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
. 2022 Sep 22;10(10):1831.
doi: 10.3390/healthcare10101831.

Classification Algorithms Used in Predicting Glaucoma Progression

Filip Tarcoveanu  1 , Florin Leon  2 , Silvia Curteanu  3 , Dorin Chiselita  1 , Camelia Margareta Bogdanici  1 , Nicoleta Anton  1
Affiliations

Classification Algorithms Used in Predicting Glaucoma Progression

Filip Tarcoveanu et al. Healthcare (Basel). .

Abstract

In this paper, various machine learning algorithms were used in order to predict the evolution of open-angle glaucoma (POAG). The datasets were built containing clinical observations and objective measurements made at the Countess of Chester Hospital in the UK and at the "St. Spiridon" Hospital of Iași, Romania. Using these datasets, different classification problems were proposed. The evaluation of glaucoma progression was conducted based on parameters such as VFI (Visual field index), MD (Mean Deviation), PSD (Pattern standard deviation), and RNFL (Retinal Nerve Fiber Layer). As classification tools, the following algorithms were used: Multilayer Perceptron, Random Forest, Random Tree, C4.5, k-Nearest Neighbors, Support Vector Machine, and Non-Nested Generalized Exemplars. The best results, with an accuracy of over 90%, were obtained with Multilayer Perceptron and Random Forest algorithms. The NNGE algorithm also proved very useful in creating a hierarchy of the input values according to their influence (weight) on the considered outputs. On the other hand, the decision tree algorithms gave us insight into the logic used in their classification, which is of practical importance in obtaining additional information regarding the rationale behind a certain rule or decision.

Keywords: artificial intelligence; classification algorithms; glaucoma; machine learning; predictions.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Inputs and outputs considered in the 4 problems created to predict glaucoma evolution.
Figure 2
Figure 2
Selected inputs for predicting glaucoma progression for the modified dataset.
Figure 3
Figure 3
The decision tree generated by the C4.5 algorithm.
Figure 4
Figure 4
Decision tree generated by the Random Tree algorithm.
Figure 5
Figure 5
Decision tree of the C4.5 algorithm for predicting treatment change.
Figure 6
Figure 6
Results of C4.5 algorithm to predict diabetic retinopathy.
Figure 7
Figure 7
Results of the use of Random tree algorithm to predict diabetic retinopathy.
See this image and copyright information in PMC

References

    1. Bryson O., Muata K., Kendall G. An exploration of a set of entropy-based hybrid splitting methods for decision tree induction. J. Database Manag. 2004;15:1–28. doi: 10.4018/jdm.2004070101. - DOI
    1. Akpan U.I., Starkey A. Review of classification algorithms with changing inter-class distances. Mach. Learn. Appl. 2021;4:100031. doi: 10.1016/j.mlwa.2021.100031. - DOI
    1. Papadopoulos A., Manolopoulos Y. Nearest Neighbor Search: A Database Perspective. Springer; New York, NY, USA: 2004.
    1. Lee P.M. In: Bayesian Statistics: An Introduction. 3rd ed. Peter M., editor. Arnold Publishers; London, UK: 2004.
    1. Jensen F. Bayesian Networks and Decision Graphs. Springer; Berlin/Heidelberg, Germany: 2001. Decision Graphs. Statistics for Engineering and Information Science.