Abstract 271: Detection of Ventricular Fibrillation with Continuing Chest Compression Using Adaptive Least Mean-Square Estimation of Cardiopulmonary Resuscitation Artifacts and Removal of the Artifacts
Introduction: Adequate perfusion during cardiopulmonary resuscitation (CPR) is crucial for successful defibrillation after ventricular fibrillation (VF), but the effects of chest compressions (CC) are compromised from interruptions due to rhythm analysis. A novel algorithm utilizing corrupted ECG signal to detect VF during continuing CC is developed.
Method: VF waveforms were retrieved from automatic external defibrillator (AED) records of adult non-traumatic cardiac arrests. Ten CC artifacts were retrieved from arrests with asystole. Corrupted ECG was constructed by adding a scaled CC artifact to a VF with strength determined by signal-to-interference ratio (SIR). Using empirical mode decomposition, the fluctuation and frequency of CC were retrieved. VF was detected by subtracting the CC artifacts, modeled by least mean-square (LMS) algorithm, from ECG signals. Amplitude spectrum analysis (AMSA) was used to quantify the component with frequency range 0.7[[Unable to Display Character: ‐]]30 Hz.
Result: One-hundred and fifty VF (36 successful and 114 unsuccessful defibrillation, p<0.01) were included. After removing CC artifacts with the algorithm, successful vs unsuccessful cases remained distinguished (p<0.05) in SIR ranged 0 to -9dB. The detected and the original VFs had similar AMSA with correlation of 0.98, 0.95, 0.93 and 0.86 when SIR were 0, -3, -6 and -9dB (p<0.001). The mean of difference between the detected VFs and the original VFs were 0.19, 0.56, 1.36 and 3.33 for SIR of 0, -3, -6 and -9dB, respectively, in Bland-Altman plot.
Conclusions: The proposed adaptive algorithm using LMS could model CPR artifact without external signals, and effectively detect VF with continuing CC.
- Cardiac arrest
- Cardiopulmonary resuscitation
- Ventricular fibrillation
- Emergency care
- © 2012 by American Heart Association, Inc.