Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 7 min ago
Peer-reviewedCC BY 4.0Frontiers in Ophthalmology

Early diagnosis program for multimodal primary open-angle glaucoma based on clinical process

  • Jingyi Ma1
  • Bin Lv2
  • Yuanyuan Li1
  • Pan Fan1
  • Xu Zhao2
  • Yingtao Zhang2
  • Huiping Yuan1
  1. 1The Department of Ophthalmology, The Second Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang, China
  2. 2School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China
Read full textPDFDOICite

Abstract

Background: Glaucoma is among the leading causes of blindness. It is important to detect glaucoma at early stages. Using structural and functional examinations to identify primary open-angle glaucoma (POAG) is critical. Computer-aided diagnosis of glaucoma requires multimodal data to identify an accurate and explainable model for early glaucoma diagnosis.

Methods: In this study, 301 multimodal data points were collected from the ophthalmology department at the Second Affiliated Hospital of Harbin Medical University. Data regarding fundus photography (FP), retinal nerve fiber layer thickness (RNFLt), intraocular pressure (IOP) values, visual field examination parameters and age were obtained. A powerful deep learning network was used to segment the optic nerve head obtained from the FPs. Machine learning classifiers (MLCs) were adopted to obtain the final classification results using 3 datasets: early glaucoma eyes, suspected glaucoma eyes, and healthy eyes; moreover, the diagnostic results of glaucoma specialists and general nonglaucoma ophthalmologists were collected.

Results: The overall area under the curve was 0.9858. The accuracy values of the deep learning- machine learning system, the glaucoma specialist group, the general ophthalmologist group were 0.9478, 0.9493, 0.8725, respectively.

Conclusions: The algorithm delivers superior results in the early diagnosis of POAG. This study’s hybrid deep learning-machine learning framework can effectively assist with clinical decision-making for early POAG.

Related

  1. Primary pulmonary NUT carcinoma: pathological features, clinical diagnosis, treatment, and prognosis — An extended review
    Shan Wu, Miao Zhang, Hui Wang
    Oncology reviewsPeer-reviewedCC BYFull textGeneral medicineEurope PMC
  2. Artificial Intelligence for Thyroid Nodule Diagnosis: From Multimodal Integration to Clinical Utility.
    Jie Li, Xiaofei Wang
    Diagnostics (Basel, Switzerland)Peer-reviewedCC BYFull textEndocrinology & metabolismEurope PMC
  3. Clinical applications and recent advances in multimodal image fusion for hepatocellular carcinoma diagnosis: a narrative review.
    Zhirui Gan, Xuejia Zheng, Feng Zhu +3
    Journal of gastrointestinal oncologyPeer-reviewedCC BY-NC-NDFull textOncologyEurope PMC
  4. Clinical Disease Activity and Power Doppler Changes Observed During a Multimodal Rehabilitation Program in Rheumatoid Arthritis: A Retrospective Longitudinal Observational Study
    Cristina Octaviana Daia, Madalina Codruta Verenca, Mirela Manea +5
    Journal of Clinical MedicinePeer-reviewedCC BY 4.0Full textGeneral medicineCrossrefEurope PMC
  5. Clinical, CT, and MR Findings for the Pretreatment Diagnosis of Primary Epithelial Tumors of the Lacrimal Gland
    Yu-Yun Chang, Kuei-Hong Kuo, Hsin-Wei Wu +5
    Current Medical ImagingPeer-reviewedCC BY 4.0Full textMedical imaging & radiologyPMC

Cite

BibTeXRIS
BibTeX
@article{ma2026early,
  title = {{Early diagnosis program for multimodal primary open-angle glaucoma based on clinical process}},
  author = {Jingyi Ma and Bin Lv and Yuanyuan Li and Pan Fan and Xu Zhao and Yingtao Zhang and Huiping Yuan},
  journal = {Frontiers in Ophthalmology},
  year = {2026},
  month = oct,
  doi = {10.3389/fopht.2026.1975341},
  url = {https://doi.org/10.3389/fopht.2026.1975341},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Early diagnosis program for multimodal primary open-angle glaucoma based on clinical process
AU  - Jingyi Ma
AU  - Bin Lv
AU  - Yuanyuan Li
AU  - Pan Fan
AU  - Xu Zhao
AU  - Yingtao Zhang
AU  - Huiping Yuan
PY  - 2026
DA  - 2026/10/21
JO  - Frontiers in Ophthalmology
DO  - 10.3389/fopht.2026.1975341
UR  - https://doi.org/10.3389/fopht.2026.1975341
AB  - Background: Glaucoma is among the leading causes of blindness. It is important to detect glaucoma at early stages. Using structural and functional examinations to identify primary open-angle glaucoma (POAG) is critical. Computer-aided diagnosis of glaucoma requires multimodal data to identify an accurate and explainable model for early glaucoma diagnosis.  Methods: In this study, 301 multimodal data points were collected from the ophthalmology department at the Second Affiliated Hospital of Harbin Medical University. Data regarding fundus photography (FP), retinal nerve fiber layer thickness (RNFLt), intraocular pressure (IOP) values, visual field examination parameters and age were obtained. A powerful deep learning network was used to segment the optic nerve head obtained from the FPs. Machine learning classifiers (MLCs) were adopted to obtain the final classification results using 3 datasets: early glaucoma eyes, suspected glaucoma eyes, and healthy eyes; moreover, the diagnostic results of glaucoma specialists and general nonglaucoma ophthalmologists were collected.  Results: The overall area under the curve was 0.9858. The accuracy values of the deep learning- machine learning system, the glaucoma specialist group, the general ophthalmologist group were 0.9478, 0.9493, 0.8725, respectively.  Conclusions: The algorithm delivers superior results in the early diagnosis of POAG. This study’s hybrid deep learning-machine learning framework can effectively assist with clinical decision-making for early POAG.
SN  - 2674-0826
ER  -