DOAJ (DOAJ: Directory of Open Access Journals), Dec 1, 2014
This paper presents an ECG database, named 'PacedECGdb' (available at http://biomed.bas.bg/bioaut... more This paper presents an ECG database, named 'PacedECGdb' (available at http://biomed.bas.bg/bioautomation/2014/vol_18.4/files/PacedECGdb.zip), which contains different arrhythmias generated by HKP (Heidelberger Praxisklinik) simulator, combined with artificially superimposed pacing pulses that cover the wide ranges of rising edge (from <10 µs to 100 µs) and total pulse durations (from 100 µs to 2 ms) and correspond to various pacemaker modes. It involves a total number of 1404 recordings-780 representing 'pure' ECG with pacing pulses and 624 that comprise paced ECGs corrupted by tremor. The signals are recorded with 9.81 µV/LSB amplitude resolution at 128 kHz sampling rate in order to preserve the steep raising and trailing edges of the pace pulses. To the best of our knowledge, 'PacedECGdb' is the first publicly available paced ECG database. It could be used for development and testing of methods for pace detection in the ECG. The existence of ECGs corrupted by tremor (the only physiological noise that could compromise the methods for pacing pulses detection) is an advantage, since such signals could be applied to define the signal-to-noise level for correct operation of the algorithm, or for improvement of the noise immunity of a method that is under development. The open access of the database makes it suitable for comparative studies including different algorithms.
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
The paper presents a prototype of ECG simulator, which may be a beneficial tool in designing and ... more The paper presents a prototype of ECG simulator, which may be a beneficial tool in designing and debugging of automatic diagnosis software methods implemented in real ECG devices. The main advantages of the proposed simulator are both the expanded memory capacity and the easy approach for reconfiguration of the memory content, data format and sampling frequency.
Traditional means for identity validation (PIN codes, passwords), and physiological and behaviora... more Traditional means for identity validation (PIN codes, passwords), and physiological and behavioral biometric characteristics (fingerprint, iris, and speech) are susceptible to hacker attacks and/or falsification. This paper presents a method for person verification/identification based on correlation of present-to-previous limb ECG leads: I (I), II (II), calculated from them first principal ECG component (PCA), linear and nonlinear combinations between I , II , and PCA. For the verification task, the one-toone scenario is applied and threshold values for I , II , and PCA and their combinations are derived. The identification task supposes one-to-many scenario and the tested subject is identified according to the maximal correlation with a previously recorded ECG in a database. The population based ECG-ILSA database of 540 patients (147 healthy subjects, 175 patients with cardiac diseases, and 218 with hypertension) has been considered. In addition a common reference PTB dataset (14 healthy individuals) with short time interval between the two acquisitions has been taken into account. The results on ECG-ILSA database were satisfactory with healthy people, and there was not a significant decrease in nonhealthy patients, demonstrating the robustness of the proposed method. With PTB database, the method provides an identification accuracy of 92.9% and a verification sensitivity and specificity of 100% and 89.9%.
This study aims to test the usability of the transthoracic impedance cardiogram (ICG) for assessm... more This study aims to test the usability of the transthoracic impedance cardiogram (ICG) for assessment of the quality of myocardial contractions in atrial fibrillation (AFIB) vs. sinus rhythm (SR), using signals recorded via defibrillation pads during external cardioversion (ECV). Data from 88 patients with persistent AFIB who received planned ECV are processed. AFIB is treated with cardioverter/defibrillator DG4000 (Schiller Médical, France) using a non-escalating protocol 200J/200J/200J. Successful ECV is defined as restoration of SR for >1min. The electrocardiogram (ECG), thoracic baseline impedance (Z) and dynamic impedance components dZ, dZ/dt captured via self-adhesive pads in anteroapical position are processed. Heartbeat contractions are evaluated by several measures extracted from the mean ICG patterns during systole: from dZ pattern-ICG (peak amplitude, range, area); from dZ/dt pattern-ICG velocity (peak, range, area) and left ventricular ejection time (LVET). The hemodynamical indices measured before and after ECV are: mean heart rate over 2 minutes (HR), standard deviation of HR (HRV), systolic (SysBP) and diastolic (DiaBP) blood pressure. When the rhythm converts from AFIB to SR (74 patients), all measures on dZ, dZ/dt patterns significantly increase: dZ (64-102%), dZ/dt (31-67%), LVET (18%), p < 0.05. Significant decrease of HR (-36%), HRV (-53%), SysBP (-11%) and DiaBP (-19%) are also observed. Unsuccessful ECVs without conversion to SR (14 patients) are, however, associated with non-significant increase of dZ (10-21%), dZ/dt (0.3-29%), LVET (9%), p > 0.05 when comparing pre-shock AFIB vs. post-shock AFIB. No clear change in HR (-9%) and HRV (6%), and slight decrease of SysBP (-10%) and DiaBP (-8%) are observed. The level of improvement of cardiac output quality in post-shock SR vs. pre-shock AFIB as estimated by ICG is related to a set of more than 60 clinical and hemodynamical parameters.
The automatic external defibrillator (AED) is a lifesaving device, which processes and analyses t... more The automatic external defibrillator (AED) is a lifesaving device, which processes and analyses the electrocardiogram (ECG) and delivers a defibrillation shock to terminate ventricular fibrillation or tachycardia above 180 bpm. The built-in algorithm for ECG analysis has to discriminate between shockable and non-shockable rhythms and its accuracy, represented by sensitivity and specificity, is aimed at approaching the maximum values of 100%. An algorithm for VF/VT detection is proposed using a band-pass digital filter with integer coefficients, which is very simple to implement in real-time operation. A branch for wave detection is activated for heart rate measurement and an auxiliary parameter calculation. The method was tested with ECG records from the widely recognized databases of the American Heart Association (AHA) and the Massachusetts Institute of Technology (MIT). A sensitivity of 95.93% and a specificity of 94.38% were obtained.
Chest compressions during cardiopulmonary resuscitation (CPR) induce artifacts in the ECG that ma... more Chest compressions during cardiopulmonary resuscitation (CPR) induce artifacts in the ECG that may provoque inaccurate rhythm classification by the algorithm of the defibrillator. The objective of this study was to design an algorithm to produce reliable shock/no-shock decisions during CPR using convolutional neural networks (CNN). A total of 3319 ECG segments of 9 s extracted during chest compressions were used, whereof 586 were shockable and 2733 nonshockable. Chest compression artifacts were removed using a Recursive Least Squares (RLS) filter, and the filtered ECG was fed to a CNN classifier with three convolutional blocks and two fully connected layers for the shock/no-shock classification. A 5-fold cross validation architecture was adopted to train/test the algorithm, and the proccess was repeated 100 times to statistically characterize the performance. The proposed architecture was compared to the most accurate algorithms that include handcrafted ECG features and a random forest classifier (baseline model). The median (90% confidence interval) sensitivity, specificity, accuracy and balanced accuracy of the method were 95.8% (94.6-96.8), 96.1% (95.8-96.5), 96.1% (95.7-96.4) and 96.0% (95.5-96.5), respectively. The proposed algorithm outperformed the baseline model by 0.6-points in accuracy. This new approach shows the potential of deep learning methods to provide reliable diagnosis of the cardiac rhythm without interrupting chest compression therapy.
Human identification (ID) is a biometric task, comparing single input sample to many stored templ... more Human identification (ID) is a biometric task, comparing single input sample to many stored templates to identify an individual in a reference database. This paper aims to present the perspectives of personalized heartbeat pattern for reliable ECG-based identification. The investigations are using a database with 460 pairs of 12-lead resting electrocardiograms (ECG) with 10-s durations recorded at time-instants T1 and T2 > T1 + 1 year. Intra-subject long-term ECG stability and inter-subject variability of personalized PQRST (500 ms) and QRS (100 ms) patterns is quantified via cross-correlation, amplitude ratio and pattern matching between T1 and T2 using 7 features × 12-leads. Single and multi-lead ID models are trained on the first 230 ECG pairs. Their validation on 10, 20, ... 230 reference subjects (RS) from the remaining 230 ECG pairs shows: (i) two best single-lead ID models using lead II for a small population RS = (10-140) with identification accuracy AccID = (89.4-67.2)% and aVF for a large population RS = (140-230) with AccID = (67.2-63.9)%; (ii) better performance of the 6-lead limb vs. The 6-lead chest ID model-(91.4-76.1)% vs. (90.9-70)% for RS = (10-230); (iii) best performance of the 12-lead ID model-(98.4-87.4)% for RS = (10-230). The tolerable reference database size, keeping AccID > 80%, is RS = 30 in the single-lead ID scenario (II); RS = 50 (6 chest leads); RS = 100 (6 limb leads), RS > 230-maximal population in this study (12-lead ECG).
The paper presents results from testing a pace pulse detection algorithm in case of EMG artifacts... more The paper presents results from testing a pace pulse detection algorithm in case of EMG artifacts. The study is performed over a large dataset containing 624 ECG+EMG signals acquired with high amplitude and time resolution. Two operating frequencies are studied – 16 kHz and 32 kHz. PPV of the algorithm decreases considerably in case of EMG noise – about 10% for 32 kHz (89.32% vs. 98.95%) and about 22% for 16 kHz (74.70% vs. 96.75%). The observed Se variation is below 0.5% (99.44% vs. 99.27% for 32 kHz, 97.30% vs. 97.14% for 16 kHz).
2015 Computing in Cardiology Conference (CinC), 2015
False Intensive Care Unit (ICU) alarms induce stress in both patients and clinical staff and decr... more False Intensive Care Unit (ICU) alarms induce stress in both patients and clinical staff and decrease the quality of care, thus significantly increasing both the hospital recovery time and re-hospitalization rates. Therefore, PhysioNet/CinC Challenge 2015 encourages the development of algorithms for the analysis of bedside monitor data for robust detection of life-threatening arrhythmias. We participated in the Challenge with: (i) a closed source implementation of Arrhythmia Detection Library (ADLib, Schiller AG), including modules for lead quality monitoring, heartbeat detection, heartbeat classification and ventricular fibrillation detection; (ii) an open source Pulse Wave Analysis Module for verification of the hemodynamic status based on arterial blood pressure and photoplethysmogram signals; (iii) an open source Alarm Decision Module for final alarm rejection/validation. Our best scored entry in the real-time event is: score 79.41%, with 93%/83% true positive/negative rates. The average/max running time is 12.5/29.5% of quota.
2015 Computing in Cardiology Conference (CinC), 2015
This study presents a method for automated detection of misplaced supplementary precordial leads,... more This study presents a method for automated detection of misplaced supplementary precordial leads, including the right-sided V3R, V4R and the posterior V8, V9 leads. Considering their uncommon use in clinical routine, a lead reversal is quite probable and could result in erroneous diagnosis and treatment. The method allows real-time implementation by scoring inter-lead crosscorrelations over continuous 4s episodes, scanning the normal progression of PQRST waveforms within leads [V4R, V3R, V3, V4] and [V4, V5, V6, V8, V9]. A large 16-lead ECG database with 1333 chest pain patients is used to test the performance of the method for all possible 23 swaps between the supplementary leads V4R, V3R, V8, V9, assuming correct positions of the standard V1-V6. The sensitivity (Se) for lead reversals is Se=94.1±4.6%, ranged between 78.5% and 97.8%, with the most difficult detection of V3R/V4R swap (Se=78.5%), V4R/V9 swap (Se=83.7%), V8/V9 swap (Se=91.8%). The achieved specificity for the correct lead positions is Sp=83.4%.
Cardio-pulmonary resuscitation (CPR) is a life-saving first aid which is part of the treatment gi... more Cardio-pulmonary resuscitation (CPR) is a life-saving first aid which is part of the treatment given in case of sudden cardiac death. According to the American Heart Association (AHA) 2005 Guidelines for CPR, there are three key components related to the chest compressions which should be considered: (i) optimal compression depth between 3.8 and 5.4 centimeters; (ii) optimal compression rate between 85 and 115 compressions per minute; (iii) complete chest recoil by releasing all pressure from the chest after each chest compression (CC). A device for automatic control of the quality of chest compressions during CPR was developed. It embedded hardware and software solutions for simultaneous measurement of the depth, rate and the chest recoil thus providing a feedback about the efficiency of the cardiac massage at each CC compression. The system is applicable as a training device for basic education in CPR or as a consulting system for rescuers on the scene of the cardiac incident. The accuracy of the CC Device was adjusted by theoretical and experimental calibration, and tested by planned experiments, as well as experiments with a medical team.
2019 IEEE XXVIII International Scientific Conference Electronics (ET), 2019
The paper presents an ECG telemetry monitoring system including: (i) portable analyzers of the he... more The paper presents an ECG telemetry monitoring system including: (i) portable analyzers of the heart activity; (ii) hybrid network architecture with wireless (bluetooth) and wired (RS485 interface) parts; and (iii) central unit. The system is applied on 85 cardio-vascular patients in the Cardiology unit of the Department of propedeutics of internal medicine in the University hospital “Alexandrovska” – Sofia. It has helped for the registration of rhythm and/or conduction disturbances in 89.4 % of the patients which has allowed the application of a timely therapeutic treatment. Serious technical failures have not been reported during the follow-up period of the ECG telemetry monitoring system.
Published: filled by editor Abstract: This paper presents an ECG database, named 'PacedECGdb&... more Published: filled by editor Abstract: This paper presents an ECG database, named 'PacedECGdb' (available at http://biomed.bas.bg/bioautomation/2014/vol_18.4/files/PacedECGdb.zip), which contains different arrhythmias generated by HKP (Heidelberger Praxisklinik) simulator, combined with artificially superimposed pacing pulses that cover the wide ranges of rising edge (from <10 µs to 100 µs) and total pulse durations (from 100 µs to 2 ms) and correspond to various pacemaker modes. It involves a total number of 1404 recordings - 780 representing 'pure' ECG with pacing pulses and 624 that comprise paced ECGs corrupted by tremor. The signals are recorded with 9.81 µV/LSB amplitude resolution at 128 kHz sampling rate in order to preserve the steep raising and trailing edges of the pace pulses. To the best of our knowledge, 'PacedECGdb' is the first publicly available paced ECG database. It could be used for development and testing of methods for pace detection i...
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).
OBJECTIVE The aim of this study was to present new combination of algorithms for rhythm analysis ... more OBJECTIVE The aim of this study was to present new combination of algorithms for rhythm analysis during cardiopulmonary resuscitation (CPR) in automated external defibrillators (AED), called Analyze Whilst Compressing (AWC), designed for decreasing pre-shock pause and early stopping of chest compressions (CC) for treating refibrillation. METHODS Two stages for AED rhythm analysis were presented, namely, "Standard Analysis Stage" (conventional shock-advisory analysis run over 5 s after CC interruption every two minutes) and "AWC Stage" (two-step sequential analysis process during CPR). AWC steps were run in presence of CC (Step1), and if shockable rhythm was detected then a reconfirmation step was run in absence of CC (Step2, analysis duration 5 s). RESULTS In total 16057 ECG strips from 2916 out-of-hospital cardiac arrest (OHCA) patients treated with AEDs (DEFIGARD TOUCH7, Schiller Médical, France) were subjected patient-wise to AWC training (8559 strips, 1604 patients) and validation (7498 strips, 1312 patients). Considering validation results, "Standard Analysis Stage" presented ventricular fibrillation (VF) sensitivity Se = 98.3% and non-shockable rhythm specificity Sp>99%; "AWC Stage" decision after Step2 reconfirmation achieved Se = 92.1%, Sp>99%. CONCLUSION AWC presented similar performances to other AED algorithms during CPR, fulfilling performance goals recommended by standards. AWC provided advances in the challenge for improving CPR quality by: (i) not interrupting chest compressions for prevalent part of non-shockable rhythms (66-83%); (ii) minimizing pre-shock pause for 92.1% of VF patients. AWC required hands-off reconfirmation in 34.4% of cases. Reconfirmation was also common limitation of other reported algorithms (26.4-100%) although following different protocols for triggering chest compression resumption and shock delivery.
DOAJ (DOAJ: Directory of Open Access Journals), Dec 1, 2014
This paper presents an ECG database, named 'PacedECGdb' (available at http://biomed.bas.bg/bioaut... more This paper presents an ECG database, named 'PacedECGdb' (available at http://biomed.bas.bg/bioautomation/2014/vol_18.4/files/PacedECGdb.zip), which contains different arrhythmias generated by HKP (Heidelberger Praxisklinik) simulator, combined with artificially superimposed pacing pulses that cover the wide ranges of rising edge (from <10 µs to 100 µs) and total pulse durations (from 100 µs to 2 ms) and correspond to various pacemaker modes. It involves a total number of 1404 recordings-780 representing 'pure' ECG with pacing pulses and 624 that comprise paced ECGs corrupted by tremor. The signals are recorded with 9.81 µV/LSB amplitude resolution at 128 kHz sampling rate in order to preserve the steep raising and trailing edges of the pace pulses. To the best of our knowledge, 'PacedECGdb' is the first publicly available paced ECG database. It could be used for development and testing of methods for pace detection in the ECG. The existence of ECGs corrupted by tremor (the only physiological noise that could compromise the methods for pacing pulses detection) is an advantage, since such signals could be applied to define the signal-to-noise level for correct operation of the algorithm, or for improvement of the noise immunity of a method that is under development. The open access of the database makes it suitable for comparative studies including different algorithms.
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
The paper presents a prototype of ECG simulator, which may be a beneficial tool in designing and ... more The paper presents a prototype of ECG simulator, which may be a beneficial tool in designing and debugging of automatic diagnosis software methods implemented in real ECG devices. The main advantages of the proposed simulator are both the expanded memory capacity and the easy approach for reconfiguration of the memory content, data format and sampling frequency.
Traditional means for identity validation (PIN codes, passwords), and physiological and behaviora... more Traditional means for identity validation (PIN codes, passwords), and physiological and behavioral biometric characteristics (fingerprint, iris, and speech) are susceptible to hacker attacks and/or falsification. This paper presents a method for person verification/identification based on correlation of present-to-previous limb ECG leads: I (I), II (II), calculated from them first principal ECG component (PCA), linear and nonlinear combinations between I , II , and PCA. For the verification task, the one-toone scenario is applied and threshold values for I , II , and PCA and their combinations are derived. The identification task supposes one-to-many scenario and the tested subject is identified according to the maximal correlation with a previously recorded ECG in a database. The population based ECG-ILSA database of 540 patients (147 healthy subjects, 175 patients with cardiac diseases, and 218 with hypertension) has been considered. In addition a common reference PTB dataset (14 healthy individuals) with short time interval between the two acquisitions has been taken into account. The results on ECG-ILSA database were satisfactory with healthy people, and there was not a significant decrease in nonhealthy patients, demonstrating the robustness of the proposed method. With PTB database, the method provides an identification accuracy of 92.9% and a verification sensitivity and specificity of 100% and 89.9%.
This study aims to test the usability of the transthoracic impedance cardiogram (ICG) for assessm... more This study aims to test the usability of the transthoracic impedance cardiogram (ICG) for assessment of the quality of myocardial contractions in atrial fibrillation (AFIB) vs. sinus rhythm (SR), using signals recorded via defibrillation pads during external cardioversion (ECV). Data from 88 patients with persistent AFIB who received planned ECV are processed. AFIB is treated with cardioverter/defibrillator DG4000 (Schiller Médical, France) using a non-escalating protocol 200J/200J/200J. Successful ECV is defined as restoration of SR for >1min. The electrocardiogram (ECG), thoracic baseline impedance (Z) and dynamic impedance components dZ, dZ/dt captured via self-adhesive pads in anteroapical position are processed. Heartbeat contractions are evaluated by several measures extracted from the mean ICG patterns during systole: from dZ pattern-ICG (peak amplitude, range, area); from dZ/dt pattern-ICG velocity (peak, range, area) and left ventricular ejection time (LVET). The hemodynamical indices measured before and after ECV are: mean heart rate over 2 minutes (HR), standard deviation of HR (HRV), systolic (SysBP) and diastolic (DiaBP) blood pressure. When the rhythm converts from AFIB to SR (74 patients), all measures on dZ, dZ/dt patterns significantly increase: dZ (64-102%), dZ/dt (31-67%), LVET (18%), p < 0.05. Significant decrease of HR (-36%), HRV (-53%), SysBP (-11%) and DiaBP (-19%) are also observed. Unsuccessful ECVs without conversion to SR (14 patients) are, however, associated with non-significant increase of dZ (10-21%), dZ/dt (0.3-29%), LVET (9%), p > 0.05 when comparing pre-shock AFIB vs. post-shock AFIB. No clear change in HR (-9%) and HRV (6%), and slight decrease of SysBP (-10%) and DiaBP (-8%) are observed. The level of improvement of cardiac output quality in post-shock SR vs. pre-shock AFIB as estimated by ICG is related to a set of more than 60 clinical and hemodynamical parameters.
The automatic external defibrillator (AED) is a lifesaving device, which processes and analyses t... more The automatic external defibrillator (AED) is a lifesaving device, which processes and analyses the electrocardiogram (ECG) and delivers a defibrillation shock to terminate ventricular fibrillation or tachycardia above 180 bpm. The built-in algorithm for ECG analysis has to discriminate between shockable and non-shockable rhythms and its accuracy, represented by sensitivity and specificity, is aimed at approaching the maximum values of 100%. An algorithm for VF/VT detection is proposed using a band-pass digital filter with integer coefficients, which is very simple to implement in real-time operation. A branch for wave detection is activated for heart rate measurement and an auxiliary parameter calculation. The method was tested with ECG records from the widely recognized databases of the American Heart Association (AHA) and the Massachusetts Institute of Technology (MIT). A sensitivity of 95.93% and a specificity of 94.38% were obtained.
Chest compressions during cardiopulmonary resuscitation (CPR) induce artifacts in the ECG that ma... more Chest compressions during cardiopulmonary resuscitation (CPR) induce artifacts in the ECG that may provoque inaccurate rhythm classification by the algorithm of the defibrillator. The objective of this study was to design an algorithm to produce reliable shock/no-shock decisions during CPR using convolutional neural networks (CNN). A total of 3319 ECG segments of 9 s extracted during chest compressions were used, whereof 586 were shockable and 2733 nonshockable. Chest compression artifacts were removed using a Recursive Least Squares (RLS) filter, and the filtered ECG was fed to a CNN classifier with three convolutional blocks and two fully connected layers for the shock/no-shock classification. A 5-fold cross validation architecture was adopted to train/test the algorithm, and the proccess was repeated 100 times to statistically characterize the performance. The proposed architecture was compared to the most accurate algorithms that include handcrafted ECG features and a random forest classifier (baseline model). The median (90% confidence interval) sensitivity, specificity, accuracy and balanced accuracy of the method were 95.8% (94.6-96.8), 96.1% (95.8-96.5), 96.1% (95.7-96.4) and 96.0% (95.5-96.5), respectively. The proposed algorithm outperformed the baseline model by 0.6-points in accuracy. This new approach shows the potential of deep learning methods to provide reliable diagnosis of the cardiac rhythm without interrupting chest compression therapy.
Human identification (ID) is a biometric task, comparing single input sample to many stored templ... more Human identification (ID) is a biometric task, comparing single input sample to many stored templates to identify an individual in a reference database. This paper aims to present the perspectives of personalized heartbeat pattern for reliable ECG-based identification. The investigations are using a database with 460 pairs of 12-lead resting electrocardiograms (ECG) with 10-s durations recorded at time-instants T1 and T2 > T1 + 1 year. Intra-subject long-term ECG stability and inter-subject variability of personalized PQRST (500 ms) and QRS (100 ms) patterns is quantified via cross-correlation, amplitude ratio and pattern matching between T1 and T2 using 7 features × 12-leads. Single and multi-lead ID models are trained on the first 230 ECG pairs. Their validation on 10, 20, ... 230 reference subjects (RS) from the remaining 230 ECG pairs shows: (i) two best single-lead ID models using lead II for a small population RS = (10-140) with identification accuracy AccID = (89.4-67.2)% and aVF for a large population RS = (140-230) with AccID = (67.2-63.9)%; (ii) better performance of the 6-lead limb vs. The 6-lead chest ID model-(91.4-76.1)% vs. (90.9-70)% for RS = (10-230); (iii) best performance of the 12-lead ID model-(98.4-87.4)% for RS = (10-230). The tolerable reference database size, keeping AccID > 80%, is RS = 30 in the single-lead ID scenario (II); RS = 50 (6 chest leads); RS = 100 (6 limb leads), RS > 230-maximal population in this study (12-lead ECG).
The paper presents results from testing a pace pulse detection algorithm in case of EMG artifacts... more The paper presents results from testing a pace pulse detection algorithm in case of EMG artifacts. The study is performed over a large dataset containing 624 ECG+EMG signals acquired with high amplitude and time resolution. Two operating frequencies are studied – 16 kHz and 32 kHz. PPV of the algorithm decreases considerably in case of EMG noise – about 10% for 32 kHz (89.32% vs. 98.95%) and about 22% for 16 kHz (74.70% vs. 96.75%). The observed Se variation is below 0.5% (99.44% vs. 99.27% for 32 kHz, 97.30% vs. 97.14% for 16 kHz).
2015 Computing in Cardiology Conference (CinC), 2015
False Intensive Care Unit (ICU) alarms induce stress in both patients and clinical staff and decr... more False Intensive Care Unit (ICU) alarms induce stress in both patients and clinical staff and decrease the quality of care, thus significantly increasing both the hospital recovery time and re-hospitalization rates. Therefore, PhysioNet/CinC Challenge 2015 encourages the development of algorithms for the analysis of bedside monitor data for robust detection of life-threatening arrhythmias. We participated in the Challenge with: (i) a closed source implementation of Arrhythmia Detection Library (ADLib, Schiller AG), including modules for lead quality monitoring, heartbeat detection, heartbeat classification and ventricular fibrillation detection; (ii) an open source Pulse Wave Analysis Module for verification of the hemodynamic status based on arterial blood pressure and photoplethysmogram signals; (iii) an open source Alarm Decision Module for final alarm rejection/validation. Our best scored entry in the real-time event is: score 79.41%, with 93%/83% true positive/negative rates. The average/max running time is 12.5/29.5% of quota.
2015 Computing in Cardiology Conference (CinC), 2015
This study presents a method for automated detection of misplaced supplementary precordial leads,... more This study presents a method for automated detection of misplaced supplementary precordial leads, including the right-sided V3R, V4R and the posterior V8, V9 leads. Considering their uncommon use in clinical routine, a lead reversal is quite probable and could result in erroneous diagnosis and treatment. The method allows real-time implementation by scoring inter-lead crosscorrelations over continuous 4s episodes, scanning the normal progression of PQRST waveforms within leads [V4R, V3R, V3, V4] and [V4, V5, V6, V8, V9]. A large 16-lead ECG database with 1333 chest pain patients is used to test the performance of the method for all possible 23 swaps between the supplementary leads V4R, V3R, V8, V9, assuming correct positions of the standard V1-V6. The sensitivity (Se) for lead reversals is Se=94.1±4.6%, ranged between 78.5% and 97.8%, with the most difficult detection of V3R/V4R swap (Se=78.5%), V4R/V9 swap (Se=83.7%), V8/V9 swap (Se=91.8%). The achieved specificity for the correct lead positions is Sp=83.4%.
Cardio-pulmonary resuscitation (CPR) is a life-saving first aid which is part of the treatment gi... more Cardio-pulmonary resuscitation (CPR) is a life-saving first aid which is part of the treatment given in case of sudden cardiac death. According to the American Heart Association (AHA) 2005 Guidelines for CPR, there are three key components related to the chest compressions which should be considered: (i) optimal compression depth between 3.8 and 5.4 centimeters; (ii) optimal compression rate between 85 and 115 compressions per minute; (iii) complete chest recoil by releasing all pressure from the chest after each chest compression (CC). A device for automatic control of the quality of chest compressions during CPR was developed. It embedded hardware and software solutions for simultaneous measurement of the depth, rate and the chest recoil thus providing a feedback about the efficiency of the cardiac massage at each CC compression. The system is applicable as a training device for basic education in CPR or as a consulting system for rescuers on the scene of the cardiac incident. The accuracy of the CC Device was adjusted by theoretical and experimental calibration, and tested by planned experiments, as well as experiments with a medical team.
2019 IEEE XXVIII International Scientific Conference Electronics (ET), 2019
The paper presents an ECG telemetry monitoring system including: (i) portable analyzers of the he... more The paper presents an ECG telemetry monitoring system including: (i) portable analyzers of the heart activity; (ii) hybrid network architecture with wireless (bluetooth) and wired (RS485 interface) parts; and (iii) central unit. The system is applied on 85 cardio-vascular patients in the Cardiology unit of the Department of propedeutics of internal medicine in the University hospital “Alexandrovska” – Sofia. It has helped for the registration of rhythm and/or conduction disturbances in 89.4 % of the patients which has allowed the application of a timely therapeutic treatment. Serious technical failures have not been reported during the follow-up period of the ECG telemetry monitoring system.
Published: filled by editor Abstract: This paper presents an ECG database, named 'PacedECGdb&... more Published: filled by editor Abstract: This paper presents an ECG database, named 'PacedECGdb' (available at http://biomed.bas.bg/bioautomation/2014/vol_18.4/files/PacedECGdb.zip), which contains different arrhythmias generated by HKP (Heidelberger Praxisklinik) simulator, combined with artificially superimposed pacing pulses that cover the wide ranges of rising edge (from <10 µs to 100 µs) and total pulse durations (from 100 µs to 2 ms) and correspond to various pacemaker modes. It involves a total number of 1404 recordings - 780 representing 'pure' ECG with pacing pulses and 624 that comprise paced ECGs corrupted by tremor. The signals are recorded with 9.81 µV/LSB amplitude resolution at 128 kHz sampling rate in order to preserve the steep raising and trailing edges of the pace pulses. To the best of our knowledge, 'PacedECGdb' is the first publicly available paced ECG database. It could be used for development and testing of methods for pace detection i...
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).
OBJECTIVE The aim of this study was to present new combination of algorithms for rhythm analysis ... more OBJECTIVE The aim of this study was to present new combination of algorithms for rhythm analysis during cardiopulmonary resuscitation (CPR) in automated external defibrillators (AED), called Analyze Whilst Compressing (AWC), designed for decreasing pre-shock pause and early stopping of chest compressions (CC) for treating refibrillation. METHODS Two stages for AED rhythm analysis were presented, namely, "Standard Analysis Stage" (conventional shock-advisory analysis run over 5 s after CC interruption every two minutes) and "AWC Stage" (two-step sequential analysis process during CPR). AWC steps were run in presence of CC (Step1), and if shockable rhythm was detected then a reconfirmation step was run in absence of CC (Step2, analysis duration 5 s). RESULTS In total 16057 ECG strips from 2916 out-of-hospital cardiac arrest (OHCA) patients treated with AEDs (DEFIGARD TOUCH7, Schiller Médical, France) were subjected patient-wise to AWC training (8559 strips, 1604 patients) and validation (7498 strips, 1312 patients). Considering validation results, "Standard Analysis Stage" presented ventricular fibrillation (VF) sensitivity Se = 98.3% and non-shockable rhythm specificity Sp>99%; "AWC Stage" decision after Step2 reconfirmation achieved Se = 92.1%, Sp>99%. CONCLUSION AWC presented similar performances to other AED algorithms during CPR, fulfilling performance goals recommended by standards. AWC provided advances in the challenge for improving CPR quality by: (i) not interrupting chest compressions for prevalent part of non-shockable rhythms (66-83%); (ii) minimizing pre-shock pause for 92.1% of VF patients. AWC required hands-off reconfirmation in 34.4% of cases. Reconfirmation was also common limitation of other reported algorithms (26.4-100%) although following different protocols for triggering chest compression resumption and shock delivery.
Uploads
Papers by Irena Jekova