Prediction of countershock success using single features from multiple ventricular fibrillation frequency bands and feature combinations using neural networks

被引:86
作者
Neurauter, Andreas
Eftestol, Trygve
Kramer-Johansen, Jo
Abella, Benjamin S.
Sunde, Kjetil
Wenzel, Volker
Lindner, Karl H.
Eilevstjonn, Joar
Mykebust, Helge
Steen, Petter A.
Strohmenger, Hans-Ulrich [1 ]
机构
[1] Innsbruck Med Univ, Dept Anaesthesiol & Crit Care Med, Innsbruck, Austria
[2] Univ Stavanger, Dept Elect & Comp Engn, Stavanger, Norway
[3] Ullevaal Univ Hosp, Dept Anaesthesiol, Expt Med Res Inst, Oslo, Norway
[4] Ullevaal Univ Hosp, Prehosp Div, Oslo, Norway
[5] Univ Chicago Hosp, Emergency Resuscitat Ctr, Chicago, IL USA
[6] Univ Chicago Hosp, Sect Emergency Med, Chicago, IL USA
[7] Laerdal Med AS, Stavanger, Norway
关键词
ventricutar fibrillation; electrocardiography; outcome prediction; slope; neural networks;
D O I
10.1016/j.resuscitation.2006.10.002
中图分类号
R4 [临床医学];
学科分类号
1002 ; 100602 ;
摘要
Targeted defibrillation therapy is needed to optimise survival chances of ventricular fibrillation (VF) patients, but at present VF analysis strategies to optimise defibrillation timing have insufficient predictive power. From 197 patients with inhospital and out-of-hospital cardiac arrest, 770 electrocardiogram (ECG) recordings of countershock attempts were analysed. Preshock VF ECG features in the time and frequency domain were tested retrospectively for outcome prediction. Using band pass filters, the ECG spectrum was split into various frequency bands of 2-26Hz bandwidth in the range of 0-26Hz. Neural networks were used for single feature combinations to optimise prediction of countershock success. Areas under curves (AUC) of receiver operating characteristics (ROC) were used to estimate prediction power of single and combined features. The highest ROC AUC of 0.863 was reached by the median slope in the interval 10-22 Hz resulting in a sensitivity of 95% and a specificity of 50%. The best specificity of 55% at the 95% sensitivity [eve[ was reached by power spectrum analysis (PSA) in the 6-26 Hz interval. Neural networks combining single predictive features were unable to increase outcome prediction. Using frequency band segmentation of human VF ECG, several single predictive features with high ROC AUC > 0.840 were identified. Combining these single predictive features using neural networks did not further improve outcome prediction in human VF data. This may indicate that various simple VF features, such as median slope already reach the maximum prediction power extractable from VF ECG. (C) 2006 Elsevier Ireland Ltd. AU rights reserved.
引用
收藏
页码:253 / 263
页数:11
相关论文
共 27 条
[1]   Compression depth estimation for CPR quality assessment using DSP on accelerometer signals [J].
Aase, SO ;
Myklebust, H .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2002, 49 (03) :263-268
[2]   Quality of cardiopulmonary resuscitation during in-hospital cardiac arrest [J].
Abella, BS ;
Alvarado, JP ;
Myklebust, H ;
Edelson, DP ;
Barry, A ;
O'Hearn, N ;
Vanden Hoek, TL ;
Becker, LB .
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2005, 293 (03) :305-310
[3]   The beneficial effect of basic life support on ventricular fibrillation mean frequency and coronary perfusion pressure [J].
Achleitner, U ;
Wenzel, V ;
Strohmenger, HU ;
Lindner, KH ;
Baubin, MA ;
Krismer, AC ;
Mayr, VD ;
Amann, A .
RESUSCITATION, 2001, 51 (02) :151-158
[4]  
[Anonymous], 1996, PATTERN CLASSIFICATI
[5]   Signal analysis of the human electrocardiogram during ventricular fibrillation: Frequency and amplitude parameters as predictors of successful countershock [J].
Brown, CG ;
Dzwonczyk, R .
ANNALS OF EMERGENCY MEDICINE, 1996, 27 (02) :184-188
[6]   Scaling exponent predicts defibrillation success for out-of-hospital ventricular fibrillation cardiac arrest [J].
Callaway, CW ;
Sherman, LD ;
Mosesso, VN ;
Dietrich, TJ ;
Holt, E ;
Clarkson, MC .
CIRCULATION, 2001, 103 (12) :1656-1661
[7]   RECOMMENDED GUIDELINES FOR UNIFORM REPORTING OF DATA FROM OUT-OF-HOSPITAL CARDIAC-ARREST - THE UTSTEIN STYLE [J].
CHAMBERLAIN, D ;
CUMMINS, RO .
RESUSCITATION, 1991, 22 (01) :1-26
[8]   European Resuscitation Council Guidelines for Resuscitation 2005 - Section 3. Electrical therapies: Automated external defibrillators, defibrillation., cardioversion and pacing [J].
Deakin, CD ;
Nolan, JP .
RESUSCITATION, 2005, 67 :S25-S37
[9]  
Demuth H., NEURAL NETWORK TOOLB
[10]   Effects of interrupting precordial compressions on the calculated probability of defibrillation success during out-of-hospital cardiac arrest [J].
Eftestol, T ;
Sunde, K ;
Steen, PA .
CIRCULATION, 2002, 105 (19) :2270-2273