ECG derived feature combination versus single feature in predicting defibrillation success in out-of-hospital cardiac arrested patients

Beitrag in einer Fachzeitschrift
(Originalarbeit)


Details zur Publikation

Autorinnen und Autoren: Ivanovic M, Ring M, Baronio F, Calza S, Vukcevic V, Hadzievski L, Maluckov A, Eskofier B
Zeitschrift: Biomedical Physics and Engineering Express
Jahr der Veröffentlichung: 2018
Band: 5
Heftnummer: 1
Seitenbereich: 015012
ISSN: 2057-1976
Sprache: Englisch


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 performing 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.


FAU-Autorinnen und Autoren / FAU-Herausgeberinnen und Herausgeber

Eskofier, Björn Prof. Dr.
Lehrstuhl für Informatik 14 (Maschinelles Lernen und Datenanalytik)
Lehrstuhl für Informatik 14 (Maschinelles Lernen und Datenanalytik)
Ivanovic, Marija
Lehrstuhl für Informatik 14 (Maschinelles Lernen und Datenanalytik)
Ring, Matthias


Zitierweisen

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

MLA:
Ivanovic, Marija, et al. "ECG derived feature combination versus single feature in predicting defibrillation success in out-of-hospital cardiac arrested patients." Biomedical Physics and Engineering Express 5.1 (2018): 015012.

BibTeX: 

Zuletzt aktualisiert 2019-06-01 um 11:10