This study investigates the use of atrioventricular (AV) synchronization as an important diagnost... more This study investigates the use of atrioventricular (AV) synchronization as an important diagnostic criterion for atrial fibrillation and flutter (AF) using one to twelve ECG leads. Heart rate, lead-specific AV conduction time, and P-/f-wave amplitude were evaluated by three representative ECG metrics (mean value, standard deviation), namely RR-interval (RRi-mean, RRi-std), PQ-interval (PQi-mean, PQI-std), and PQ-amplitude (PQa-mean, PQa-std), in 71,545 standard 12-lead ECG records from the six largest PhysioNet CinC Challenge 2021 databases. Two rhythm classes were considered (AF, non-AF), randomly assigning records into training (70%), validation (20%), and test (10%) datasets. In a grid search of 19, 55, and 83 dense neural network (DenseNet) architectures and five independent training runs, we optimized models for one-lead, six-lead (chest or limb), and twelve-lead input features. Lead-set performance and SHapley Additive exPlanations (SHAP) input feature importance were evaluat...
Objective of this preliminary study is to propose a method to assess the status of autonomic nerv... more Objective of this preliminary study is to propose a method to assess the status of autonomic nervous regulation and adaptation reserves of the body in patients with multivessel coronary artery disease (MCAD) in the preoperative and early postoperative period after CABG. A modified Indicator of the Activity of Regulatory Systems (IARS) has been used, whose value is determined by the estimated 5 HRV indices: heart rate (HR), standard deviation of examined normal RR interval (SDNN), geometrical HRV index, low frequency (LF) and very low frequency (VLF) bands of total HRV spectrum. The results show: i. Significantly higher sympathetic tone towards the parasympathetic contour preoperative (p <;0.001) and postoperative (p <;0.0001), and this prevalence increases postoperative; ii. Parasympathetic tone is moderately suppressed preoperative and to a greater extend postoperative (p <;0.05); iii. Compared to the moderate stress of the regulatory systems preoperative (IASR = 4.07), in...
Reliable and correct external electrocardiogram (ECG) signal analysis is of crucial importance fo... more Reliable and correct external electrocardiogram (ECG) signal analysis is of crucial importance for further development of automatic external defibrillators (AED) and their use by non-specialists. We proposed and evaluate a set of ECG parameters, derived from the output signal of a band-pass digital filter and from an in-house developed wave detection method. The extracted parameters were evaluated by means of discriminant analysis. It attained specificity between 92.1% and 95.4% and sensitivity between 96.8% and 93.4% respectively for different combinations of the proposed parameters. The parameter evaluation and the detection ability assessment were performed on ECG recordings from the widely recognized databases of the American Heart Association (AHA) and Massachusetts Institute of Technology (MIT).
High performance of the shock advisory analysis of the electrocardiogram (ECG) during cardiopulmo... more High performance of the shock advisory analysis of the electrocardiogram (ECG) during cardiopulmonary resuscitation (CPR) in out-of-hospital cardiac arrest (OHCA) is important for better management of the resuscitation protocol. It should provide fewer interruptions of chest compressions (CC) for non-shockable organized rhythms (OR) and Asystole, or prompt CC stopping for early treatment of shockable ventricular fibrillation (VF). Major disturbing factors are strong CC artifacts corrupting raw ECG, which we aimed to analyze with optimized end-to-end convolutional neural network (CNN) without pre-filtering or additional sensors. The hyperparameter random search of 1500 CNN models with 2–7 convolutional layers, 5–50 filters and 5–100 kernel sizes was done on large databases from independent OHCA interventions for training (3001 samples) and validation (2528 samples). The best model, named CNN3-CC-ECG network with three convolutional layers (filters@kernels: 5@5,25@20,50@20) presented ...
Considering the significant burden to patients and healthcare systems globally related to atrial ... more 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 (DenseNet-3@128-32-4), 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. Dense...
Deep neural networks (DNN) are state-of-the-art machine learning algorithms that can be learned t... more Deep neural networks (DNN) are state-of-the-art machine learning algorithms that can be learned to self-extract significant features of the electrocardiogram (ECG) and can generally provide high-output diagnostic accuracy if subjected to robust training and optimization on large datasets at high computational cost. So far, limited research and optimization of DNNs in shock advisory systems is found on large ECG arrhythmia databases from out-of-hospital cardiac arrests (OHCA). The objective of this study is to optimize the hyperparameters (HPs) of deep convolutional neural networks (CNN) for detection of shockable (Sh) and nonshockable (NSh) rhythms, and to validate the best HP settings for short and long analysis durations (2–10 s). Large numbers of (Sh + NSh) ECG samples were used for training (720 + 3170) and validation (739 + 5921) from Holters and defibrillators in OHCA. An end-to-end deep CNN architecture was implemented with one-lead raw ECG input layer (5 s, 125 Hz, 2.5 uV/LS...
This study presents a 2-stage heartbeat classifier of supraventricular (SVB) and ventricular (VB)... more This study presents a 2-stage heartbeat classifier of supraventricular (SVB) and ventricular (VB) beats. Stage 1 makes computationally-efficient classification of SVB-beats, using simple correlation threshold criterion for finding close match with a predominant normal (reference) beat template. The non-matched beats are next subjected to measurement of 20 basic features, tracking the beat and reference template morphology and RR-variability for subsequent refined classification in SVB or VB-class by Stage 2. Four linear classifiers are compared: cluster, fuzzy, linear discriminant analysis (LDA) and classification tree (CT), all subjected to iterative training for selection of the optimal feature space among extended 210-sized set, embodying interactive second-order effects between 20 independent features. The optimization process minimizes at equal weight the false positives in SVB-class and false negatives in VB-class. The training with European ST-T, AHA, MIT-BIH Supraventricular...
Nowadays the application of automatic external defibrillators (AEDs) becomes a widespread practic... more Nowadays the application of automatic external defibrillators (AEDs) becomes a widespread practice for early treatment of out-of-hospital cardiac arrest patients. A reliable recognition of life-threatening cardiac arrhythmias is required. However, it may be impeded by artifacts, which compromise the quality of the electrocardiogram (ECG). The aim of this study was to develop software procedures for detection of some typical for AED application artifacts, such as: (i) amplifier saturation; (ii) baseline wander; (iii) single steep and high- amplitude artifacts; (iv) tremor. The developed real-time operating procedures were synchronized with the implemented algorithm for ventricular fibrillation detection. Thus, the in-time detection of significant artifacts would prevent from a compromised shock-advisory decision. The presented algorithm was developed in Matlab environment. It was tested with ECG recordings from an out-of-hospital database, which contains various types of noises and d...
The morphological and rhythm analysis of the electrocardiogram (ECG) is based on ventricular beat... more The morphological and rhythm analysis of the electrocardiogram (ECG) is based on ventricular beats detection, wave parameters measurement, as amplitudes, widths, polarities, intervals and relations between them, and a subsequent classification supporting the diagnostic process. Number of algorithms for detection and classification of the QRS complexes have been developed by researchers in the Centre of Biomedical Engineering - Bulgarian Academy of Sciences, and are reviewed in this material. Combined criteria have been introduced dealing with the QRS areas and amplitudes, the waveshapes evaluated by steep slopes and sharp peaks, vectorcardiographic (VCG) loop descriptors, RR intervals irregularities. Algorithms have been designed for application on a single ECG lead, a synthesized lead derived by multichannel synchronous recordings, or simultaneous multilead analysis. Some approaches are based on templates matching, cross-correlation or rely on a continuous updating of adaptive thre...
This study investigates the use of atrioventricular (AV) synchronization as an important diagnost... more This study investigates the use of atrioventricular (AV) synchronization as an important diagnostic criterion for atrial fibrillation and flutter (AF) using one to twelve ECG leads. Heart rate, lead-specific AV conduction time, and P-/f-wave amplitude were evaluated by three representative ECG metrics (mean value, standard deviation), namely RR-interval (RRi-mean, RRi-std), PQ-interval (PQi-mean, PQI-std), and PQ-amplitude (PQa-mean, PQa-std), in 71,545 standard 12-lead ECG records from the six largest PhysioNet CinC Challenge 2021 databases. Two rhythm classes were considered (AF, non-AF), randomly assigning records into training (70%), validation (20%), and test (10%) datasets. In a grid search of 19, 55, and 83 dense neural network (DenseNet) architectures and five independent training runs, we optimized models for one-lead, six-lead (chest or limb), and twelve-lead input features. Lead-set performance and SHapley Additive exPlanations (SHAP) input feature importance were evaluat...
Objective of this preliminary study is to propose a method to assess the status of autonomic nerv... more Objective of this preliminary study is to propose a method to assess the status of autonomic nervous regulation and adaptation reserves of the body in patients with multivessel coronary artery disease (MCAD) in the preoperative and early postoperative period after CABG. A modified Indicator of the Activity of Regulatory Systems (IARS) has been used, whose value is determined by the estimated 5 HRV indices: heart rate (HR), standard deviation of examined normal RR interval (SDNN), geometrical HRV index, low frequency (LF) and very low frequency (VLF) bands of total HRV spectrum. The results show: i. Significantly higher sympathetic tone towards the parasympathetic contour preoperative (p <;0.001) and postoperative (p <;0.0001), and this prevalence increases postoperative; ii. Parasympathetic tone is moderately suppressed preoperative and to a greater extend postoperative (p <;0.05); iii. Compared to the moderate stress of the regulatory systems preoperative (IASR = 4.07), in...
Reliable and correct external electrocardiogram (ECG) signal analysis is of crucial importance fo... more Reliable and correct external electrocardiogram (ECG) signal analysis is of crucial importance for further development of automatic external defibrillators (AED) and their use by non-specialists. We proposed and evaluate a set of ECG parameters, derived from the output signal of a band-pass digital filter and from an in-house developed wave detection method. The extracted parameters were evaluated by means of discriminant analysis. It attained specificity between 92.1% and 95.4% and sensitivity between 96.8% and 93.4% respectively for different combinations of the proposed parameters. The parameter evaluation and the detection ability assessment were performed on ECG recordings from the widely recognized databases of the American Heart Association (AHA) and Massachusetts Institute of Technology (MIT).
High performance of the shock advisory analysis of the electrocardiogram (ECG) during cardiopulmo... more High performance of the shock advisory analysis of the electrocardiogram (ECG) during cardiopulmonary resuscitation (CPR) in out-of-hospital cardiac arrest (OHCA) is important for better management of the resuscitation protocol. It should provide fewer interruptions of chest compressions (CC) for non-shockable organized rhythms (OR) and Asystole, or prompt CC stopping for early treatment of shockable ventricular fibrillation (VF). Major disturbing factors are strong CC artifacts corrupting raw ECG, which we aimed to analyze with optimized end-to-end convolutional neural network (CNN) without pre-filtering or additional sensors. The hyperparameter random search of 1500 CNN models with 2–7 convolutional layers, 5–50 filters and 5–100 kernel sizes was done on large databases from independent OHCA interventions for training (3001 samples) and validation (2528 samples). The best model, named CNN3-CC-ECG network with three convolutional layers (filters@kernels: 5@5,25@20,50@20) presented ...
Considering the significant burden to patients and healthcare systems globally related to atrial ... more 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 (DenseNet-3@128-32-4), 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. Dense...
Deep neural networks (DNN) are state-of-the-art machine learning algorithms that can be learned t... more Deep neural networks (DNN) are state-of-the-art machine learning algorithms that can be learned to self-extract significant features of the electrocardiogram (ECG) and can generally provide high-output diagnostic accuracy if subjected to robust training and optimization on large datasets at high computational cost. So far, limited research and optimization of DNNs in shock advisory systems is found on large ECG arrhythmia databases from out-of-hospital cardiac arrests (OHCA). The objective of this study is to optimize the hyperparameters (HPs) of deep convolutional neural networks (CNN) for detection of shockable (Sh) and nonshockable (NSh) rhythms, and to validate the best HP settings for short and long analysis durations (2–10 s). Large numbers of (Sh + NSh) ECG samples were used for training (720 + 3170) and validation (739 + 5921) from Holters and defibrillators in OHCA. An end-to-end deep CNN architecture was implemented with one-lead raw ECG input layer (5 s, 125 Hz, 2.5 uV/LS...
This study presents a 2-stage heartbeat classifier of supraventricular (SVB) and ventricular (VB)... more This study presents a 2-stage heartbeat classifier of supraventricular (SVB) and ventricular (VB) beats. Stage 1 makes computationally-efficient classification of SVB-beats, using simple correlation threshold criterion for finding close match with a predominant normal (reference) beat template. The non-matched beats are next subjected to measurement of 20 basic features, tracking the beat and reference template morphology and RR-variability for subsequent refined classification in SVB or VB-class by Stage 2. Four linear classifiers are compared: cluster, fuzzy, linear discriminant analysis (LDA) and classification tree (CT), all subjected to iterative training for selection of the optimal feature space among extended 210-sized set, embodying interactive second-order effects between 20 independent features. The optimization process minimizes at equal weight the false positives in SVB-class and false negatives in VB-class. The training with European ST-T, AHA, MIT-BIH Supraventricular...
Nowadays the application of automatic external defibrillators (AEDs) becomes a widespread practic... more Nowadays the application of automatic external defibrillators (AEDs) becomes a widespread practice for early treatment of out-of-hospital cardiac arrest patients. A reliable recognition of life-threatening cardiac arrhythmias is required. However, it may be impeded by artifacts, which compromise the quality of the electrocardiogram (ECG). The aim of this study was to develop software procedures for detection of some typical for AED application artifacts, such as: (i) amplifier saturation; (ii) baseline wander; (iii) single steep and high- amplitude artifacts; (iv) tremor. The developed real-time operating procedures were synchronized with the implemented algorithm for ventricular fibrillation detection. Thus, the in-time detection of significant artifacts would prevent from a compromised shock-advisory decision. The presented algorithm was developed in Matlab environment. It was tested with ECG recordings from an out-of-hospital database, which contains various types of noises and d...
The morphological and rhythm analysis of the electrocardiogram (ECG) is based on ventricular beat... more The morphological and rhythm analysis of the electrocardiogram (ECG) is based on ventricular beats detection, wave parameters measurement, as amplitudes, widths, polarities, intervals and relations between them, and a subsequent classification supporting the diagnostic process. Number of algorithms for detection and classification of the QRS complexes have been developed by researchers in the Centre of Biomedical Engineering - Bulgarian Academy of Sciences, and are reviewed in this material. Combined criteria have been introduced dealing with the QRS areas and amplitudes, the waveshapes evaluated by steep slopes and sharp peaks, vectorcardiographic (VCG) loop descriptors, RR intervals irregularities. Algorithms have been designed for application on a single ECG lead, a synthesized lead derived by multichannel synchronous recordings, or simultaneous multilead analysis. Some approaches are based on templates matching, cross-correlation or rely on a continuous updating of adaptive thre...
Uploads
Papers by Vessela Krasteva