Spectral Analysis of Light-Adapted Electroretinograms in Neurodevelopmental Disorders: Classification with Machine Learning DOI Creative Commons
Paul A. Constable, Javier Orlando Pinzón-Arenas, Luís Roberto Mercado Díaz

et al.

Bioengineering, Journal Year: 2024, Volume and Issue: 12(1), P. 15 - 15

Published: Dec. 28, 2024

Electroretinograms (ERGs) show differences between typically developing populations and those with a diagnosis of autism spectrum disorder (ASD) or attention deficit/hyperactivity (ADHD). In series ERGs collected in ASD (n = 77), ADHD 43), + 21), control 137) groups, this analysis explores the use machine learning feature selection techniques to improve classification these clinically defined groups. Standard time domain signal features were evaluated different models. For classification, balanced accuracy (BA) 0.87 was achieved for male participants. ADHD, BA 0.84 female When three-group model (ASD, control) lower, at 0.70, fell further 0.53 when all groups included control). The findings support role ERG establishing broad two-group but model's performance depends upon sex is limited multiple classes are modeling.

Language: Английский

Electroretinogram Analysis Using a Short-Time Fourier Transform and Machine Learning Techniques DOI Creative Commons
Faisal B. Albasu, Mikhail Kulyabin, Aleksei Zhdanov

et al.

Bioengineering, Journal Year: 2024, Volume and Issue: 11(9), P. 866 - 866

Published: Aug. 26, 2024

Electroretinography (ERG) is a non-invasive method of assessing retinal function by recording the retina's response to brief flash light. This study focused on optimizing ERG waveform signal classification utilizing Short-Time Fourier Transform (STFT) spectrogram preprocessing with machine learning (ML) decision system. Several window functions different sizes and overlaps were compared enhance feature extraction concerning specific ML algorithms. The obtained spectrograms employed train deep models alongside manual for more classical models. Our findings demonstrated superiority Visual Transformer architecture Hamming function, showcasing its advantage in classification. Also, as result, we recommend RF algorithm scenarios necessitating extraction, particularly Boxcar (rectangular) or Bartlett functions. By elucidating optimal methodologies classification, this contributes advancing diagnostic capabilities analysis clinical settings.

Language: Английский

Citations

5
A Future Picture: A Review of Current Generative Adversarial Neural Networks in Vitreoretinal Pathologies and Their Future Potentials DOI Creative Commons

Raheem Remtulla,

Adam Samet, Merve Kulbay

et al.

Biomedicines, Journal Year: 2025, Volume and Issue: 13(2), P. 284 - 284

Published: Jan. 24, 2025

Machine learning has transformed ophthalmology, particularly in predictive and discriminatory models for vitreoretinal pathologies. However, generative modeling, especially adversarial networks (GANs), remains underexplored. GANs consist of two neural networks—the generator discriminator—that work opposition to synthesize highly realistic images. These synthetic images can enhance diagnostic accuracy, expand the capabilities imaging technologies, predict treatment responses. have already been applied fundus imaging, optical coherence tomography (OCT), fluorescein autofluorescence (FA). Despite their potential, face challenges reliability accuracy. This review explores GAN architecture, advantages over other deep models, clinical applications retinal disease diagnosis monitoring. Furthermore, we discuss limitations current propose novel combining with OCT, OCT-angiography, angiography, electroretinograms, visual fields, indocyanine green angiography.

Language: Английский

Citations

0
Comparison of Bioelectric Signals and Their Applications in Artificial Intelligence: A Review DOI Creative Commons

Juarez-Castro Flavio Alfonso,

Toledo-Rios Juan Salvador,

Marco Antonio Aceves-Fernández

et al.

Computers, Journal Year: 2025, Volume and Issue: 14(4), P. 145 - 145

Published: April 11, 2025

This review examines the role of various bioelectrical signals in conjunction with artificial intelligence (AI) and analyzes how these are utilized AI applications. The applications electroencephalography (EEG), electroretinography (ERG), electromyography (EMG), electrooculography (EOG), electrocardiography (ECG) diagnostic therapeutic systems focused on. Signal processing techniques discussed, relevant studies that have clinical research settings highlighted. Advances signal classification methodologies powered by significantly improved accuracy efficiency medical analysis. integration algorithms for real-time monitoring diagnosis, particularly personalized medicine, is emphasized. AI-driven approaches shown to potential enhance precision improve patient outcomes. However, further needed optimize models diverse environments fully exploit interaction between technologies.

Language: Английский

Citations

0
Synthetic electroretinogram signal generation using a conditional generative adversarial network DOI Creative Commons
Mikhail Kulyabin, Aleksei Zhdanov, Irene Lee

et al.

Documenta Ophthalmologica, Journal Year: 2025, Volume and Issue: unknown

Published: April 16, 2025

Abstract Purpose The electroretinogram (ERG) records the functional response of retina. In some neurological conditions, ERG waveform may be altered and could support biomarker discovery. heterogeneous or rare populations, where either large data sets availability a challenge, synthetic signals with Artificial Intelligence (AI) help to mitigate against these factors classification models. Methods This approach was tested using publicly available dataset real ERGs, n = 560 (ASD) 498 (Control) recorded at 9 different flash strengths from 18 ASD (mean age 12.2 ± 2.7 years) 31 Controls 11.8 3.3 that were augmented waveforms, generated through Conditional Generative Adversarial Network. Two deep learning models used classify groups only combined ERGs. One Time Series Transformer (with waveforms in their original form) second Visual model utilizing images wavelets derived Continuous Wavelet Transform Model performance classifying evaluated Balanced Accuracy (BA) as main outcome measure. Results BA improved 0.756 0.879 when ERGs included across all recordings for training Transformer. also achieved best 0.89 single strength 0.95 log cd s m −2 . Conclusions supports application AI improve group recordings.

Language: Английский

Citations

0
Spectral Analysis of Light-Adapted Electroretinograms in Neurodevelopmental Disorders: Classification with Machine Learning DOI Creative Commons
Paul A. Constable, Javier Orlando Pinzón-Arenas, Luís Roberto Mercado Díaz

et al.

Bioengineering, Journal Year: 2024, Volume and Issue: 12(1), P. 15 - 15

Published: Dec. 28, 2024

Electroretinograms (ERGs) show differences between typically developing populations and those with a diagnosis of autism spectrum disorder (ASD) or attention deficit/hyperactivity (ADHD). In series ERGs collected in ASD (n = 77), ADHD 43), + 21), control 137) groups, this analysis explores the use machine learning feature selection techniques to improve classification these clinically defined groups. Standard time domain signal features were evaluated different models. For classification, balanced accuracy (BA) 0.87 was achieved for male participants. ADHD, BA 0.84 female When three-group model (ASD, control) lower, at 0.70, fell further 0.53 when all groups included control). The findings support role ERG establishing broad two-group but model's performance depends upon sex is limited multiple classes are modeling.

Language: Английский

Citations

0