Next Article in Journal
Application of Prandtl’s Theory in the Design of an Experimental Chamber for Static Pressure Measurements
Next Article in Special Issue
Detecting Phase-Synchrony Connectivity Anomalies in EEG Signals. Application to Dyslexia Diagnosis
Previous Article in Journal
Accurate Pupil Center Detection in Off-the-Shelf Eye Tracking Systems Using Convolutional Neural Networks
Previous Article in Special Issue
Detection of Mild Cognitive Impairment with MEG Functional Connectivity Using Wavelet-Based Neuromarkers
 
 
Article

Application of Dense Neural Networks for Detection of Atrial Fibrillation and Ranking of Augmented ECG Feature Set

1
Institute of Biophysics and Biomedical Engineering, Bulgarian Academy of Sciences, Acad. G. Bonchev Str. Bl 105, 1113 Sofia, Bulgaria
2
Department of Internal Diseases “Prof. St. Kirkovich”, Medical University of Sofia, 1431 Sofia, Bulgaria
*
Author to whom correspondence should be addressed.
Both authors contributed equally to this work.
Academic Editors: Andrés Ortiz García, Juan Manuel Gorriz and Javier Ramírez
Sensors 2021, 21(20), 6848; https://doi.org/10.3390/s21206848
Received: 14 September 2021 / Revised: 5 October 2021 / Accepted: 13 October 2021 / Published: 15 October 2021
(This article belongs to the Special Issue Smart Computing Systems for Biomedical Signal Processing)
Considering the significant burden to patients and healthcare systems globally related to atrial fibrillation (AF) complications, the early AF diagnosis is of crucial importance. In the view of prominent perspectives for fast and accurate point-of-care arrhythmia detection, our study optimizes an artificial neural network (NN) classifier and ranks the importance of enhanced 137 diagnostic ECG features computed from time and frequency ECG signal representations of short single-lead strips available in 2017 Physionet/CinC Challenge database. Based on hyperparameters’ grid search of densely connected NN layers, we derive the optimal topology with three layers and 128, 32, 4 neurons per layer ([email protected]), which presents maximal F1-scores for classification of Normal rhythms (0.883, 5076 strips), AF (0.825, 758 strips), Other rhythms (0.705, 2415 strips), Noise (0.618, 279 strips) and total F1 relevant to the CinC Challenge of 0.804, derived by five-fold cross-validation. [email protected] performs equally well with 137 to 32 features and presents tolerable reduction by about 0.03 to 0.06 points for limited input sets, including 8 and 16 features, respectively. The feature reduction is linked to effective application of a comprehensive method for computation of the feature map importance based on the weights of the activated neurons through the total path from input to specific output in DenseNet. The detailed analysis of 20 top-ranked ECG features with greatest importance to the detection of each rhythm and overall of all rhythms reveals DenseNet decision-making process, noticeably corresponding to the cardiologists’ diagnostic point of view. View Full-Text
Keywords: artificial neural network; ECG; PhysioNet Computing in Cardiology Challenge 2017 database; atrial fibrillation; arrhythmia detection; noise detection; feature importance; neuron weights; optimization; deep learning artificial neural network; ECG; PhysioNet Computing in Cardiology Challenge 2017 database; atrial fibrillation; arrhythmia detection; noise detection; feature importance; neuron weights; optimization; deep learning
Show Figures

Figure 1

MDPI and ACS Style

Krasteva, V.; Christov, I.; Naydenov, S.; Stoyanov, T.; Jekova, I. Application of Dense Neural Networks for Detection of Atrial Fibrillation and Ranking of Augmented ECG Feature Set. Sensors 2021, 21, 6848. https://doi.org/10.3390/s21206848

AMA Style

Krasteva V, Christov I, Naydenov S, Stoyanov T, Jekova I. Application of Dense Neural Networks for Detection of Atrial Fibrillation and Ranking of Augmented ECG Feature Set. Sensors. 2021; 21(20):6848. https://doi.org/10.3390/s21206848

Chicago/Turabian Style

Krasteva, Vessela, Ivaylo Christov, Stefan Naydenov, Todor Stoyanov, and Irena Jekova. 2021. "Application of Dense Neural Networks for Detection of Atrial Fibrillation and Ranking of Augmented ECG Feature Set" Sensors 21, no. 20: 6848. https://doi.org/10.3390/s21206848

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop