EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Eye Disease Classification and Management Recommendation Using Swin Transformer

Anggara Falih Hartono, Eva Yulia Puspaningrum, Faisal Muttaqin

bit-Tech · 10.08.2026 · 9 (1) · 714-721

DOI: 10.32877/bt.v9i1.3966 ↗

Kurz gefasst

Fachartikel in der Zeitschrift bit-Tech, online erschienen am 10.08.2026. Verfasst von Anggara Falih Hartono und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Visual impairment caused by eye diseases such as cataracts, glaucoma, and diabetic retinopathy can significantly reduce quality of life and may lead to blindness if not diagnosed at an early stage. The limited availability of medical professionals and diagnostic equipment remains a major challenge in the initial screening process. This research aims to design and develop a prototype for preliminary eye disease classification and educational guidance using the Swin Transformer architecture. The dataset used in this study consists of 4,117 images across four classes: normal, cataract, glaucoma, and diabetic retinopathy, which were divided into an 80:20 train-test split. The research process includes data collection, preprocessing, data splitting, model training, model evaluation, and integration of the trained model into a web-based application using FastAPI and React. The system is also equipped with a knowledge-based recommendation module that provides preliminary management guidance according to the classification results. Evaluation results show that the proposed model achieved an accuracy of 93% and a macro-average F1-score of 0.93. Website implementation testing demonstrated that the system successfully classified four representative test images and displayed both confidence scores and appropriate educational recommendations. Therefore, the system output from this study serves as a proof-of-concept prototype for preliminary image-based classification rather than a clinically validated diagnostic tool.

Zitieren

APA

Hartono, A. F., Puspaningrum, E. Y., & Muttaqin, F. (2026). Eye Disease Classification and Management Recommendation Using Swin Transformer. bit-Tech, 9(1), 714-721. https://doi.org/10.32877/bt.v9i1.3966

Vancouver

Hartono AF, Puspaningrum EY, Muttaqin F. Eye Disease Classification and Management Recommendation Using Swin Transformer. bit-Tech. 2026;9(1):714-721. doi:10.32877/bt.v9i1.3966

BibTeX
@article{Hartono2026,
  author = {Hartono, Anggara Falih and Puspaningrum, Eva Yulia and Muttaqin, Faisal},
  title = {Eye Disease Classification and Management Recommendation Using Swin Transformer},
  journal = {bit-Tech},
  year = {2026},
  volume = {9},
  number = {1},
  pages = {714--721},
  doi = {10.32877/bt.v9i1.3966}
}
Kostenlos starten →