Visual field prediction using a deep bidirectional gated recurrent unit network model.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
10 07 2023
10 07 2023
Historique:
received:
15
07
2022
accepted:
20
06
2023
medline:
12
7
2023
pubmed:
11
7
2023
entrez:
10
7
2023
Statut:
epublish
Résumé
Although deep learning architecture has been used to process sequential data, only a few studies have explored the usefulness of deep learning algorithms to detect glaucoma progression. Here, we proposed a bidirectional gated recurrent unit (Bi-GRU) algorithm to predict visual field loss. In total, 5413 eyes from 3321 patients were included in the training set, whereas 1272 eyes from 1272 patients were included in the test set. Data from five consecutive visual field examinations were used as input; the sixth visual field examinations were compared with predictions by the Bi-GRU. The performance of Bi-GRU was compared with the performances of conventional linear regression (LR) and long short-term memory (LSTM) algorithms. Overall prediction error was significantly lower for Bi-GRU than for LR and LSTM algorithms. In pointwise prediction, Bi-GRU showed the lowest prediction error among the three models in most test locations. Furthermore, Bi-GRU was the least affected model in terms of worsening reliability indices and glaucoma severity. Accurate prediction of visual field loss using the Bi-GRU algorithm may facilitate decision-making regarding the treatment of patients with glaucoma.
Identifiants
pubmed: 37429862
doi: 10.1038/s41598-023-37360-1
pii: 10.1038/s41598-023-37360-1
pmc: PMC10333213
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
11154Informations de copyright
© 2023. The Author(s).
Références
Resnikoff, S. et al. Global data on visual impairment in the year 2002. Bull. World Health Organization 9 (2004).
Weinreb, R. N., Aung, T. & Medeiros, F. A. The pathophysiology and treatment of glaucoma: A review. JAMA 311, 1901 (2014).
doi: 10.1001/jama.2014.3192
pubmed: 24825645
pmcid: 4523637
Henson, D. B., Chaudry, S., Artes, P. H., Faragher, E. B., & Ansons, A. Response variability in the visual field: Comparison of optic neuritis, glaucoma, ocular hypertension, and normal eyes. 41, 5 (2000).
Wang, M. et al. An artificial intelligence approach to detect visual field progression in glaucoma based on spatial pattern analysis. Invest. Ophthalmol. Vis. Sci. 60, 365 (2019).
doi: 10.1167/iovs.18-25568
pubmed: 30682206
pmcid: 6348996
Murata, H., Araie, M. & Asaoka, R. A new approach to measure visual field progression in glaucoma patients using variational bayes linear regression. Invest. Ophthalmol. Vis. Sci. 55, 8386–8392 (2014).
doi: 10.1167/iovs.14-14625
pubmed: 25414192
Wen, J. C. et al. Forecasting future Humphrey Visual Fields using deep learning. PLoS ONE 14, e0214875 (2019).
doi: 10.1371/journal.pone.0214875
pubmed: 30951547
pmcid: 6450620
Berchuck, S. I., Mukherjee, S. & Medeiros, F. A. Estimating rates of progression and predicting future visual fields in glaucoma using a deep variational autoencoder. Sci Rep 9, 18113 (2019).
doi: 10.1038/s41598-019-54653-6
pubmed: 31792321
pmcid: 6888896
Salehinejad, H., Sankar, S., Barfett, J., Colak, E., Valaee, S. Recent advances in recurrent neural networks. 21.
Liu, S., Yang, N., Li, M. & Zhou, M. A recursive recurrent neural network for statistical machine translation. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 1491–1500 (Association for Computational Linguistics, 2014). https://doi.org/10.3115/v1/P14-1140 .
Young, T., Hazarika, D., Poria, S. & Cambria, E. Recent trends in deep learning based natural language processing. IEEE Comput. Intell. Mag. 13, 55–75 (2018).
doi: 10.1109/MCI.2018.2840738
Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9, 1735–1780 (1997).
doi: 10.1162/neco.1997.9.8.1735
pubmed: 9377276
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. (2014) https://doi.org/10.48550/ARXIV.1412.3555 .
Park, K., Kim, J. & Lee, J. Visual field prediction using recurrent neural network. Sci Rep 9, 8385 (2019).
doi: 10.1038/s41598-019-44852-6
pubmed: 31182763
pmcid: 6557823
Dixit, A., Yohannan, J. & Boland, M. V. Assessing glaucoma progression using machine learning trained on longitudinal visual field and clinical data. Ophthalmology 128, 1016–1026 (2021).
doi: 10.1016/j.ophtha.2020.12.020
pubmed: 33359887
Lynn, H. M., Pan, S. B. & Kim, P. A deep bidirectional gru network model for biometric electrocardiogram classification based on recurrent neural networks. IEEE Access 7, 145395–145405 (2019).
doi: 10.1109/ACCESS.2019.2939947
Cho, K. et al. Learning phrase representations using RNN encoder–decoder for statistical machine translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) 1724–1734 (Association for Computational Linguistics, 2014). https://doi.org/10.3115/v1/D14-1179 .
Khandelwal, S., Lecouteux, B. & Besacier, L. Comparing GRU and LSTM for Automatic Speech Recognition. 7.
Li, X. et al. Time-series production forecasting method based on the integration of Bidirectional Gated Recurrent Unit (Bi-GRU) network and Sparrow Search Algorithm (SSA). J. Petrol. Sci. Eng. 208, 109309 (2022).
doi: 10.1016/j.petrol.2021.109309
Darmawahyuni, A., Nurmaini, S., Rachmatullah, M. N., Firdaus, F. & Tutuko, B. Unidirectional-bidirectional recurrent networks for cardiac disorders classification. TELKOMNIKA 19, 902 (2021).
doi: 10.12928/telkomnika.v19i3.18876
Schuster, M. & Paliwal, K. K. Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45, 2673–2681 (1997).
doi: 10.1109/78.650093
Pascanu, R., Gulcehre, C., Cho, K. & Bengio, Y. How to construct deep recurrent neural networks. (2013). https://doi.org/10.48550/ARXIV.1312.6026 .
Garway-Heath, D. F., Poinoosawmy, D., Fitzke, F. W. & Hitchings, R. A. Mapping the visual field to the optic disc in normal tension glaucoma eyes. 107, 7 (2000).
Asaoka, R., Murata, H., Iwase, A. & Araie, M. Detecting preperimetric glaucoma with standard automated perimetry using a deep learning classifier. Ophthalmology 123, 1974–1980 (2016).
doi: 10.1016/j.ophtha.2016.05.029
pubmed: 27395766
Elze, T. et al. Patterns of functional vision loss in glaucoma determined with archetypal analysis. J. R. Soc. Interface. 12, 20141118 (2015).
doi: 10.1098/rsif.2014.1118
pubmed: 25505132
pmcid: 4305414
Cai, S. et al. Clinical correlates of computationally derived visual field defect archetypes in patients from a glaucoma clinic. Curr. Eye Res. 42, 568–574 (2017).
doi: 10.1080/02713683.2016.1205630
pubmed: 27494512
Yousefi, S. et al. Detection of longitudinal visual field progression in glaucoma using machine learning. Am. J. Ophthalmol. 193, 71–79 (2018).
doi: 10.1016/j.ajo.2018.06.007
pubmed: 29920226
Bengio, Y., Simard, P. & Frasconi, P. Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5, 157–166 (1994).
doi: 10.1109/72.279181
pubmed: 18267787
Johnson, C. A. & Nelson-Quigg, J. M. A prospective three-year study of response properties of normal subjects and patients during automated perimetry. Ophthalmology 100, 269–274 (1993).
doi: 10.1016/S0161-6420(93)31660-X
pubmed: 8437837
Katz, J., Sommer, A. & Witt, K. Reliability of visual field results over repeated testing. Ophthalmology 98, 70–75 (1991).
doi: 10.1016/S0161-6420(91)32339-X
pubmed: 2023736
Murata, H. et al. Identifying areas of the visual field important for quality of life in patients with glaucoma. PLoS ONE 8, e58695 (2013).
doi: 10.1371/journal.pone.0058695
pubmed: 23520528
pmcid: 3592814
Abe, R. Y. et al. The impact of location of progressive visual field loss on longitudinal changes in quality of life of patients with glaucoma. Ophthalmology 123, 552–557 (2016).
doi: 10.1016/j.ophtha.2015.10.046
pubmed: 26704883
Rao, H. L. et al. Role of visual field reliability indices in ruling out glaucoma. JAMA Ophthalmol 133, 40 (2015).
doi: 10.1001/jamaophthalmol.2014.3609
pubmed: 25256758
Raman, P., Khy Ching, Y., Sivagurunathan, P. D., Ramli, N. & Mohd. Khalid, K. H. The Association between visual field reliability indices and cognitive impairment in glaucoma patients. J. Glaucoma 28, 685–690 (2019).
Casas-Llera, P. et al. Visual field index rate and event-based glaucoma progression analysis: Comparison in a glaucoma population. Br. J. Ophthalmol. 93, 1576–1579 (2009).
doi: 10.1136/bjo.2009.158097
pubmed: 19535357
Crabb, D. P., Fitzke, F. W., McNaught, A. I., Edgar, D. F. & Hitchings, R. A. Improving the prediction of visual field progression in glaucoma using spatial processing. Ophthalmology 104, 517–524 (1997).
doi: 10.1016/S0161-6420(97)30281-4
pubmed: 9082283
Bengtsson, B. Prediction of glaucomatous visual field loss by extrapolation of linear trends. Arch Ophthalmol 127, 1610 (2009).
doi: 10.1001/archophthalmol.2009.297
pubmed: 20008716
Nouri-Mahdavi, K. Comparison of methods to predict visual field progression in glaucoma. Arch Ophthalmol 125, 1176 (2007).
doi: 10.1001/archopht.125.9.1176
pubmed: 17846355
European Glaucoma Society Terminology and Guidelines for Glaucoma, 5th Edition. Br. J. Ophthalmol. 105, 1–169 (2021).
Prum, B. E. et al. Primary open-angle glaucoma preferred practice pattern® guidelines. Ophthalmology 123, P41–P111 (2016).
doi: 10.1016/j.ophtha.2015.10.053
pubmed: 26581556