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  - 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 . .