Multiclass Classification of Retinal and Optic Nerve Disorders Using Time-Domain Features from Band-Separated PERG Signals
Abstract
Pattern Electroretinogram (PERG) signals offer critical insights into the functional status of retinal ganglion cells and are widely used for diagnosing optic nerve and retinal pathologies. While existing research has predominantly emphasized binary classification or full-spectrum signal analysis, limited studies have addressed the use of frequency band-based feature extraction in multiclass classification scenarios. This study introduces a novel approach that segments PERG signals into defined frequency bands and extracts a comprehensive set of time-domain features to support five-class classification. The dataset, originally comprising 15 diagnostic classes, was consolidated into five clinically relevant categories to ensure balanced representation. From each frequency band, more than 30 time-domain features were derived per eye, capturing key waveform characteristics. A consolidated dataset of five clinically relevant diagnostic classes have been used. Multiple machine learning models were evaluated, with AdaBoost-ECOC achieving the best performance: 99.11% ± 1.26 accuracy, 82.92% ± 0.59 precision, and 83.03% ± 0.55 F1-score. These results demonstrate the effectiveness and efficiency of frequency-based time-domain feature extraction for PERG signal classification.References
I. Fernández, R. Cuadrado-Asensio, Y. Larriba, C. Rueda, and R. M. Coco-Martín, ‘A comprehensive dataset of pattern electroretinograms for ocular electrophysiology research’, Sci. Data, vol. 11, no. 1, p. 1013, 2024.
J. V. Odom et al., ‘ISCEV standard for clinical visual evoked potentials (2009 update)’, Doc. Ophthalmol., vol. 120, pp. 111–119, 2010.
D. L. McCulloch et al., ‘ISCEV Standard for full-field clinical electroretinography (2015 update)’, Doc. Ophthalmol., vol. 130, no. 1, pp. 1–12, 2015.
S. K. S. K. Nataraj et al., ‘Statistical cross-correlation band features based thought controlled communication system’, AI Commun., vol. 8, no. 4, pp. 20–28, Aug. 2016, doi: 10.3233/AIC-160703.
R. Hamilton et al., ‘VEP estimation of visual acuity: a systematic review’, Doc. Ophthalmol., vol. 142, pp. 25–74, 2021.
D. C. Hood et al., ‘ISCEV standard for clinical multifocal electroretinography (mfERG)(2011 edition)’, Doc. Ophthalmol., vol. 124, pp. 1–13, 2012.
J. Bures, M. Petran, and J. Zachar, Electrophysiological methods in biological research. Academic Press, 2013.
R. N. Weinreb and P. T. Khaw, ‘Primary open-angle glaucoma’, Lancet, vol. 363, no. 9422, pp. 1711–1720, 2004.
N. V Thakor, ‘Biopotentials and electrophysiology measurement’, Meas. Instrumentation, Sensors Handb., vol. 74, 1999.
J. Rettinger, S. Schwarz, and W. Schwarz, Electrophysiology. Springer, 2022.
D. A. Thompson, M. Bach, J. J. McAnany, M. Šuštar Habjan, S. Viswanathan, and A. G. Robson, ‘ISCEV standard for clinical pattern electroretinography (2024 update)’, Doc. Ophthalmol., vol. 148, no. 2, pp. 75–85, 2024.
A. B. Suttle et al., ‘Assessment of the drug interaction potential and single‐and repeat‐dose pharmacokinetics of the BRAF inhibitor dabrafenib’, J. Clin. Pharmacol., vol. 55, no. 4, pp. 392–400, 2015.
G. A. Omura, ‘Progress in gynecologic cancer research: the Gynecologic Oncology Group experience’, in Seminars in oncology, 2008, vol. 35, no. 5, pp. 507–521.
V. Parisi, ‘Electrophysiological assessment of glaucomatous visual dysfunction during treatment with cytidine-5′-diphosphocholine (citicoline): a study of 8 years of follow-up’, Doc. Ophthalmol., vol. 110, pp. 91–102, 2005.
G. E. Holder, ‘Pattern electroretinography (PERG) and an integrated approach to visual pathway diagnosis’, Prog. Retin. Eye Res., vol. 20, no. 4, pp. 531–561, 2001.
M. Bach and M. B. Hoffmann, ‘Update on the pattern electroretinogram in glaucoma’, Optom. Vis. Sci., vol. 85, no. 6, pp. 386–395, 2008.
A. G. Robson et al., ‘ISCEV Standard for full-field clinical electroretinography (2022 update)’, Doc. Ophthalmol., vol. 144, no. 3, pp. 165–177, 2022.
A. L. Goldberger et al., ‘PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals’, Circulation, vol. 101, no. 23, pp. e215–e220, 2000.
M. Kulyabin, A. Zhdanov, A. Dolganov, M. Ronkin, V. Borisov, and A. Maier, ‘Enhancing electroretinogram classification with multi-wavelet analysis and visual transformer’, Sensors, vol. 23, no. 21, p. 8727, 2023.
S. Asanad and R. Karanjia, ‘Multifocal electroretinogram’, in StatPearls [Internet], StatPearls Publishing, 2022.
G. E. Holder, A. G. Robson, C. R. Hogg, M. Kurz-Levin, N. Lois, and A. C. Bird, ‘Pattern ERG: clinical overview, and some observations on associated fundus autofluorescence imaging in inherited maculopathy’, Doc. Ophthalmol., vol. 106, no. 1, p. 17, 2003.
C. Canedo, I. Fernández, R. M. Coco, R. Cuadrado, and C. Rueda, ‘Novel modeling proposals for the analysis of pattern electroretinogram signals’, in Statistical Methods at the Forefront of Biomedical Advances, Springer, 2023, pp. 255–273.
P. A. Constable, M. Bach, L. J. Frishman, B. G. Jeffrey, A. G. Robson, and I. S. for C. E. of V. http://www. iscev. org, ‘ISCEV Standard for clinical electro-oculography (2017 update)’, Doc. Ophthalmol., vol. 134, pp. 1–9, 2017.
E. J. Ahn, Y. I. Shin, Y. K. Kim, J. W. Jeoung, and K. H. Park, ‘Hemifield-based analysis of pattern electroretinography in normal subjects and patients with preperimetric glaucoma’, Sci. Rep., vol. 14, no. 1, p. 5116, 2024.
M. Bach et al., ‘ISCEV standard for clinical pattern electroretinography (PERG): 2012 update’, Doc. Ophthalmol., vol. 126, pp. 1–7, 2013.
A. Aykut, B. Akgün, A. S. Sezenöz, M. O. Sevik, and Ö. Şahin, ‘Diagnosing retinal disorders with artificial intelligence: the role of large language models in interpreting pattern electroretinography data’, J. Heal. Sci. Med., vol. 7, no. 5, pp. 538–542, 2024.
M. Kulyabin et al., ‘Synthetic Electroretinogram Signal Generation Using Conditional Generative Adversarial Network for Enhancing Classification of Autism Spectrum Disorder’, arXiv Prepr. arXiv2407.08166, 2024.
O. Garćıa-Alarćon, S. Puga-Guzḿan, and J. Moreno-Valenzuela, ‘On parameter identification of the Furuta pendulum’, Procedia Eng., vol. 35, pp. 77–84, 2012.
T. Harčarik, J. Bocko, and K. Masláková, ‘Frequency analysis of acoustic signal using the Fast Fourier Transformation in MATLAB’, Procedia Eng., vol. 48, pp. 199–204, 2012.
P. Monsalve et al., ‘Next generation PERG method: expanding the response dynamic range and capturing response adaptation’, Transl. Vis. Sci. Technol., vol. 6, no. 3, p. 5, 2017.
E. D. Übeyli, ‘Statistics over features: EEG signals analysis’, Comput. Biol. Med., vol. 39, no. 8, pp. 733–741, 2009.
DOI:
https://doi.org/10.31449/inf.v50i9.9657Downloads
Published
How to Cite
Issue
Section
License
Authors retain copyright in their work. By submitting to and publishing with Informatica, authors grant the publisher (Slovene Society Informatika) the non-exclusive right to publish, reproduce, and distribute the article and to identify itself as the original publisher.
All articles are published under the Creative Commons Attribution license CC BY 3.0. Under this license, others may share and adapt the work for any purpose, provided appropriate credit is given and changes (if any) are indicated.
Authors may deposit and share the submitted version, accepted manuscript, and published version, provided the original publication in Informatica is properly cited.
