Author/Editor		Podbregar, Matej; Kovačič, Miha; Podbregar-Marš, Andreja; Brezočnik, Miran
Title		Napovedovanje uspešnosti defibrilacije s pomočjo "genetskega" programiranja pri bolnikih z zunajbolnišničnim srčnim zastojem
Translated title		Predicting defibrillation success by "genetic" programming in patients with out-of-hospital cardiac arrest
Type		članek
Source		In: Bručan A, Gričar M, Vajd R, editors. Urgentna medicina: izbrana poglavja. Zbornik 10. mednarodni simpozij o urgentni medicini; 2003 jun 11-14; Portorož. Ljubljana: Slovensko združenje za urgentno medicino,
Publication year		2003
Volume		str. 163-5
Language		slo
Abstract		In some patients with ventricular fibrillation (VF) we might have a better chance of successful defibrillation after a period with chest compression and ventilation before the defibrillation attempt: It would therefore be important to know whether a defibrillation will be successful. 203 defibrillations were administered in 47 patients with out-of-hospital cardiac arrest due to cardiac cause. Model developed by "genetic" programming (GP) to predict defibrillation success was constructed using: maximal amplitude, a total energy of power spectral density, and Hurst exponent of VF electrocardiogram (ECG) signal. Positive and negative likelihood ratios of the model for testing data were 35.5 and 0.00, respectively. Using model developed by GP on the complete database, 120 of 124 not-successful defibrillations would have been avoided, whereas al) of 79 successful defibrillations would have been administered. The VF ECG contains information predictive of defibrillation suceess. Model developed by GP, including data from time-domain, frequency domain and nonlinear dynamics, could reduce the delivery of unsuccessful defibrillations.
Descriptors		EMERGENCY MEDICAL SERVICES HEART ARREST VENTRICULAR FIBRILLATION HEART MASSAGE RESPIRATION, ARTIFICIAL PROGNOSIS