Machine Learning Techniques for the Detection of Shockable Rhythms in Automated External Defibrillators

Carlos Figuera, Unai Irusta, Eduardo Morgado, Elisabete Aramendi, Unai Ayala, Lars Wik, Jo Kramer-Johansen, Trygve Eftestøl, Felipe Alonso-Atienza, Carlos Figuera, Unai Irusta, Eduardo Morgado, Elisabete Aramendi, Unai Ayala, Lars Wik, Jo Kramer-Johansen, Trygve Eftestøl, Felipe Alonso-Atienza

Abstract

Early recognition of ventricular fibrillation (VF) and electrical therapy are key for the survival of out-of-hospital cardiac arrest (OHCA) patients treated with automated external defibrillators (AED). AED algorithms for VF-detection are customarily assessed using Holter recordings from public electrocardiogram (ECG) databases, which may be different from the ECG seen during OHCA events. This study evaluates VF-detection using data from both OHCA patients and public Holter recordings. ECG-segments of 4-s and 8-s duration were analyzed. For each segment 30 features were computed and fed to state of the art machine learning (ML) algorithms. ML-algorithms with built-in feature selection capabilities were used to determine the optimal feature subsets for both databases. Patient-wise bootstrap techniques were used to evaluate algorithm performance in terms of sensitivity (Se), specificity (Sp) and balanced error rate (BER). Performance was significantly better for public data with a mean Se of 96.6%, Sp of 98.8% and BER 2.2% compared to a mean Se of 94.7%, Sp of 96.5% and BER 4.4% for OHCA data. OHCA data required two times more features than the data from public databases for an accurate detection (6 vs 3). No significant differences in performance were found for different segment lengths, the BER differences were below 0.5-points in all cases. Our results show that VF-detection is more challenging for OHCA data than for data from public databases, and that accurate VF-detection is possible with segments as short as 4-s.

Conflict of interest statement

Competing Interests: The authors have declared that no competing interests exist.

Figures

Fig 1. Examples of ECG found in…
Fig 1. Examples of ECG found in public (top) and OHCA (bottom) data.
The top-left segment corresponds to a VF from CUDB (record, cu05) right after VF onset, and presents large amplitude and a fibrillation frequency of 4.5 Hz. The bottom-left segments were recorded during OHCA 5–10 minutes after VF onset, and have smaller amplitudes and fibrillation frequencies (3.5 Hz and 2.5 Hz). The top-right segment corresponds to a NSR from cu05 right before VF onset. The bottom-right segments are examples of PEA in OHCA patients. Both cases show aberrant QRS complexes and low heart rates. The bottom example presents an extremely low heart-rate of 15 beats per minute.
Fig 2. Overview of the test procedure.
Fig 2. Overview of the test procedure.
Blue boxes specify the figures and tables where the results corresponding to each procedure can be found in the manuscript.
Fig 3. Box plots of the performance…
Fig 3. Box plots of the performance metrics for the five algorithms for the public databases (a) and the OHCA database (b).
All features were included in the algorithms.
Fig 4. Feature selection with BSTsel (top)…
Fig 4. Feature selection with BSTsel (top) and the L1-LRsel (bottom) approaches.
The results are shown for 4-s (left) and 8-s (right) segments for both public and OHCA databases. The mean BER is shown (with errorbars) for each subset size, and the horizontal line represents the subset selection threshold for the public (red) and OHCA (green) databases. The triangle and dot marks and their corresponding numbers represent the selected subset and the minimum BER subset, respectively.
Fig 5. Examples of misclassified 8-s ECG…
Fig 5. Examples of misclassified 8-s ECG samples from the public (left) and OHCA (right) databases.
A VF is shown on top and two nonshockable rhythms below for both databases.

References

    1. Hayashi M, Shimizu W, Albert CM. The spectrum of epidemiology underlying sudden cardiac death. Circulation research. 2015;116(12):1887–1906. 10.1161/CIRCRESAHA.116.304521
    1. Hallstrom A, Ornato JP. Public-access defibrillation and survival after out-of-hospital cardiac arrest. The New England journal of medicine. 2004;351(7):637 10.1056/NEJMoa040566
    1. Kerber RE, Becker LB, Bourland JD, Cummins RO, Hallstrom AP, Michos MB, et al. Automatic External Defibrillators for Public Access Defibrillation: Recommendations for Specifying and Reporting Arrhythmia Analysis Algorithm Performance, Incorporating New Waveforms, and Enhancing Safety A Statement for Health Professionals From the American Heart Association Task Force on Automatic External Defibrillation, Subcommittee on AED Safety and Efficacy. Circulation. 1997;95(6):1677–1682.
    1. Kuo S, Dillman R. Computer detection of ventricular fibrillation In: Computers in Cardiology; 1978. p. 2747–2750.
    1. Chen S, Thakor NV, Mower MM. Ventricular fibrillation detection by a regression test on the autocorrelation function. Medical and Biological Engineering and Computing. 1987. May;25(3):241–9. 10.1007/BF02447420
    1. Barro S, Ruiz R, Cabello D, Mira J. Algorithmic sequential decision making in the frequency domain for life threatening centricular arrhythmias and aimitative artifacts: a diagnostic system. Journal of Biomedical Engineering. 1989. July;11(4):320–8. 10.1016/0141-5425(89)90067-8
    1. Thakor NV, Zhu YS, Pan KY. Ventricular tachycardia and fibrillation detection by a sequential hypothesis testing algorithm. IEEE Transactions on Biomedical Engineering. 1990. September;37(9):837–43. 10.1109/10.58594
    1. Clayton RH, Murray A. Comparison of techniques for time-frequency analysis of the ECG during human ventricular fibrillation In: IEE Proceedings Science, Measurement and Technology. vol. 145; 1998. p. 301–6.
    1. Zhang XS, Zhu YS, Thakor NV, Wang ZZ. Detecting ventricular tachycardia and fibrillation by complexity measure. IEEE Transactions on Biomedical Engineering. 1999. May;46(5):548–55. 10.1109/10.759055
    1. Jekova I, Krasteva V. Real time detection of ventricular fibrillation and tachycardia. Physiological Measurement. 2004;25(5):1167 10.1088/0967-3334/25/5/007
    1. Amann A, Tratnig R, Unterkofler K. Reliability of old and new ventricular fibrillation detection algorithms for automated external defibrillators. Biomedical Engineering Online. 2005. October;4(60).
    1. Amann A, Tratnig R, Unterkofler K. Detecting ventricular fibrillation by time-delay methods. IEEE Transactions on Biomedical Engineering. 2007. January;54(1):174–177. 10.1109/TBME.2006.880909
    1. Jekova I. Shock advisory tool: Detection of life-threatening cardiac arrhythmias and shock success prediction by means of a common parameter set. Biomedical Signal Processing and Control. 2007;2(1):25–33. 10.1016/j.bspc.2007.01.002
    1. Anas E, Lee S, Hasan M. Sequential algorithm for life threatening cardiac pathologies detection based on mean signal strength and EMD functions. BioMedical Engineering OnLine. 2010;9(1):43 10.1186/1475-925X-9-43
    1. Arafat M, Chowdhury A, Hasan M. A simple time domain algorithm for the detection of ventricular fibrillation in electrocardiogram. Signal, Image and Video Processing. 2011;5:1–10. 10.1007/s11760-009-0136-1
    1. Alonso-Atienza F, Morgado E, Fernandez-Martinez L, Garcia-Alberola A, Rojo-Alvarez J. Detection of life-threatening arrhythmias using feature selection and support vector machines. Biomedical Engineering, IEEE Transactions on. 2014;61(3):832–840. 10.1109/TBME.2013.2290800
    1. Li Q, Rajagopalan C, Clifford GD. Ventricular Fibrillation and Tachycardia Classification Using a Machine Learning Approach. Biomedical Engineering, IEEE Transactions on. 2014. June;61(6):1607–1613. 10.1109/TBME.2013.2275000
    1. Moody GB, Mark RG. The impact of the MIT-BIH Arrhythmia Database. Engineering in Medicine and Biology Magazine, IEEE. 2001;20(3):45–50. 10.1109/51.932724
    1. Greenwald SD. The Development and Analysis of a Ventricular Fibrillation Detector. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science; 1986.
    1. Nolle FM, Badura FK, Catlett JM, W BR, H SM. CREI-GARD, a new concept in computerized arrhythmia monitoring systems In: Computers in Cardiology. vol. 13; 1986. p. 515–518.
    1. Weaver WD, Cobb LA, Dennis D, Ray R, Hallstrom AP, Copass MK. Amplitude of ventricular fibrillation waveform and outcome after cardiac arrest. Ann Intern Med. 1985. January;102(1):53–55. 10.7326/0003-4819-102-1-53
    1. Krasteva V, Jekova I, Dotsinsky I, Didon JP. Shock advisory system for heart rhythm analysis during cardiopulmonary resuscitation using a single ECG input of automated external defibrillators. Ann Biomed Eng. 2010. April;38(4):1326–1336. 10.1007/s10439-009-9885-9
    1. Ayala U, Irusta U, Ruiz J, Eftestøl T, Kramer-Johansen J, Alonso-Atienza F, et al. A Reliable Method for Rhythm Analysis during Cardiopulmonary Resuscitation. BioMed Research International. 2014;2014 10.1155/2014/872470
    1. Wik L, Kramer-Johansen J, Myklebust H, Sørebø H, Svensson L, Fellows B, et al. Quality of cardiopulmonary resuscitation during out-of-hospital cardiac arrest. JAMA. 2005. January;293(3):299–304. 10.1001/jama.293.3.299
    1. Kramer-Johansen J, Myklebust H, Wik L, Fellows B, Svensson L, Sørebø H, et al. Quality of out-of-hospital cardiopulmonary resuscitation with real time automated feedback: a prospective interventional study. Resuscitation. 2006. December;71(3):283–292. 10.1016/j.resuscitation.2006.05.011
    1. Li Y, Bisera J, Geheb F, Tang W, Weil MH. Identifying potentially shockable rhythms without interrupting cardiopulmonary resuscitation. Crit Care Med. 2008. January;36(1):198–203. 10.1097/01.CCM.0000295589.64729.6B
    1. Irusta U, Ruiz J, Aramendi E, de Gauna SR, Ayala U, Alonso E. A high-temporal resolution algorithm to discriminate shockable from nonshockable rhythms in adults and children. Resuscitation. 2012;83(9):1090–1097. 10.1016/j.resuscitation.2012.01.032
    1. Jekova I, Krasteva V, Ménétré S, Stoyanov T, Christov I, Fleischhackl R, et al. Bench study of the accuracy of a commercial AED arrhythmia analysis algorithm in the presence of electromagnetic interferences. Physiol Meas. 2009. July;30(7):695–705. 10.1088/0967-3334/30/7/012
    1. Li Y, Bisera J, Weil MH, Tang W. An Algorithm Used for Ventricular Fibrillation Detection Without Interrupting Chest Compression. IEEE Transactions on Biomedical Engineering. 2012. January;59(1):78–86. 10.1109/TBME.2011.2118755
    1. Lake DE, Richman JS, Griffin MP, Moorman JR. Sample entropy analysis of neonatal heart rate variability. Am J Physiol Regul Integr Comp Physiol. 2002. September;283(3):R789–797. 10.1152/ajpregu.00069.2002
    1. Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning Springer Series in Statistics. New York, NY, USA: Springer New York Inc.; 2001.
    1. Camps-Valls G, Rojo-Álvarez JL, Martínez-Ramón M. Kernel methods in bioengineering, communications and image processing. Hershey, PA, USA: Idea Group Inc.; 2007.
    1. Amann A, Tratnig R, Unterkofler K. A new ventricular fibrillation detection algorithm for automated external defibrillators In: Computers in Cardiology; 2005. p. 559–562.
    1. Jekova I. Comparison of five algorithms for the detection of ventricular fibrillation from the surface ECG. Physiological Measurement. 2000;21:429–39. 10.1088/0967-3334/21/4/301
    1. Aramendi E, Irusta U, Pastor E, Bodegas A, Benito F. ECG spectral and morphological parameters reviewed and updated to detect adult and paediatric life-threatening arrhythmia. Physiological Measurement. 2010;31(6):749 10.1088/0967-3334/31/6/002
    1. Irusta U, Ruiz J. An algorithm to discriminate supraventricular from ventricular tachycardia in automated external defibrillators valid for adult and paediatric patients. Resuscitation. 2009. November;80(11):1229–1233. 10.1016/j.resuscitation.2009.07.013
    1. Ayala U, Irusta U, Alonso E, Gonzalez D. Performance of VF detection parameters in an algorithm design scenario and in a real resuscitation scenario In: Computing in Cardiology, 2011. IEEE; 2011. p. 545–548.
    1. Didon JP, Krasteva V, Méenéetré S, Stoyanov T, Jekova I. Shock advisory system with minimal delay triggering after end of chest compressions: accuracy and gained hands-off time. Resuscitation. 2011. December;82 Suppl 2:S8–15. 10.1016/S0300-9572(11)70145-9
    1. Ruiz J, Ayala U, Ruiz de Gauna S, Irusta U, Gonzáalez-Otero D, Alonso E, et al. Feasibility of automated rhythm assessment in chest compression pauses during cardiopulmonary resuscitation. Resuscitation. 2013. September;84 9:1223–1228. 10.1016/j.resuscitation.2013.01.034
    1. Monsieurs KG, Nolan JP, Bossaert LL, Greif R, Maconochie IK, Nikolaou NI, et al. European Resuscitation Council Guidelines for Resuscitation 2015: Section 1. Executive summary. Resuscitation. 2015. October;95:1–80. 10.1016/j.resuscitation.2015.07.038
    1. Weisfeldt ML, Becker LB. Resuscitation after cardiac arrest: a 3-phase time-sensitive model. JAMA. 2002. December;288(23):3035–3038. 10.1001/jama.288.23.3035
    1. Brown CG, Dzwonczyk R, Martin DR. Physiologic measurement of the ventricular fibrillation ECG signal: estimating the duration of ventricular fibrillation. Ann Emerg Med. 1993. January;22(1):70–74. 10.1016/S0196-0644(05)80253-7
    1. Sherman LD, Rea TD, Waters JD, Menegazzi JJ, Callaway CW. Logarithm of the absolute correlations of the ECG waveform estimates duration of ventricular fibrillation and predicts successful defibrillation. Resuscitation. 2008. September;78(3):346–354. 10.1016/j.resuscitation.2008.04.009
    1. Daya MR, Schmicker RH, Zive DM, Rea TD, Nichol G, Buick JE, et al. Out-of-hospital cardiac arrest survival improving over time: Results from the Resuscitation Outcomes Consortium (ROC). Resuscitation. 2015. June;91:108–115. 10.1016/j.resuscitation.2015.02.003
    1. Mehta C, Brady W. Pulseless electrical activity in cardiac arrest: electrocardiographic presentations and management considerations based on the electrocardiogram. Am J Emerg Med. 2012. January;30(1):236–239. 10.1016/j.ajem.2010.08.017
    1. Jekova I, Mitev P. Detection of ventricular fibrillation and tachycardia from the surface ECG by a set of parameters acquired from four methods. Physiological Measurement. 2002. November;23(4):629–634. 10.1088/0967-3334/23/4/303
    1. Jekova I, Mougeolle F, Valance A. Defibrillation shoc success estimation by a set of six parameters dervied form the electrocardiogram. Physiological Measurement. 2004;25:1179–88. 10.1088/0967-3334/25/5/008
    1. Krasteva V, Jekova I. Assessment of ECG frequency and morphology parameters for automatic classification of life-threatening cardiac arrhythmias. Physiol Meas. 2005. October;26(5):707–723. 10.1088/0967-3334/26/5/011
    1. Minami K, Nakajima H, Toyoshima T. Real-time discrimination of ventricular tachyarrhythmia with Fourier-transform neural network. IEEE Trans Biomed Eng. 1999. February;46(2):179–185. 10.1109/10.740880
    1. Clayton RH, Murray A, Campbell RW. Comparison of four techniques for recognition of ventricular fibrillation from the surface ECG. Medical and Biological Engineering and Computing. 1993. March;31(2):111–7. 10.1007/BF02446668
    1. Cheskes S, Schmicker RH, Christenson J, Salcido DD, Rea T, Powell J, et al. Perishock pause: an independent predictor of survival from out-of-hospital shockable cardiac arrest. Circulation. 2011. July;124(1):58–66. 10.1161/CIRCULATIONAHA.110.010736
    1. Snyder D, Morgan C. Wide variation in cardiopulmonary resuscitation interruption intervals among commercially available automated external defibrillators may affect survival despite high defibrillation efficacy. Crit Care Med. 2004. September;32(9 Suppl):S421–S424. 10.1097/01.CCM.0000134265.35871.2B
    1. Ayala U, Irusta U, Ruiz J, Ruiz de Gauna S, González-Otero D, Alonso E, et al. Fully automatic rhythm analysis during chest compression pauses. Resuscitation. 2015. April;89:25–30. 10.1016/j.resuscitation.2014.11.022

Source: PubMed

스폰서 및 공동 작업자

건강 상태

약물 개입

3
구독하다