EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Artificial Intelligence in Glaucoma: Advances in Diagnosis, Progression Forecasting, and Surgical Outcome Prediction

Chiao-Hsin Lan iD, Ta-Hung Chiu iD, Wei-Ting Yen iD, Da-Wen Lu iD

International Journal of Molecular Sciences · 08.05.2025 · 26 (10) · 4473

DOI: 10.3390/ijms26104473 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift International Journal of Molecular Sciences, online erschienen am 08.05.2025. Verfasst von Chiao-Hsin Lan und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Medicine, National Defense Medical Center, Taipei 11490, Taiwan. Hauptthemen laut MEDLINE: Glaucoma, Artificial Intelligence. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Tri-Service General Hospital Research Foundation, the National Defense Medical Center Foundation, Tri-Service General Hospital Research Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Glaucoma is a leading cause of irreversible blindness, with challenges persisting in early diagnosis, disease progression, and surgical outcome prediction. Recent advances in artificial intelligence have enabled significant progress by extracting clinically relevant patterns from structural, functional, and molecular data. This review outlines the current applications of artificial intelligence in glaucoma care, including early detection using fundus photography and OCT and disease progression prediction using deep learning architectures such as convolutional neural networks, recurrent neural networks, transformer models, generative adversarial networks, and autoencoders. Surgical outcome forecasting has been enhanced through multimodal models that integrate electronic health records and imaging data. We also highlight emerging AI applications in omics analysis, including transcriptomics and metabolomics, for biomarker discovery and individualized risk stratification. Despite these advances, key challenges remain in interpretability, integration of heterogeneous data, and the lack of personalized surgical timing guidance. Future work should focus on transparent, generalizable, and multimodal AI models, supported by large, well-curated datasets, to advance precision medicine in glaucoma.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GlaucomaArtificial IntelligenceHumansDisease ProgressionDeep LearningNeural Networks, ComputerForecasting

Stichwörter der Autor:innen

artificial intelligencefundus photographyglaucomamolecular biomarkersoptical coherence tomographyvisual field

Autor:innen und Institutionen

  • School of Medicine, National Defense Medical Center, Taipei 11490, Taiwan.
  • Department of General Medicine, Tri-Service General Hospital, National Defense Medical Center, Taipei 114202, Taiwan.
  • Department of Ophthalmology, Tri-Service General Hospital, National Defense Medical Center, Taipei 114202, Taiwan.

ORCID-Profile: Chiao-Hsin Lan, Ta-Hung Chiu, Wei-Ting Yen, Da-Wen Lu

Förderung

  • the Tri-Service General Hospital Research Foundation
  • the National Defense Medical Center Foundation
  • Tri-Service General Hospital Research Foundation
  • National Defense Medical Center Foundation

Zitieren

APA

Lan, C. H., Chiu, T. H., Yen, W. T., & Lu, D. W. (2025). Artificial Intelligence in Glaucoma: Advances in Diagnosis, Progression Forecasting, and Surgical Outcome Prediction. International Journal of Molecular Sciences, 26(10), 4473. https://doi.org/10.3390/ijms26104473

Vancouver

Lan CH, Chiu TH, Yen WT, Lu DW. Artificial Intelligence in Glaucoma: Advances in Diagnosis, Progression Forecasting, and Surgical Outcome Prediction. International Journal of Molecular Sciences. 2025;26(10):4473. doi:10.3390/ijms26104473

BibTeX
@article{Lan2025,
  author = {Lan, Chiao-Hsin and Chiu, Ta-Hung and Yen, Wei-Ting and Lu, Da-Wen},
  title = {Artificial Intelligence in Glaucoma: Advances in Diagnosis, Progression Forecasting, and Surgical Outcome Prediction},
  journal = {International Journal of Molecular Sciences},
  year = {2025},
  volume = {26},
  number = {10},
  pages = {4473},
  doi = {10.3390/ijms26104473}
}
Kostenlos starten →