Application of artificial intelligence in the diagnosis of glaucoma and short-term follow-up
Main Article Content
Abstract
This paired diagnostic accuracy study evaluated Cybersight AI for detecting primary glaucoma at baseline and 3 months. The analysis included 78 eyes from 42 patients at Hue Central Hospital Eye Center, including 42 primary glaucoma eyes and 36 non-glaucoma eyes with complete paired AI outputs. Comprehensive ophthalmologist diagnosis based on clinical examination, gonioscopy, retinal nerve fiber layer OCT and visual fields served as the reference standard. At baseline, sensitivity, specificity, accuracy and AUC were 61.9%, 86.1%, 73.1% and 0.762, respectively. At 3 months, the corresponding estimates were 61.9%, 94.4%, 76.9% and 0.784. The paired AUC difference was not statistically significant (p = 0.356), and overall accuracy did not differ significantly (p = 0.371). Cybersight AI showed moderate discrimination with stable sensitivity and a non-significant trend toward higher specificity, supporting its role as an adjunct for triage and clinical decision support rather than a stand-alone diagnostic test.
Article Details
Keywords
Glaucoma, artificial intelligence, fundus photography, diagnostic accuracy, ROC–AUC, triage
References
2. Tonti E, Tonti S, Mancini F, et al. Artificial Intelligence and Advanced Technology in Glaucoma: A Review. Journal of personalized medicine. 2024;14(10).
3. Ling XC, Chen HS, Yeh PH, et al. Deep Learning in Glaucoma Detection and Progression Prediction: A Systematic Review and Meta-Analysis. Biomedicines. 2025;13(2).
4. Anton N DB, Curteanu S, Catãlin L, Ilie OD, Târcoveanu F, Bogdănici CM. Comprehensive Review on the Use of Artificial Intelligence in Ophthalmology and Future Research Directions. Diagnostics (Basel). 2022 13:100.
5. Shahriari MH, Asadi F, Moghaddasi H, Roshanpour A, Sharifipour F, Khorrami Z. Applications of machine learning in glaucoma diagnosis based on tabular data: a systematic review. BMC Biomedical Engineering. 2025;7(1):9.
6. Ashtari-Majlan M, Dehshibi MM, Masip D. Glaucoma diagnosis in the era of deep learning: A survey. Expert Systems with Applications. 2024;256:124888.
7. SS. S. Glaucoma blindness-A rapidly emerging non-communicable ocular disease in India: Addressing the issue with advocacy. J Family Med Prim Care. 2020 31(5):2200-2206.
8. Wolvaardt EH, V. H. Update on glaucoma. Community Eye Health Journal. 2021;34(112):31.
9. Wu H WY, Li F, Liu Z, Shi F. The national, regional, and global impact of glaucoma as reported in the 2019 Global Burden of Disease Study. Arch Med Sci. 2023 19(6):1913-1919.
10. Jaccard N. AI for Glaucoma Care. Glaucoma Today. 2022.
11. Foster P, Buhrmann R, Quigley H, Johnson G. The definition and classification of glaucoma in prevalence surveys. The British journal of ophthalmology. 2002;86:238-242.
12. Crowston JG, Hopley CR, Healey PR, Lee A, Mitchell P, Blue Mountains Eye S. The effect of optic disc diameter on vertical cup to disc ratio percentiles in a population based cohort: the Blue Mountains Eye Study. Br J Ophthalmol. 2004;88(6):766-770.
13. Myers JGaH, David S. and Schuman, Joel S. Is It Glaucoma or Not? Watch for RNFL OCT Artifacts. EyeNet Magazine, American Academy of Ophthalmology. 2024.
14. Ruia S, Tripathy K. Humphrey Visual Field. In: StatPearls. Treasure Island (FL) ineligible companies. Disclosure: Koushik Tripathy declares no relevant financial relationships with ineligible companies.: StatPearls Publishing 2025.
15. La Bruna S, Rai A, Mao G, et al. The OCT RNFL Probability Map and Artifacts Resembling Glaucomatous Damage. Transl Vis Sci Technol. 2022;11(3):18.
16. Tello A, Vazquez E, Villamizar SJ, et al. Diagnostic accuracy of the non-compliance of the ISNT rule in glaucoma: Systematic review and meta-analysis. European journal of ophthalmology. 2025:11206721251392629.
17. Tham YC, Li X, Wong TY, Quigley HA, Aung T, Cheng CY. Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis. Ophthalmology. 2014;121(11):2081-2090.
18. Cohen JF, Korevaar DA, Altman DG, et al. STARD 2015 guidelines for reporting diagnostic accuracy studies: explanation and elaboration. BMJ open. 2016;6(11):e012799.
19. Huang X, Sun J, Gupta K, et al. Detecting glaucoma from multi-modal data using probabilistic deep learning. Front Med (Lausanne). 2022;9:923096.
20. Crowston JG, Hopley CR, Healey PR, Lee A, Mitchell P. The effect of optic disc diameter on vertical cup to disc ratio percentiles in a population based cohort: the Blue Mountains Eye Study. Br J Ophthalmol. 2004;88(6):766-770.