TY  - JOUR
AU  - Benini, Sergio
AU  - Ivanović, Marija D.
AU  - Savardi, Mattia
AU  - Kršić, Jelena
AU  - Hadžievski, Ljupčo
AU  - Baronio, Fabio
PY  - 2021
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/9547
AB  - The provided database of 260 ECG signals was collected from patients with out-of-hospital cardiac arrest while treated by the emergency medical services. Each ECG signal contains a 9 second waveform showing ventricular fibrillation, followed by 1 min of post-shock waveform. Patients’ ECGs are made available in multiple formats. All ECGs recorded during the prehospital treatment are provided in PFD files, after being anonymized, printed in paper, and scanned. For each ECG, the dataset also includes the whole digitized waveform (9 s pre- and 1 min post-shock each) and numerous features in temporal and frequency domain extracted from the 9 s episode immediately prior to the first defibrillation shock. Based on the shock outcome, each ECG file has been annotated by three expert cardiologists, - using majority decision -, as successful (56 cases), unsuccessful (195 cases), or indeterminable (9 cases). The code for preprocessing, for feature extraction, and for limiting the investigation to different temporal intervals before the shock is also provided. These data could be reused to design algorithms to predict shock outcome based on ventricular fibrillation analysis, with the goal to optimize the defibrillation strategy (immediate defibrillation versus cardiopulmonary resuscitation and/or drug administration) for enhancing resuscitation. © 2020
T2  - Data in Brief
T1  - ECG waveform dataset for predicting defibrillation outcome in out-of-hospital cardiac arrested patients
VL  - 34
SP  - 106635
DO  - 10.1016/j.dib.2020.106635
ER  - 

@article{
author = "Benini, Sergio and Ivanović, Marija D. and Savardi, Mattia and Kršić, Jelena and Hadžievski, Ljupčo and Baronio, Fabio",
year = "2021",
abstract = "The provided database of 260 ECG signals was collected from patients with out-of-hospital cardiac arrest while treated by the emergency medical services. Each ECG signal contains a 9 second waveform showing ventricular fibrillation, followed by 1 min of post-shock waveform. Patients’ ECGs are made available in multiple formats. All ECGs recorded during the prehospital treatment are provided in PFD files, after being anonymized, printed in paper, and scanned. For each ECG, the dataset also includes the whole digitized waveform (9 s pre- and 1 min post-shock each) and numerous features in temporal and frequency domain extracted from the 9 s episode immediately prior to the first defibrillation shock. Based on the shock outcome, each ECG file has been annotated by three expert cardiologists, - using majority decision -, as successful (56 cases), unsuccessful (195 cases), or indeterminable (9 cases). The code for preprocessing, for feature extraction, and for limiting the investigation to different temporal intervals before the shock is also provided. These data could be reused to design algorithms to predict shock outcome based on ventricular fibrillation analysis, with the goal to optimize the defibrillation strategy (immediate defibrillation versus cardiopulmonary resuscitation and/or drug administration) for enhancing resuscitation. © 2020",
journal = "Data in Brief",
title = "ECG waveform dataset for predicting defibrillation outcome in out-of-hospital cardiac arrested patients",
volume = "34",
pages = "106635",
doi = "10.1016/j.dib.2020.106635"
}

Benini, S., Ivanović, M. D., Savardi, M., Kršić, J., Hadžievski, L.,& Baronio, F.. (2021). ECG waveform dataset for predicting defibrillation outcome in out-of-hospital cardiac arrested patients. in Data in Brief, 34, 106635.
https://doi.org/10.1016/j.dib.2020.106635

Benini S, Ivanović MD, Savardi M, Kršić J, Hadžievski L, Baronio F. ECG waveform dataset for predicting defibrillation outcome in out-of-hospital cardiac arrested patients. in Data in Brief. 2021;34:106635.
doi:10.1016/j.dib.2020.106635 .

Benini, Sergio, Ivanović, Marija D., Savardi, Mattia, Kršić, Jelena, Hadžievski, Ljupčo, Baronio, Fabio, "ECG waveform dataset for predicting defibrillation outcome in out-of-hospital cardiac arrested patients" in Data in Brief, 34 (2021):106635,
https://doi.org/10.1016/j.dib.2020.106635 . .

TY  - JOUR
AU  - Ivanović, Marija D.
AU  - Mančić, Ana
AU  - Hermann-Avigliano, Carla
AU  - Hadžievski, Ljupčo
AU  - Maluckov, Aleksandra
PY  - 2020
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/8837
AB  - In this paper, we establish a new scheme for identification and classification of high intensity events generated by the propagation of light through a photorefractive SBN crystal. Among these events, which are the inevitable consequence of the development of modulation instability, are speckling and soliton-like patterns. The usual classifiers, developed on statistical measures, such as the significant intensity, often provide only a partial characterization of these events. Here, we try to overcome this deficiency by implementing the convolution neural network method to relate experimental data of light intensity distribution and corresponding numerical outputs with different high intensity regimes. The train and test sets are formed of experimentally obtained intensity profiles at the crystal output facet and corresponding numerical profiles. The accuracy of detection of speckles reaches maximum value of 100%, while the accuracy of solitons and caustic detection is above 97%. These performances are promising for the creation of neural network based routines for prediction of extreme events in wave media. © 2020 IOP Publishing Ltd.
T2  - Journal of Optics
T1  - Deep learning-based classification of high intensity light patterns in photorefractive crystals
VL  - 22
IS  - 3
SP  - 035504
DO  - 10.1088/2040-8986/ab70f0
ER  - 

@article{
author = "Ivanović, Marija D. and Mančić, Ana and Hermann-Avigliano, Carla and Hadžievski, Ljupčo and Maluckov, Aleksandra",
year = "2020",
abstract = "In this paper, we establish a new scheme for identification and classification of high intensity events generated by the propagation of light through a photorefractive SBN crystal. Among these events, which are the inevitable consequence of the development of modulation instability, are speckling and soliton-like patterns. The usual classifiers, developed on statistical measures, such as the significant intensity, often provide only a partial characterization of these events. Here, we try to overcome this deficiency by implementing the convolution neural network method to relate experimental data of light intensity distribution and corresponding numerical outputs with different high intensity regimes. The train and test sets are formed of experimentally obtained intensity profiles at the crystal output facet and corresponding numerical profiles. The accuracy of detection of speckles reaches maximum value of 100%, while the accuracy of solitons and caustic detection is above 97%. These performances are promising for the creation of neural network based routines for prediction of extreme events in wave media. © 2020 IOP Publishing Ltd.",
journal = "Journal of Optics",
title = "Deep learning-based classification of high intensity light patterns in photorefractive crystals",
volume = "22",
number = "3",
pages = "035504",
doi = "10.1088/2040-8986/ab70f0"
}

Ivanović, M. D., Mančić, A., Hermann-Avigliano, C., Hadžievski, L.,& Maluckov, A.. (2020). Deep learning-based classification of high intensity light patterns in photorefractive crystals. in Journal of Optics, 22(3), 035504.
https://doi.org/10.1088/2040-8986/ab70f0

Ivanović MD, Mančić A, Hermann-Avigliano C, Hadžievski L, Maluckov A. Deep learning-based classification of high intensity light patterns in photorefractive crystals. in Journal of Optics. 2020;22(3):035504.
doi:10.1088/2040-8986/ab70f0 .

Ivanović, Marija D., Mančić, Ana, Hermann-Avigliano, Carla, Hadžievski, Ljupčo, Maluckov, Aleksandra, "Deep learning-based classification of high intensity light patterns in photorefractive crystals" in Journal of Optics, 22, no. 3 (2020):035504,
https://doi.org/10.1088/2040-8986/ab70f0 . .

TY  - JOUR
AU  - Ivanović, Marija D.
AU  - Hannink, Julius
AU  - Ring, Matthias
AU  - Baronio, Fabio
AU  - Vukčević, Vladan
AU  - Hadžievski, Ljupčo
AU  - Eskofier, Bjoern
PY  - 2020
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/9678
AB  - Optimizing timing of defibrillation by evaluating the likelihood of a successful outcome could significantly enhance resuscitation. Previous studies employed conventional machine learning approaches and hand-crafted features to address this issue, but none have achieved superior performance to be widely accepted. This study proposes a novel approach in which predictive features are automatically learned.MethodsA raw 4s VF episode immediately prior to first defibrillation shock was feed to a 3-stage CNN feature extractor. Each stage was composed of 4 components: convolution, rectified linear unit activation, dropout and max-pooling. At the end of feature extractor, the feature map was flattened and connected to a fully connected multi-layer perceptron for classification. For model evaluation, a 10 fold cross-validation was employed. To balance classes, SMOTE oversampling method has been applied to minority class.ResultsThe obtained results show that the proposed model is highly accurate in predicting defibrillation outcome (Acc = 93.6 %). Since recommendations on classifiers suggest at least 50 % specificity and 95 % sensitivity as safe and useful predictors for defibrillation decision, the reported sensitivity of 98.8 % and specificity of 88.2 %, with the analysis speed of 3 ms/input signal, indicate that the proposed model possesses a good prospective to be implemented in automated external defibrillators.ConclusionsThe learned features demonstrate superiority over hand-crafted ones when performed on the same dataset. This approach benefits from being fully automatic by fusing feature extraction, selection and classification into a single learning model. It provides a superior strategy that can be used as a tool to guide treatment of OHCA patients in bringing optimal decision of precedence treatment. Furthermore, for encouraging replicability, the dataset has been made publicly available to the research community.
T2  - Artificial Intelligence in Medicine
T1  - Predicting defibrillation success in out-of-hospital cardiac arrested patients: Moving beyond feature design
VL  - 110
SP  - 101963
DO  - 10.1016/j.artmed.2020.101963
ER  - 

@article{
author = "Ivanović, Marija D. and Hannink, Julius and Ring, Matthias and Baronio, Fabio and Vukčević, Vladan and Hadžievski, Ljupčo and Eskofier, Bjoern",
year = "2020",
abstract = "Optimizing timing of defibrillation by evaluating the likelihood of a successful outcome could significantly enhance resuscitation. Previous studies employed conventional machine learning approaches and hand-crafted features to address this issue, but none have achieved superior performance to be widely accepted. This study proposes a novel approach in which predictive features are automatically learned.MethodsA raw 4s VF episode immediately prior to first defibrillation shock was feed to a 3-stage CNN feature extractor. Each stage was composed of 4 components: convolution, rectified linear unit activation, dropout and max-pooling. At the end of feature extractor, the feature map was flattened and connected to a fully connected multi-layer perceptron for classification. For model evaluation, a 10 fold cross-validation was employed. To balance classes, SMOTE oversampling method has been applied to minority class.ResultsThe obtained results show that the proposed model is highly accurate in predicting defibrillation outcome (Acc = 93.6 %). Since recommendations on classifiers suggest at least 50 % specificity and 95 % sensitivity as safe and useful predictors for defibrillation decision, the reported sensitivity of 98.8 % and specificity of 88.2 %, with the analysis speed of 3 ms/input signal, indicate that the proposed model possesses a good prospective to be implemented in automated external defibrillators.ConclusionsThe learned features demonstrate superiority over hand-crafted ones when performed on the same dataset. This approach benefits from being fully automatic by fusing feature extraction, selection and classification into a single learning model. It provides a superior strategy that can be used as a tool to guide treatment of OHCA patients in bringing optimal decision of precedence treatment. Furthermore, for encouraging replicability, the dataset has been made publicly available to the research community.",
journal = "Artificial Intelligence in Medicine",
title = "Predicting defibrillation success in out-of-hospital cardiac arrested patients: Moving beyond feature design",
volume = "110",
pages = "101963",
doi = "10.1016/j.artmed.2020.101963"
}

Ivanović, M. D., Hannink, J., Ring, M., Baronio, F., Vukčević, V., Hadžievski, L.,& Eskofier, B.. (2020). Predicting defibrillation success in out-of-hospital cardiac arrested patients: Moving beyond feature design. in Artificial Intelligence in Medicine, 110, 101963.
https://doi.org/10.1016/j.artmed.2020.101963

Ivanović MD, Hannink J, Ring M, Baronio F, Vukčević V, Hadžievski L, Eskofier B. Predicting defibrillation success in out-of-hospital cardiac arrested patients: Moving beyond feature design. in Artificial Intelligence in Medicine. 2020;110:101963.
doi:10.1016/j.artmed.2020.101963 .

Ivanović, Marija D., Hannink, Julius, Ring, Matthias, Baronio, Fabio, Vukčević, Vladan, Hadžievski, Ljupčo, Eskofier, Bjoern, "Predicting defibrillation success in out-of-hospital cardiac arrested patients: Moving beyond feature design" in Artificial Intelligence in Medicine, 110 (2020):101963,
https://doi.org/10.1016/j.artmed.2020.101963 . .

TY  - JOUR
AU  - Petrović, Jovana S.
PY  - 2019
UR  - https://linkinghub.elsevier.com/retrieve/pii/S2590147819300014
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/8045
AB  - Ultrafast-laser inscribed optical memories have been considered as a high-density low-energy-consumption alternative to the magnetization-based memories. The optical memories are based on laser-induced material modifications resulting in the refractive index change. The long-term stability of such modifications has been indicated by subjecting them to the accelerated aging by annealing at elevated temperatures. Here, the first direct evidence is provided of the durability of the type II refractive index change in BK7 glass. The investigation was performed for over 27 months at room temperature. The results show the existence of the laser pulse intensity threshold above which the magnitude of the index change does not deteriorate with time and, hence, is suitable for optical memory, photonic crystal and fibre-grating writing. © 2019
T2  - Optical Materials: X
T1  - Durability of the refractive index change induced by a single femtosecond laser pulse in glass
VL  - 1
SP  - 100004
DO  - 10.1016/j.omx.2019.100004
ER  - 

@article{
author = "Petrović, Jovana S.",
year = "2019",
abstract = "Ultrafast-laser inscribed optical memories have been considered as a high-density low-energy-consumption alternative to the magnetization-based memories. The optical memories are based on laser-induced material modifications resulting in the refractive index change. The long-term stability of such modifications has been indicated by subjecting them to the accelerated aging by annealing at elevated temperatures. Here, the first direct evidence is provided of the durability of the type II refractive index change in BK7 glass. The investigation was performed for over 27 months at room temperature. The results show the existence of the laser pulse intensity threshold above which the magnitude of the index change does not deteriorate with time and, hence, is suitable for optical memory, photonic crystal and fibre-grating writing. © 2019",
journal = "Optical Materials: X",
title = "Durability of the refractive index change induced by a single femtosecond laser pulse in glass",
volume = "1",
pages = "100004",
doi = "10.1016/j.omx.2019.100004"
}

Petrović, J. S.. (2019). Durability of the refractive index change induced by a single femtosecond laser pulse in glass. in Optical Materials: X, 1, 100004.
https://doi.org/10.1016/j.omx.2019.100004

Petrović JS. Durability of the refractive index change induced by a single femtosecond laser pulse in glass. in Optical Materials: X. 2019;1:100004.
doi:10.1016/j.omx.2019.100004 .

Petrović, Jovana S., "Durability of the refractive index change induced by a single femtosecond laser pulse in glass" in Optical Materials: X, 1 (2019):100004,
https://doi.org/10.1016/j.omx.2019.100004 . .

TY  - CONF
AU  - Ivanović, Marija D.
AU  - Miletić, Marjan
AU  - Subotić, Ida
AU  - Boljević, Darko
PY  - 2019
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/8804
AB  - Acute myocardial infraction (AMI) is a leading cause of death in the developed countries. Survival of patients having acute coronary syndrome (ACS) dramatically depends on treatment delay. Hence, a technology that would enable ECG recording immediately after ACS symptom occurrence may significantly decrease AMI mortality. In this study we investigate the signal quality of reconstructed 12-lead ECGs by using 3-lead handheld device with dry electrode in realistic ambulatory conditions. For each subject enrolled in the study an individual transformation matrix was calculated during the calibration procedure, and used for 12-lead reconstruction whenever that subject sends a recording from a handheld device. To evaluate fidelity of 12-lead reconstructions, 3 performance metrics were defined. The results show that the reconstruction error is largest on QRS complex and smallest on ST segment for all 3 metrics. This indicates that the reconstruction of the ST segment, which carries the most important information for ischemia detection, is reconstructed with the highest quality. © 2019 IEEE.
PB  - IEEE
C3  - Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (41; 2019; Berlin)
T1  - Signal Quality in Reconstructed 12-Lead Ambulatory ECGs Recorded Using 3-Lead Device
SP  - 5481
EP  - 5487
DO  - 10.1109/EMBC.2019.8857251
ER  - 

@conference{
author = "Ivanović, Marija D. and Miletić, Marjan and Subotić, Ida and Boljević, Darko",
year = "2019",
abstract = "Acute myocardial infraction (AMI) is a leading cause of death in the developed countries. Survival of patients having acute coronary syndrome (ACS) dramatically depends on treatment delay. Hence, a technology that would enable ECG recording immediately after ACS symptom occurrence may significantly decrease AMI mortality. In this study we investigate the signal quality of reconstructed 12-lead ECGs by using 3-lead handheld device with dry electrode in realistic ambulatory conditions. For each subject enrolled in the study an individual transformation matrix was calculated during the calibration procedure, and used for 12-lead reconstruction whenever that subject sends a recording from a handheld device. To evaluate fidelity of 12-lead reconstructions, 3 performance metrics were defined. The results show that the reconstruction error is largest on QRS complex and smallest on ST segment for all 3 metrics. This indicates that the reconstruction of the ST segment, which carries the most important information for ischemia detection, is reconstructed with the highest quality. © 2019 IEEE.",
publisher = "IEEE",
journal = "Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (41; 2019; Berlin)",
title = "Signal Quality in Reconstructed 12-Lead Ambulatory ECGs Recorded Using 3-Lead Device",
pages = "5481-5487",
doi = "10.1109/EMBC.2019.8857251"
}

Ivanović, M. D., Miletić, M., Subotić, I.,& Boljević, D.. (2019). Signal Quality in Reconstructed 12-Lead Ambulatory ECGs Recorded Using 3-Lead Device. in Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (41; 2019; Berlin)
IEEE., 5481-5487.
https://doi.org/10.1109/EMBC.2019.8857251

Ivanović MD, Miletić M, Subotić I, Boljević D. Signal Quality in Reconstructed 12-Lead Ambulatory ECGs Recorded Using 3-Lead Device. in Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (41; 2019; Berlin). 2019;:5481-5487.
doi:10.1109/EMBC.2019.8857251 .

Ivanović, Marija D., Miletić, Marjan, Subotić, Ida, Boljević, Darko, "Signal Quality in Reconstructed 12-Lead Ambulatory ECGs Recorded Using 3-Lead Device" in Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (41; 2019; Berlin) (2019):5481-5487,
https://doi.org/10.1109/EMBC.2019.8857251 . .

TY  - JOUR
AU  - Ivanović, Marija D.
AU  - Petrović, Jovana S.
AU  - Savić, Andrej
AU  - Gligorić, Goran
AU  - Miletić, Marjan
AU  - Vukčević, Miodrag
AU  - Bojović, Boško
AU  - Hadžievski, Ljupčo
AU  - Allsop, Thomas P.
AU  - Webb, David J.
PY  - 2018
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/7637
AB  - Objective: The ventilators involved in non-invasive mechanical ventilation commonly provide ventilator support via a facemask. The interface of the mask with a patient promotes air leaks that cause errors in the feedback information provided by a pneumatic sensor and hence patient-ventilator asynchrony with multiple negative consequences. Our objective is to test the possibility of using chest-wall motion measured by an optical fibre-grating sensor as a more accurate non-invasive ventilator triggering mechanism. Approach: The basic premise of our approach is that the measurement accuracy can be improved by using a triggering signal that precedes pneumatic triggering in the neuro-ventilatory coupling sequence. We propose a technique that uses the measurement of chest-wall curvature by a long-period fibre-grating sensor. The sensor was applied externally to the rib-cage and interrogated in the lateral (edge) filtering scheme. The study was performed on 34 healthy volunteers. Statistical data analysis of the time lag between the fibregrating sensor and the reference pneumotachograph was preceded by the removal of the unwanted heartbeat signal by wavelet transform processing. Main results: The results show a consistent fibregrating signal advance with respect to the standard pneumatic signal by (230 +/- 100) ms in both the inspiratory and expiratory phases. We further show that heart activity removal yields a tremendous improvement in sensor accuracy by reducing it from 60 ml to 0.3 ml. Significance: The results indicate that the proposed measurement technique may lead to a more reliable triggering decision. Its imperviousness to air leaks, non-invasiveness, low-cost and ease of implementation offer good prospects for applications in both clinical and homecare ventilation.
T2  - Physiological Measurement
T1  - Real-time chest-wall-motion tracking by a single optical fibre grating: a prospective method for ventilator triggering
VL  - 39
IS  - 4
SP  - 045009
DO  - 10.1088/1361-6579/aab7ac
ER  - 

@article{
author = "Ivanović, Marija D. and Petrović, Jovana S. and Savić, Andrej and Gligorić, Goran and Miletić, Marjan and Vukčević, Miodrag and Bojović, Boško and Hadžievski, Ljupčo and Allsop, Thomas P. and Webb, David J.",
year = "2018",
abstract = "Objective: The ventilators involved in non-invasive mechanical ventilation commonly provide ventilator support via a facemask. The interface of the mask with a patient promotes air leaks that cause errors in the feedback information provided by a pneumatic sensor and hence patient-ventilator asynchrony with multiple negative consequences. Our objective is to test the possibility of using chest-wall motion measured by an optical fibre-grating sensor as a more accurate non-invasive ventilator triggering mechanism. Approach: The basic premise of our approach is that the measurement accuracy can be improved by using a triggering signal that precedes pneumatic triggering in the neuro-ventilatory coupling sequence. We propose a technique that uses the measurement of chest-wall curvature by a long-period fibre-grating sensor. The sensor was applied externally to the rib-cage and interrogated in the lateral (edge) filtering scheme. The study was performed on 34 healthy volunteers. Statistical data analysis of the time lag between the fibregrating sensor and the reference pneumotachograph was preceded by the removal of the unwanted heartbeat signal by wavelet transform processing. Main results: The results show a consistent fibregrating signal advance with respect to the standard pneumatic signal by (230 +/- 100) ms in both the inspiratory and expiratory phases. We further show that heart activity removal yields a tremendous improvement in sensor accuracy by reducing it from 60 ml to 0.3 ml. Significance: The results indicate that the proposed measurement technique may lead to a more reliable triggering decision. Its imperviousness to air leaks, non-invasiveness, low-cost and ease of implementation offer good prospects for applications in both clinical and homecare ventilation.",
journal = "Physiological Measurement",
title = "Real-time chest-wall-motion tracking by a single optical fibre grating: a prospective method for ventilator triggering",
volume = "39",
number = "4",
pages = "045009",
doi = "10.1088/1361-6579/aab7ac"
}

Ivanović, M. D., Petrović, J. S., Savić, A., Gligorić, G., Miletić, M., Vukčević, M., Bojović, B., Hadžievski, L., Allsop, T. P.,& Webb, D. J.. (2018). Real-time chest-wall-motion tracking by a single optical fibre grating: a prospective method for ventilator triggering. in Physiological Measurement, 39(4), 045009.
https://doi.org/10.1088/1361-6579/aab7ac

Ivanović MD, Petrović JS, Savić A, Gligorić G, Miletić M, Vukčević M, Bojović B, Hadžievski L, Allsop TP, Webb DJ. Real-time chest-wall-motion tracking by a single optical fibre grating: a prospective method for ventilator triggering. in Physiological Measurement. 2018;39(4):045009.
doi:10.1088/1361-6579/aab7ac .

Ivanović, Marija D., Petrović, Jovana S., Savić, Andrej, Gligorić, Goran, Miletić, Marjan, Vukčević, Miodrag, Bojović, Boško, Hadžievski, Ljupčo, Allsop, Thomas P., Webb, David J., "Real-time chest-wall-motion tracking by a single optical fibre grating: a prospective method for ventilator triggering" in Physiological Measurement, 39, no. 4 (2018):045009,
https://doi.org/10.1088/1361-6579/aab7ac . .

TY  - CONF
AU  - Atanasoski, Vladimir
AU  - Ivanović, Marija D.
AU  - Marinković, Miloš
AU  - Gligorić, Goran
AU  - Bojović, Boško
AU  - Shvilkin, Alexei V.
AU  - Petrović, Jovana S.
PY  - 2018
UR  - https://ieeexplore.ieee.org/document/8586997/
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/8050
AB  - Accurate automated detection of premature ventricular contractions from electrocardiogram requires a training set or expert intervention. We propose a fully automated unsupervised detection method. The algorithm first clusters morphologically similar heartbeats and then performs classification based on RR intervals and morphology. Tests on clinically recorded datasets show sensitivity of 94.7%, specificity of 99.6% and accuracy of 99.5%. © 2018 IEEE.
PB  - IEEE
C3  - 2018 14th Symposium on Neural Networks and Applications (NEUREL)
C3  - 14th Symposium on Neural Networks and Applications (NEUREL) (2018)
T1  - Unsupervised Classification of Premature Ventricular Contractions Based on RR Interval and Heartbeat Morphology
SP  - 1
EP  - 6
DO  - 10.1109/NEUREL.2018.8586997
ER  - 

@conference{
author = "Atanasoski, Vladimir and Ivanović, Marija D. and Marinković, Miloš and Gligorić, Goran and Bojović, Boško and Shvilkin, Alexei V. and Petrović, Jovana S.",
year = "2018",
abstract = "Accurate automated detection of premature ventricular contractions from electrocardiogram requires a training set or expert intervention. We propose a fully automated unsupervised detection method. The algorithm first clusters morphologically similar heartbeats and then performs classification based on RR intervals and morphology. Tests on clinically recorded datasets show sensitivity of 94.7%, specificity of 99.6% and accuracy of 99.5%. © 2018 IEEE.",
publisher = "IEEE",
journal = "2018 14th Symposium on Neural Networks and Applications (NEUREL), 14th Symposium on Neural Networks and Applications (NEUREL) (2018)",
title = "Unsupervised Classification of Premature Ventricular Contractions Based on RR Interval and Heartbeat Morphology",
pages = "1-6",
doi = "10.1109/NEUREL.2018.8586997"
}

Atanasoski, V., Ivanović, M. D., Marinković, M., Gligorić, G., Bojović, B., Shvilkin, A. V.,& Petrović, J. S.. (2018). Unsupervised Classification of Premature Ventricular Contractions Based on RR Interval and Heartbeat Morphology. in 2018 14th Symposium on Neural Networks and Applications (NEUREL)
IEEE., 1-6.
https://doi.org/10.1109/NEUREL.2018.8586997

Atanasoski V, Ivanović MD, Marinković M, Gligorić G, Bojović B, Shvilkin AV, Petrović JS. Unsupervised Classification of Premature Ventricular Contractions Based on RR Interval and Heartbeat Morphology. in 2018 14th Symposium on Neural Networks and Applications (NEUREL). 2018;:1-6.
doi:10.1109/NEUREL.2018.8586997 .

Atanasoski, Vladimir, Ivanović, Marija D., Marinković, Miloš, Gligorić, Goran, Bojović, Boško, Shvilkin, Alexei V., Petrović, Jovana S., "Unsupervised Classification of Premature Ventricular Contractions Based on RR Interval and Heartbeat Morphology" in 2018 14th Symposium on Neural Networks and Applications (NEUREL) (2018):1-6,
https://doi.org/10.1109/NEUREL.2018.8586997 . .

TY  - JOUR
AU  - Mančić, Ana
AU  - Baronio, Fabio
AU  - Hadžievski, Ljupčo
AU  - Wabnitz, Stefan
AU  - Maluckov, Aleksandra
PY  - 2018
UR  - https://link.aps.org/doi/10.1103/PhysRevE.98.012209
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/7797
AB  - We present a statistical analysis based on the height and return-time probabilities of high-amplitude wave events in both focusing and defocusing Manakov systems. We find that analytical rational or semirational solutions, associated with extreme, rogue wave (RW) structures, are the leading high-amplitude events in this system. We define the thresholds for classifying an extreme wave event as a RW. Our results indicate that there is a strong relationship between the type of RW and the mechanism which is responsible for its creation. Initially, high-amplitude events originate from modulation instability. Upon subsequent evolution, the interaction among these events prevails as the mechanism for RW creation. We suggest a strategy for confirming the basic properties of different extreme events. This involves the definition of proper statistical measures at each stage of the RW dynamics. Our results point to the need for redefining criteria for identifying RW events.
T2  - Physical Review E
T1  - Statistics of vector Manakov rogue waves
VL  - 98
IS  - 1
SP  - 012209
DO  - 10.1103/PhysRevE.98.012209
ER  - 

@article{
author = "Mančić, Ana and Baronio, Fabio and Hadžievski, Ljupčo and Wabnitz, Stefan and Maluckov, Aleksandra",
year = "2018",
abstract = "We present a statistical analysis based on the height and return-time probabilities of high-amplitude wave events in both focusing and defocusing Manakov systems. We find that analytical rational or semirational solutions, associated with extreme, rogue wave (RW) structures, are the leading high-amplitude events in this system. We define the thresholds for classifying an extreme wave event as a RW. Our results indicate that there is a strong relationship between the type of RW and the mechanism which is responsible for its creation. Initially, high-amplitude events originate from modulation instability. Upon subsequent evolution, the interaction among these events prevails as the mechanism for RW creation. We suggest a strategy for confirming the basic properties of different extreme events. This involves the definition of proper statistical measures at each stage of the RW dynamics. Our results point to the need for redefining criteria for identifying RW events.",
journal = "Physical Review E",
title = "Statistics of vector Manakov rogue waves",
volume = "98",
number = "1",
pages = "012209",
doi = "10.1103/PhysRevE.98.012209"
}

Mančić, A., Baronio, F., Hadžievski, L., Wabnitz, S.,& Maluckov, A.. (2018). Statistics of vector Manakov rogue waves. in Physical Review E, 98(1), 012209.
https://doi.org/10.1103/PhysRevE.98.012209

Mančić A, Baronio F, Hadžievski L, Wabnitz S, Maluckov A. Statistics of vector Manakov rogue waves. in Physical Review E. 2018;98(1):012209.
doi:10.1103/PhysRevE.98.012209 .

Mančić, Ana, Baronio, Fabio, Hadžievski, Ljupčo, Wabnitz, Stefan, Maluckov, Aleksandra, "Statistics of vector Manakov rogue waves" in Physical Review E, 98, no. 1 (2018):012209,
https://doi.org/10.1103/PhysRevE.98.012209 . .

TY  - JOUR
AU  - Mančić, Ana
AU  - Baronio, Fabio
AU  - Hadžievski, Ljupčo
AU  - Wabnitz, Stefan
AU  - Maluckov, Aleksandra
PY  - 2018
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/7798
UR  - https://arxiv.org/pdf/1807.01941.pdf
AB  - We present a statistical analysis based on the height and return-time probabilities of high-amplitude wave events in both focusing and defocusing Manakov systems. We find that analytical rational or semirational solutions, associated with extreme, rogue wave (RW) structures, are the leading high-amplitude events in this system. We define the thresholds for classifying an extreme wave event as a RW. Our results indicate that there is a strong relationship between the type of RW and the mechanism which is responsible for its creation. Initially, high-amplitude events originate from modulation instability. Upon subsequent evolution, the interaction among these events prevails as the mechanism for RW creation. We suggest a strategy for confirming the basic properties of different extreme events. This involves the definition of proper statistical measures at each stage of the RW dynamics. Our results point to the need for redefining criteria for identifying RW events.
T2  - Physical Review E
T1  - Statistics of vector Manakov rogue waves
VL  - 98
IS  - 1
SP  - 012209
DO  - 10.1103/PhysRevE.98.012209
ER  - 

@article{
author = "Mančić, Ana and Baronio, Fabio and Hadžievski, Ljupčo and Wabnitz, Stefan and Maluckov, Aleksandra",
year = "2018",
abstract = "We present a statistical analysis based on the height and return-time probabilities of high-amplitude wave events in both focusing and defocusing Manakov systems. We find that analytical rational or semirational solutions, associated with extreme, rogue wave (RW) structures, are the leading high-amplitude events in this system. We define the thresholds for classifying an extreme wave event as a RW. Our results indicate that there is a strong relationship between the type of RW and the mechanism which is responsible for its creation. Initially, high-amplitude events originate from modulation instability. Upon subsequent evolution, the interaction among these events prevails as the mechanism for RW creation. We suggest a strategy for confirming the basic properties of different extreme events. This involves the definition of proper statistical measures at each stage of the RW dynamics. Our results point to the need for redefining criteria for identifying RW events.",
journal = "Physical Review E",
title = "Statistics of vector Manakov rogue waves",
volume = "98",
number = "1",
pages = "012209",
doi = "10.1103/PhysRevE.98.012209"
}

Mančić, A., Baronio, F., Hadžievski, L., Wabnitz, S.,& Maluckov, A.. (2018). Statistics of vector Manakov rogue waves. in Physical Review E, 98(1), 012209.
https://doi.org/10.1103/PhysRevE.98.012209

Mančić A, Baronio F, Hadžievski L, Wabnitz S, Maluckov A. Statistics of vector Manakov rogue waves. in Physical Review E. 2018;98(1):012209.
doi:10.1103/PhysRevE.98.012209 .

Mančić, Ana, Baronio, Fabio, Hadžievski, Ljupčo, Wabnitz, Stefan, Maluckov, Aleksandra, "Statistics of vector Manakov rogue waves" in Physical Review E, 98, no. 1 (2018):012209,
https://doi.org/10.1103/PhysRevE.98.012209 . .

TY  - JOUR
AU  - Ivanović, Marija D.
AU  - Ring, Matthias
AU  - Baronio, Fabio
AU  - Calza, Stefano
AU  - Vukčević, Vladan
AU  - Hadžievski, Ljupčo
AU  - Maluckov, Aleksandra
AU  - Eskofier, Bjoern Michael
PY  - 2018
UR  - http://stacks.iop.org/2057-1976/5/i=1/a=015012?key=crossref.179380a6d1fbac3633b726787a95feb5
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/8095
AB  - Objective: Algorithms to predict shock outcome based on ventricular fibrillation (VF) waveform features are potentially useful tool to optimize defibrillation strategy (immediate defibrillation versus cardiopulmonary resuscitation). Researchers have investigated numerous predictive features and classification methods using single VF feature and/or their combinations, however reported predictabilities are not consistent. The purpose of this study was to validate whether combining VF features can enhance the prediction accuracy in comparison to single feature. Approach: The analysis was performed in 3 stages: feature extraction, preprocessing and feature selection and classification. Twenty eight predictive features were calculated on 4s episode of the pre-shock VF signal. The preprocessing included instances normalization and oversampling. Seven machine learning algorithms were employed for selecting the best performin single feature and combination of features using wrapper method: Logistic Regression (LR), Naïve-Bayes (NB), Decision tree (C4.5), AdaBoost.M1 (AB), Support Vector Machine (SVM), Nearest Neighbour (NN) and Random Forest (RF). Evaluation of the algorithms was performed by nested 10 fold cross-validation procedure. Main results: A total of 251 unbalanced first shocks (195 unsuccessful and 56 successful) were oversampled to 195 instances in each class. Performance metric based on average accuracy of feature combination has shown that LR and NB exhibit no improvement, C4.5 and AB an improvement not greater than 1% and SVM, NN and RF an improvement greater than 5% in predicting defibrillation outcome in comparison to the best single feature. Significance: By performing wrapper method to select best performing feature combination the non-linear machine learning strategies (SVM, NN, RF) can improve defibrillation prediction performance. © 2018 IOP Publishing Ltd.
T2  - Biomedical Physics and Engineering Express
T1  - ECG derived feature combination versus single feature in predicting defibrillation success in out-of-hospital cardiac arrested patients
VL  - 5
IS  - 1
SP  - 015012
DO  - 10.1088/2057-1976/aaebec
ER  - 

@article{
author = "Ivanović, Marija D. and Ring, Matthias and Baronio, Fabio and Calza, Stefano and Vukčević, Vladan and Hadžievski, Ljupčo and Maluckov, Aleksandra and Eskofier, Bjoern Michael",
year = "2018",
abstract = "Objective: Algorithms to predict shock outcome based on ventricular fibrillation (VF) waveform features are potentially useful tool to optimize defibrillation strategy (immediate defibrillation versus cardiopulmonary resuscitation). Researchers have investigated numerous predictive features and classification methods using single VF feature and/or their combinations, however reported predictabilities are not consistent. The purpose of this study was to validate whether combining VF features can enhance the prediction accuracy in comparison to single feature. Approach: The analysis was performed in 3 stages: feature extraction, preprocessing and feature selection and classification. Twenty eight predictive features were calculated on 4s episode of the pre-shock VF signal. The preprocessing included instances normalization and oversampling. Seven machine learning algorithms were employed for selecting the best performin single feature and combination of features using wrapper method: Logistic Regression (LR), Naïve-Bayes (NB), Decision tree (C4.5), AdaBoost.M1 (AB), Support Vector Machine (SVM), Nearest Neighbour (NN) and Random Forest (RF). Evaluation of the algorithms was performed by nested 10 fold cross-validation procedure. Main results: A total of 251 unbalanced first shocks (195 unsuccessful and 56 successful) were oversampled to 195 instances in each class. Performance metric based on average accuracy of feature combination has shown that LR and NB exhibit no improvement, C4.5 and AB an improvement not greater than 1% and SVM, NN and RF an improvement greater than 5% in predicting defibrillation outcome in comparison to the best single feature. Significance: By performing wrapper method to select best performing feature combination the non-linear machine learning strategies (SVM, NN, RF) can improve defibrillation prediction performance. © 2018 IOP Publishing Ltd.",
journal = "Biomedical Physics and Engineering Express",
title = "ECG derived feature combination versus single feature in predicting defibrillation success in out-of-hospital cardiac arrested patients",
volume = "5",
number = "1",
pages = "015012",
doi = "10.1088/2057-1976/aaebec"
}

Ivanović, M. D., Ring, M., Baronio, F., Calza, S., Vukčević, V., Hadžievski, L., Maluckov, A.,& Eskofier, B. M.. (2018). ECG derived feature combination versus single feature in predicting defibrillation success in out-of-hospital cardiac arrested patients. in Biomedical Physics and Engineering Express, 5(1), 015012.
https://doi.org/10.1088/2057-1976/aaebec

Ivanović MD, Ring M, Baronio F, Calza S, Vukčević V, Hadžievski L, Maluckov A, Eskofier BM. ECG derived feature combination versus single feature in predicting defibrillation success in out-of-hospital cardiac arrested patients. in Biomedical Physics and Engineering Express. 2018;5(1):015012.
doi:10.1088/2057-1976/aaebec .

Ivanović, Marija D., Ring, Matthias, Baronio, Fabio, Calza, Stefano, Vukčević, Vladan, Hadžievski, Ljupčo, Maluckov, Aleksandra, Eskofier, Bjoern Michael, "ECG derived feature combination versus single feature in predicting defibrillation success in out-of-hospital cardiac arrested patients" in Biomedical Physics and Engineering Express, 5, no. 1 (2018):015012,
https://doi.org/10.1088/2057-1976/aaebec . .