Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 May 27;15(6):865.
doi: 10.3390/life15060865.

The Role of Artificial Intelligence in Predicting the Progression of Intraocular Hypertension to Glaucoma

Nicoleta Anton  1   2 , Cătălin Lisa  3 , Bogdan Doroftei  4 , Ruxandra Angela Pîrvulescu  5 , Ramona Ileana Barac  5 , Ionuț Iulian Lungu  6 , Camelia Margareta Bogdănici  1   2
Affiliations

The Role of Artificial Intelligence in Predicting the Progression of Intraocular Hypertension to Glaucoma

Nicoleta Anton et al. Life (Basel). .

Abstract

AI systems, especially artificial neural networks (ANNs), are increasingly involved in the diagnosis and personalized management of ophthalmologic disorders.

Background: This study shows the practical applications of artificial intelligence for predicting the progression of intraocular hypertension (IOH) to glaucoma.

Methods: This study involved two groups of patients with IOH and a control group, analyzed using the commercial Neurosolution simulator. The findings were compared with experimental data. The performance of the neural models was evaluated using several metrics: Mean Squared Error (MSE), Normalized Mean Squared Error (NMSE), correlation coefficient (r2), and percentage error (Ep).

Results: For all three patient groups, the best performance was achieved with neural networks featuring two hidden layers: MLP(9:18:9:3) for group 1, MLP(10:20:10:3) for group 2, and MLP(10:30:20:3) for group 3. The MSE values during validation were 0.39 for groups 1 and 2, and 0.34 for group 3. For these neural networks, the probability of producing correct outputs during validation was 75% (i.e., 9 correct responses out of a possible 12). The findings in this study are in line with those reported by other researchers in the field.

Conclusions: The neural network models developed in this study demonstrated their potential for predicting the progression of intraocular hypertension to glaucoma.

Keywords: artificial intelligence; artificial neural networks; glaucoma; intraocular hypertension.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Stages of modeling with neural networks.
Figure 2
Figure 2
Mean age values across the study groups.
Figure 3
Figure 3
Five-year risk of conversion from intraocular hypertension (IOHT) to glaucoma.
Figure 4
Figure 4
Variation in MSE with increasing number of training epochs for patient group 1.
Figure 5
Figure 5
Performance evaluation of the MLP (9:18:9:3) model during the training stage: (a) PSD, (b) risk, (c) C/D.
Figure 6
Figure 6
Performance evaluation of the MLP (9:18:9:3) model during the validation stage, (a) PSD (b) risk, (c) C/D.
Figure 6
Figure 6
Performance evaluation of the MLP (9:18:9:3) model during the validation stage, (a) PSD (b) risk, (c) C/D.
Figure 7
Figure 7
Performance evaluation of the MLP (9:18:9:3) model during the testing stage: (a) PSD, (b) risk, (c) C/D.
Figure 7
Figure 7
Performance evaluation of the MLP (9:18:9:3) model during the testing stage: (a) PSD, (b) risk, (c) C/D.
Figure 8
Figure 8
Variation in MSE with increasing number of training epochs for patient group 2.
Figure 9
Figure 9
Performance evaluation of the MLP (10:20:10:3) model during the training stage: (a) PSD, (b) RISC and (c) C/D.
Figure 10
Figure 10
Performance evaluation of the MLP (10:20:10:3) model during the validation stage: (a) PSD; (b) RISC; (c) C/D.
Figure 10
Figure 10
Performance evaluation of the MLP (10:20:10:3) model during the validation stage: (a) PSD; (b) RISC; (c) C/D.
Figure 11
Figure 11
Variation in MSE as a function of the increasing number of training epochs for patient group 3.
Figure 12
Figure 12
Performance evaluation of the MLP (10:30:20:3) model during the training stage: (a) PSD MLP (10:30:20:3) and MLP experimental; (b) RISC MLP (10:30:20:3) and RISC experimental; (c) C/D MLP (10:30:20:3) and C/D experimental.
Figure 12
Figure 12
Performance evaluation of the MLP (10:30:20:3) model during the training stage: (a) PSD MLP (10:30:20:3) and MLP experimental; (b) RISC MLP (10:30:20:3) and RISC experimental; (c) C/D MLP (10:30:20:3) and C/D experimental.
Figure 13
Figure 13
Performance evaluation of the MLP (10:30:20:3) model during the validation stage; (a) PSD; (b) RISC; (c) C/D.
Figure 13
Figure 13
Performance evaluation of the MLP (10:30:20:3) model during the validation stage; (a) PSD; (b) RISC; (c) C/D.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Donkor R., Jammal A.A., Greenfield D.S. Relationship between Blood Pressure and Rates of Glaucomatous Visual Field. Progression The Vascular Imaging in Glaucoma Study. Ophthalmology. 2025;132:30–38. doi: 10.1016/j.ophtha.2024.07.026. - DOI - PubMed
    1. Jan C., He M., Vingrys A., Zhu Z., Stafford R.S. Diagnosing glaucoma in primary eye care and the role of Artifcial Intelligence applications for reducing the prevalence of undetected glaucoma in Australia. Eye. 2024;38:2003–2013. doi: 10.1038/s41433-024-03026-z. - DOI - PMC - PubMed
    1. Zhu Y., Salowe R., Chow C., Li S., Bastani O., O’Brien J.M. Advancing Glaucoma Care: Integrating Artificial Intelligence in Diagnosis, Management, and Progression Detection. Bioengineering. 2024;11:122. doi: 10.3390/bioengineering11020122. - DOI - PMC - PubMed
    1. Lemij H.G., de Vente C., Sánchez C.I., Vermeer K.A. Characteristics of a Large, Labeled Data Set for the training of artificial intelligence for glaucoma screening with fundus photographs. Ophthalmol. Sci. 2023;3:100300. doi: 10.1016/j.xops.2023.100300. - DOI - PMC - PubMed
    1. Anton N., Doroftei B., Curteanu S., Catãlin L., Ilie O.D., Târcoveanu F., Bogdănici C.M. Comprehensive Review on the Use of Artificial Intelligence in Ophthalmology and Future Research Directions. Diagnostics. 2022;13:100. doi: 10.3390/diagnostics13010100. - DOI - PMC - PubMed

LinkOut - more resources