Convolutional Neural Networks for Mechanistic Driver Detection in Atrial Fibrillation
The maintaining and initiating mechanisms of atrial fibrillation (AF) remain controversial. Deep learning is emerging as a powerful tool to better understand AF and improve its treatment, which remains suboptimal. This paper aims to provide a solution to automatically identify rotational activity dr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | International Journal of Molecular Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1422-0067/23/8/4216 |
| _version_ | 1797434566933217280 |
|---|---|
| author | Gonzalo Ricardo Ríos-Muñoz Francisco Fernández-Avilés Ángel Arenal |
| author_facet | Gonzalo Ricardo Ríos-Muñoz Francisco Fernández-Avilés Ángel Arenal |
| author_sort | Gonzalo Ricardo Ríos-Muñoz |
| collection | DOAJ |
| description | The maintaining and initiating mechanisms of atrial fibrillation (AF) remain controversial. Deep learning is emerging as a powerful tool to better understand AF and improve its treatment, which remains suboptimal. This paper aims to provide a solution to automatically identify rotational activity drivers in endocardial electrograms (EGMs) with convolutional recurrent neural networks (CRNNs). The CRNN model was compared with two other state-of-the-art methods (SimpleCNN and attention-based time-incremental convolutional neural network (ATI-CNN)) for different input signals (unipolar EGMs, bipolar EGMs, and unipolar local activation times), sampling frequencies, and signal lengths. The proposed CRNN obtained a detection score based on the Matthews correlation coefficient of 0.680, an ATI-CNN score of 0.401, and a SimpleCNN score of 0.118, with bipolar EGMs as input signals exhibiting better overall performance. In terms of signal length and sampling frequency, no significant differences were found. The proposed architecture opens the way for new ablation strategies and driver detection methods to better understand the AF problem and its treatment. |
| first_indexed | 2024-03-09T10:34:10Z |
| format | Article |
| id | doaj.art-725eab5b280a440cb00589c5b71c6f2c |
| institution | Directory Open Access Journal |
| issn | 1661-6596 1422-0067 |
| language | English |
| last_indexed | 2024-03-09T10:34:10Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Molecular Sciences |
| spelling | doaj.art-725eab5b280a440cb00589c5b71c6f2c2023-12-01T21:03:02ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672022-04-01238421610.3390/ijms23084216Convolutional Neural Networks for Mechanistic Driver Detection in Atrial FibrillationGonzalo Ricardo Ríos-Muñoz0Francisco Fernández-Avilés1Ángel Arenal2Department of Cardiology, Instituto de Investigación Sanitaria Gregorio Marañón (IiSGM), Hospital General Universitario Gregorio Marañón, 28007 Madrid, SpainDepartment of Cardiology, Instituto de Investigación Sanitaria Gregorio Marañón (IiSGM), Hospital General Universitario Gregorio Marañón, 28007 Madrid, SpainDepartment of Cardiology, Instituto de Investigación Sanitaria Gregorio Marañón (IiSGM), Hospital General Universitario Gregorio Marañón, 28007 Madrid, SpainThe maintaining and initiating mechanisms of atrial fibrillation (AF) remain controversial. Deep learning is emerging as a powerful tool to better understand AF and improve its treatment, which remains suboptimal. This paper aims to provide a solution to automatically identify rotational activity drivers in endocardial electrograms (EGMs) with convolutional recurrent neural networks (CRNNs). The CRNN model was compared with two other state-of-the-art methods (SimpleCNN and attention-based time-incremental convolutional neural network (ATI-CNN)) for different input signals (unipolar EGMs, bipolar EGMs, and unipolar local activation times), sampling frequencies, and signal lengths. The proposed CRNN obtained a detection score based on the Matthews correlation coefficient of 0.680, an ATI-CNN score of 0.401, and a SimpleCNN score of 0.118, with bipolar EGMs as input signals exhibiting better overall performance. In terms of signal length and sampling frequency, no significant differences were found. The proposed architecture opens the way for new ablation strategies and driver detection methods to better understand the AF problem and its treatment.https://www.mdpi.com/1422-0067/23/8/4216atrial fibrillationartificial intelligencerotorsarrhythmiascardiologymachine learning |
| spellingShingle | Gonzalo Ricardo Ríos-Muñoz Francisco Fernández-Avilés Ángel Arenal Convolutional Neural Networks for Mechanistic Driver Detection in Atrial Fibrillation International Journal of Molecular Sciences atrial fibrillation artificial intelligence rotors arrhythmias cardiology machine learning |
| title | Convolutional Neural Networks for Mechanistic Driver Detection in Atrial Fibrillation |
| title_full | Convolutional Neural Networks for Mechanistic Driver Detection in Atrial Fibrillation |
| title_fullStr | Convolutional Neural Networks for Mechanistic Driver Detection in Atrial Fibrillation |
| title_full_unstemmed | Convolutional Neural Networks for Mechanistic Driver Detection in Atrial Fibrillation |
| title_short | Convolutional Neural Networks for Mechanistic Driver Detection in Atrial Fibrillation |
| title_sort | convolutional neural networks for mechanistic driver detection in atrial fibrillation |
| topic | atrial fibrillation artificial intelligence rotors arrhythmias cardiology machine learning |
| url | https://www.mdpi.com/1422-0067/23/8/4216 |
| work_keys_str_mv | AT gonzaloricardoriosmunoz convolutionalneuralnetworksformechanisticdriverdetectioninatrialfibrillation AT franciscofernandezaviles convolutionalneuralnetworksformechanisticdriverdetectioninatrialfibrillation AT angelarenal convolutionalneuralnetworksformechanisticdriverdetectioninatrialfibrillation |