow reduced direct ophthalmologist review to 7.3%–8.0% of images for DR, 11.7%–11.9% for RVO, and 13.5%–16.8% for AMD. For DR, sensitivity decreased significantly (0.9168 to 0.8838; difference, -0.0330; 95% confidence interval [CI], -0.0495 to -0.0165; p < 0.001), whereas specificity did not change significantly (0.9961 to 0.9983; p = 0.183). For RVO, sensitivity was unchanged (0.9807) and specificity did not change significantly (0.9985 to 0.9988; p = 0.320). For AMD, sensitivity decreased significantly (0.8570 to 0.8445; difference, -0.0124; 95% CI, -0.0215 to -0.0033; p = 0.008), whereas specificity did not change significantly (0.9685 to 0.9843; p = 0.324). In an exploratory image-level analysis for at least one target disease, review decreased to 27.7%–30.1%; sensitivity changed from 0.9122 to 0.9039 (difference, -0.0083; 95% CI, -0.0131 to -0.0035; p < 0.001) and specificity from 0.9659 to 0.9804 ( p = 0.334). AI-assisted negative-screening can reduce ophthalmologist workload across multiple retinal diseases, but with disease-specific safety trade-offs: because AI-negative images are not reviewed, reduced sensitivity for DR and AMD means a small proportion of true-positive cases would go undetected, potentially delaying diagnosis and treatment for sight-threatening disease. These results support disease-specific implementation strategies that balance workload reduction against missed positive cases.

Autor:innen und Institutionen

  • VUNO Inc., Seoul, Korea.
  • Department of Ophthalmology, Seoul National University Hospital, Seoul, Korea.
  • Mass Eye and Ear and the Department of Ophthalmology at Harvard Medical School, Boston, Massachusetts, United States of America.

ORCID-Profile: Doohyun Park, Jihyeon Baek, Kunho Bae

Förderung

  • VUNO Inc.
  • Korea Medical Institute

Zitieren

APA

Park, D., Oh, R., Baek, J., & Bae, K. (2026). Evaluating an AI-assisted triage workflow for retinal diseases. PLOS Digital Health, 5(9), e0001700. https://doi.org/10.1371/journal.pdig.0001700

Vancouver

Park D, Oh R, Baek J, Bae K. Evaluating an AI-assisted triage workflow for retinal diseases. PLOS Digital Health. 2026;5(9):e0001700. doi:10.1371/journal.pdig.0001700

BibTeX
@article{Park2026,
  author = {Park, Doohyun and Oh, Richul and Baek, Jihyeon and Bae, Kunho},
  title = {Evaluating an AI-assisted triage workflow for retinal diseases},
  journal = {PLOS Digital Health},
  year = {2026},
  volume = {5},
  number = {9},
  pages = {e0001700},
  doi = {10.1371/journal.pdig.0001700}
}
Kostenlos starten →