Escolar Documentos
Profissional Documentos
Cultura Documentos
a r t i c l e i n f o a b s t r a c t
Article history: Background and objective: This paper builds different neural network models with simple topologies,
Received 18 April 2017 having one or two hidden layers which were subsequently employed in the prediction of ocular changes
Revised 1 November 2017
progression in patients with diabetes associated with primer open-angle glaucoma.
Accepted 14 November 2017
Material and Methods: For attempting to indicate whether there is a relationship between glaucoma and
diabetes, a simulation method, based on artificial neural networks (ANN), Jordan Elman networks (JEN)
Keywords: type, in particular, was applied in conjunction with clinical observation. The study was conducted on
Glaucoma a sample of 101 eyes with open angle glaucoma included and, in each case, the patients had associated
Diabetic retinopathy diabetes mellitus. A high degree of accuracy was exhibited by the models, demonstrating the potential ef-
Artificial neural networks
fectiveness of this artificial intelligence technique for predicting ocular changes associated with diabetes.
Direct and inverse modelling
The parameters considered in this study for modelling purpose were: glaucoma age, diabetes age, C/D
ratio (cup/disk size), glycated haemoglobin level (HbA1c), intraocular pressure (IOP), patient age, mean
deviation (MD) and LENS appearance.
Results: Relatively simple models, feed-forward neural networks with one or two intermediate layers,
provided clinically meaningful data in direct modelling, the probability of correct answers being of 95%.
Inverse modelling was also performed, in which MD depreciation was the output parameter. High accu-
racy was exhibited, in this case, with Jordan Elman networks, with the confidence interval of ±15%.
Conclusions: The neural models have demonstrated the possibility of their use in successfully predicting
the relationship between glaucoma and diabetes in a real clinical environment.
© 2017 Elsevier B.V. All rights reserved.
https://doi.org/10.1016/j.cmpb.2017.11.013
0169-2607/© 2017 Elsevier B.V. All rights reserved.
184 N. Anton Apreutesei et al. / Computer Methods and Programs in Biomedicine 154 (2018) 183–190
plied to determine visual field progression for patients with glau- Table 1
Characteristics of the patients included in the study.
coma, to classify modifications in diabetic retinopathy (presence or
absence of retinopathy signs) and in the stage of glaucoma [10–17]. Characteristics Average value
Antón et al. [18] used neural networks for interpretation of reti- Ages 64.85 +/− 7.04
nal lesions in early perimetric glaucoma and concluded that both Sex 74.13% F, 25.87% M
neural networks and statistical analysis can accurately differenti- Old glaucoma (years) 4.17 +/− 3.46
ate early changes caused by glaucoma and other diseases, with an IOP 18.61 +/− 4.77
−4.63 db (medium)
accuracy of 97%. Other studies realized by Goldbaum show that
Old diabetes (years) 8.05 +/− 6.08
the networks differentiate better between normal and altered vi- Type diabetes
sual field than the overall visual field index. [19]. I 9.81%
In recent studies, Rigla and others used artificial neural net- II 58.92%
MIXT 31.37%
works in the follow-up of patients with diabetes while promoting
HgA1c (%) 6.98 +/− 1.24
the involvement of medical personnel in this area [20]. Further- Glycemic level(mg/dl) 137.42 +/− 23.17
more, Singh et al. [21] used artificial intelligence tools in assess- DR changes Without DR 89.11%
ing the risk of diabetic foot ulcers in patients with diabetes melli- Mild DR 5.94%
tus type by utilizing both multiple regressional analysis and neural Moderate/severe DR 4.95%
Fig. 3. The balance sensitivity/specificity of the age of diabetes and age of glaucoma in the determinism of diabetic retinopathy.
changes (r = +0.008; R2 = 0.0001; p = .941), insignificant statisti- The number of hidden layers depends on the issue that will
cally. In the cases studied, by marking the ROC curves, it is found be resolved. In general, a single hidden layer is sufficient to solve
that the C/D (AUC = 0.700; IC95%: 0.565–0.835) and the mean de- most problems. However, for complex problems, up to three hid-
viation of the visual field (AUC = 0.770; IC95%: 0.657–0.863) enters den layers may need to be used. Typically, the number of input and
in the determinism of diabetic retinopathy with a weight of over output neurons corresponding to the number of input and output
70%, while the level of haemoglobin (AUC = 0.420; IC95%: 0.245– variables, respectively, is determined by the nature of the applica-
0.596) and intra-ocular pressure (AUC = 0.439; IC95%: 0.208–0.669) tion. Neurons of hidden layers play an important role in detecting
were not good predictors of diabetic retinopathy changes (Fig. 4). regularities and rules contained in the training pattern. Often, the
way of determining the appropriate number of hidden neurons is
the trial and error method. Accordingly, several models were built
3.2. Neural network modelling results with eighth inputs, one or two layers of hidden neurons and one
output, in order to find the best topology for the neural model.
Based on the statistical analysis of the database, the dataset Table 2 shows some developed ANN topologies with their per-
was found to be suitable for developing and training the neu- formance, represented by the mean square error (MSE) (Eq. 1), the
ral models, correlating the output parameter - the presence or correlation coefficient (r2 ) (Eq. 2) and percentage error (Ep ) (Eq. 3):
absence of diabetic retinopathy changes - DR (O) with input
parameters–glaucoma age (A), diabetes age (B), C/D ratio (C), gly- P N
cated haemoglobin (D), intraocular pressure (E), patient age (F), j=1 i=1 (di j − yi j )2
MSE = (1)
MD–mean deviation (H) and LENS appearance (G). N·P
The next step in the neural network modelling was the creation
of data sets for training and validation: 79 eyes were used in the where P is the number of the outputs (in this case, P = 1), N is
training stage (meaning 80%) and 20 were retained for the testing the amount of data, yij is the output value for i element with the
step (20%). processing of elements j, and dij is the desired output for i with
N. Anton Apreutesei et al. / Computer Methods and Programs in Biomedicine 154 (2018) 183–190 187
Fig. 5. Prediction of parameter O with different neural models in the validation stage. Patient eyes codes: 1- B. E.; 2-I. G.; 3- I. A.; 4-A. I.; 5-C. C.; 6-B. I.; 7-N. E.; 8-G. D.;
9-F. O.; 10-A. O.; 11- G. P.; 12- P. V; 13-C. A.; 14-I.G.; 15-C. F.; 16-C. C.; 17-C. E.; 18-C.G.; 19-T. M. and 20- C. F.
Table 3
Standard deviation values in the validation stage.
ogy, show that many of the authors are using neural networks Table 4
Different MLP and JEN topologies tested by inverse modelling.
built on the diagnostic glaucoma images or retinal diseases (visual
field, OCT). For the first time, in this manuscript, the data used No. Network topology MSE r2 Ep (%) Duration of the training
for the development of neural models are, in fact, the exact el- stage (min)
ements of diagnostic for both glaucoma and diabetic retinopathy. 1. MLP(8:8:1) 0.0 0 0466 0.997781 97.17 3.06
For direct comparison of our results with neural networks, multi- 2. MLP(8:16:1) 0.0 0 0245 0.998800 20.62 3.36
ple linear regression method (MLR) is also applied. This model was 3. MLP(8:24:1) 0.0 0 0217 0.998900 12.06 4.16
4. MLP(8:32:1) 0.0 0 0215 0.998900 9.33 3.07
obtained using the same database as for ANN model: 79 data were
5. MLP(8:40:1) 0.0 0 0214 0.998900 7.85 20.19
used to generate the model (training phase) and 20 dates were re- 6. MLP(8:48:1) 0.0 0 0215 0.998979 8.14 7.39
served for the validation stage. With MLR, the following relation 7. MLP(8:56:1) 0.0 0 0215 0.998974 11.03 7.35
resulted: 7. MLP(8:16:8:1) 0.0 0 0225 0.998920 13.00 23.49
8. MLP(8:24:8:1) 0.0 0 0220 0.998950 19.94 13.25
DR(O ) = − 0.069 + (0.00192 ∗ A ) + (0.0281 ∗ B ) − (0.188 ∗ C ) 9. MLP(8:24:16:1) 0.0 0 0214 0.998980 7.96 6.42
10. MLP(8:32:24:1) 0.0 0 0215 0.998978 9.50 17.43
− (0.0164 ∗ D ) + (0.00602∗E ) + (0.0 0 0525 ∗ F ) 11. MLP(8:40:32:1) 0.0 0 0216 0.998977 7.45 20.04
− (0.00545 ∗ G ) − (0.00491 ∗ H ) (5) 12. MLP(8:48:40:1) 0.0 0 0214 0.998980 7.32 16.03
13. MLP(8:56:48:1) 0.0 0 0214 0.998980 7.36 28.39
The relation (5) correlates the diabetic retinopathy changes - DR 14. JEN(8:16:1) 0.0 0 0 0 03 0.999998 5.08 5.22
15. JEN(8:24:1) 0.0 0 0 0 02 0.999998 1.37 6.31
(O) with parameters: glaucoma age (A), diabetes age (B), C/D ratio
16. JEN(8:32:1) 0.0 0 0 0 02 0.999999 1.15 7.21
(C), glycated haemoglobin (D), intraocular pressure (E), patient age 17. JEN(8:40:1) 0.0 0 0 0 01 0.999999 1.37 8.12
(F), MD - mean deviation (H) and LENS appearance (G). The model 18. JEN(8:48:1) 0.0 0 0 0 01 0.999997 2.89 8.56
was obtained using the same information as for the neural net- 19. JEN (8:16:8:1) 0.0 0 0 018 0.999912 35.66 6.33
work modelling: 79 eyes for the training phase. In the validation 20. JEN (8:24:16:1) 0.0 0 0 020 0.999951 10.18 8.28
21. JEN (8:32:24:1) 0.0 0 0 011 0.999949 13.16 9.40
stage, the probability of correct answers of the MLR model was
85% (17 correct answers from 20 possible), as in neural modelling
this probability was 95%. The standard deviation according to the
formula (4) for the DR prediction, in the validation stage for MLR, ing the output parameter with one of the input parameters. In in-
was calculated as 0.304826, a value much larger than the one ob- verse modelling, the output parameter was MD (O” ) and the fol-
tained from our neural models (Table 3). These results demonstrate lowing input variables were considered: glaucoma age (A”), dia-
that the neural model is more robust and accurate than other mod- betes age (B”), C/D ratio (C”), glycated haemoglobin (D”), intraocu-
els, particularly MLR. The same conclusion was obtained from the lar pressure (E”), patient age (F”), presence or absence of diabetic
studies of Kanhaiya and collaborators when they used artificial in- retinopathy changes - DR (G”) and LENS appearance (H”).
telligence tools to assess the risk of diabetic foot ulcers in patients The data which form the database was divided in training (79)
with diabetes mellitus type, using both multiple regressional anal- and validation (20) sets. Applying the trial and error method, sev-
ysis and artificial networks [21]. eral neural models with eight inputs were built, with one or two
To demonstrate the relationship between diabetes and primer intermediate layers of hidden neurons, and an output. Table 4
open-angle glaucoma, reverse modelling was carried out by replac- shows a series of neural networks with different topologies, of MLP
N. Anton Apreutesei et al. / Computer Methods and Programs in Biomedicine 154 (2018) 183–190 189
4. Discussions
a feed forward neural model having one hidden layer and 8 neu- [5] D. Dumitrescu, H. Costin, Teora Bucuresti (Eds.), Retele neuronale. Teorii si
rons, MLP(8:8:1). For this model, the probability to give correct an- Aplicatii, 1996.
[6] S. Curteanu, A. Dumitrescu, C. Mihailescu, B.C. Simionescu, The synthesis of
swers was 95% (i.e. 19 correct answers from 20 possible). For the polyacrylamide-based multicompomnent hydrogels. A neural network mod-
MLR model, the probability to give correct answers was 85% (17 elling, J. Macromol. Sci. Part A Pure Appl. Chem. A 46 (2008) 368–380.
positive answers from 20 possible). These results prove the neural [7] S. Curteanu, H. Cartwright, Neural networks applied in chemistry. I. Determi-
nation of the optimal topology of multilayer perceptron neural networks, J.
model is more robust and precise than model obtained with multi- Chemometr. 25 (2011) 527–549.
regression analysis. [8] K. Papik, B. Molnar, R. Schaefer, Z. Dombovari, Z. Tulassay, J. Feher, Application
In case of inverse neural network modelling, in order to prove of neural networks in medicine-a review. diagnostic and medical technology,
Med. Sci. Monit. 4 (1998) 538–546.
the relationship between glaucoma and diabetic retinopathy, with
[9] M. Huzum, D.V. Marţu, L. Rădulescu, S. Curteanu, Use of neural networks to
a confidence interval of ±15%, it was found that the model predict Eustachian tube permeability, J. Rom. Med. Dent. 14 (2010) 18–24.
JEN(8:32:1) showed the best results, only two values being outside [10] M.A. Simon, L. Alonso, A. Antón, A hybrid visual field classifier to support early
glaucoma diagnosis, Intel. Artif. Rev. Iberoam. Intel. Artif. 9 (2005) 9–17.
the chosen confidence interval.
[11] G.G. Gardner, D. Keating, T.H. Williamson, A.T. Elliottet, Automatic detection on
This study illustrates the fundamentals of building a neural diabetic retinopathy using an artificial neural network: a screening tool, Br. J.
model suitable for predicting the rate and degree of modification Ophthalmol. 80 (1996) 940–944.
in optic change, when both glaucoma and diabetes are present. [12] C. Bowd, K. Chan, L.M. Zangwill, M.H. Goldbaum, T.W. Lee, T.J. Sejnowski,
R.N. Weinreb, Comparing neural networks and linear discriminant functions
Special emphasis is placed on the quality of models and their abil- for glaucoma detection using confocal scanning laser ophthalmoscopy of the
ity to reproduce, by simulation, new behaviour, which was un- optic disc, Invest. Ophthalmol. Vis. Sci. 43 (2002) 3444–3454.
known in the training stage. [13] H. Parsaei, M.H. Moradi, R. Parsaei, Development and verification of artificial
neural network classifiers for eye diseases diagnosis, 14th ICBME, 2008.
[14] K. Nouri- Mahdavi, D. Hoffman, D. Gaasterland, J. Caprioli, Prediction of vi-
Conflict of interest sual field progression in glaucoma, Invest. Ophthalmol. Vis. Sci. 45 (2004)
4346–4351.
[15] M. García, C.I. Sánchez, M.I. López, D. Abásolo, R. Hornero, Neural network
We wish to confirm that there are no known conflicts of inter- based detection of hard exudates in retinal images, Comput. Methods Pro-
est associated with this publication and there has been no signifi- grams Biomed. 93 (2009) 9–19.
cant financial support for this work that could have influenced its [16] A. Giangiacomo, D. Garway-Heath, J. Caprioli, Diagnostic glaucoma progres-
sion: current practice and promising technologies, Curr. Opin. Ophthalmol. 17
outcome.
(2006) 153–162.
[17] G. Santos-García, E. Hernández Galilea, Using Artificial Neural Networks to
Acknowledgment Identify Glaucoma Stages. Cap.18. The Mystery of Glaucoma. Edited by Dr.
Tomas Kubena, 2011.
[18] A. Antón, L. Zangwill, A. Emdadi, R.N. Weinreb, Nerve fiber layer measurements
This work was supported by the “Program 4, Fundamental and with scanning laser polarimetry in ocular hypertension, Arch. Ophthalmol. 115
Border Research, Exploratory Research Projects” financed by UEFIS- (1997) 331–334.
CDI, project No. 51/2017. [19] M.H. Goldbaum, P.A. Sample, K. Chan, J. Williams, T.W. Lee, E. Blumenthal,
C.A. Girkin, L.M. Zangwill, C. Bowd, T. Sejnowski, R.N. Weinreb, Comparingma-
chine learning classifiers for diagnosing glaucoma from standard automated
Supplementary materials perimetry, Invest. Ophthalmol. Vis. Sci. 43 (2002) 162–169.
[20] M. Rigla, G. García-Sáez, B. Pons, M.E. Hernando, Artificial intelligence method-
ologies and their application to diabetes, J. Diabetes Sci. Technol. (2017),
Supplementary material associated with this article can be doi:10.1177/1932296817710475.
found, in the online version, at doi:10.1016/j.cmpb.2017.11.013. [21] K. Singh, V.K. Singh, N.K. Agrawal, S. Gupta, K. Singh, Association of Toll-like
receptor 4 polymorphisms with diabetic foot ulcers and application of artificial
References neural network in DFU risk assessment in type 2 diabetes patients, Biomed.
Res. Int. (2013) 318686, 9 pages.
[22] European Glaucoma Society Terminology and Guidelines for Glaucoma IV-nd
[1] M.O. Gordon, J.A. Beiser, J.D. Brandt, D.K. Heuer, E.J. Higginbotham, C.A. John-
edition 2014; Ch.2:2; pg. 79–89.
son, J.L. Keltner, J.P. Miller, R.K. 2nd Parrish, M.R. Wilson, M.A. Kass, The ocular
[23] International Council of Ophthalmology- ICO Guidelines for Diabetic Eye Care-
hypertension treatment Study: baseline factors that predict the onset of pri-
2014.
mary open-angle glaucoma, Arch. Ophthalmol. 120 (2002) 714–720.
[24] A. Erfanian, B. Mahmoud, Real-time ocular artefact suppression using recur-
[2] R. Varma, M. Ying-Lai, B.A. Francis, B.B. Nguyen, J. Deneen, M.R. Wilson,
rent neural network for electro-encephalogram based brain–computer inter-
S.P. Azen, Los Angeles latino eye study group: prevalence of open-angle glau-
face, Med. Biol. Eng. Comput. 43 (2005) 296–305.
coma and ocular hypertension in latinos: the Los Angeles latino eye study,
[25] X. Hu, H. Cammann, H.A. Meyer, K. Miller, K. Jung, C. Stephan, Artificial neu-
Ophthalmology 111 (2004) 1439–1448.
ral networks and prostate cancer—tools for diagnosis and management, Nature
[3] J.M. Tielsch, J. Katz, H.A. Quigley, J.C. Javitt, A. Sommer, Diabetes, intraocular
Rev. Urol. 10 (2013) 174–182.
pressure, and primary open-angle glaucoma in the Baltimore eye survey, Oph-
[26] A. Petrosian, D. Prokhorov, R. Homan, R. Dashei, D. Wunsch, Recurrent neural
thalmology 102 (1995) 48–53.
network based prediction of epileptic seizures in intra- and extracranial EEG,
[4] A. Hennis, S.Y. Wu, B. Nemesure, M.C. Leske, Barbados eye studies group: hy-
Neurocomputing 30 (20 0 0) 201–218.
pertension, diabetes, and longitudinal changes in intraocular pressure, Oph-
[27] F. Amato, A. López, E.M. Peña-Méndez, P. Vaňhara, A. Hampl, J. Havel, Artificial
thalmology 110 (2003) 908–914.
neural networks in medical diagnosis, J. Appl. Biomed. 11 (2013) 47–58.