Internet 
Українська  English  Русский  

DOI: https://doi.org/10.31071/kit2019.15.0


Inventory reference ISSN 1812-7231 Klin.inform.telemed. Volume 14, Issue 15, 2019, Pages 53-57


Author(s) M. G. Boreiko


Institution(s)

V. M. Glushkov Institute of Cybernetics, NAS of Ukraine, Kyiv


Article title Development of advanced method for heart ventricular fibrillation detection


Abstract (resume)

Introduction. The article deals with modern algorithms for detecting ventricular fibrillation such as TCI, VF, SPEC, CPLX, HILB. The best sensitivity among them is the HILB algorithm, based on the construction of phase-space plot using the Hilbert transform.

Results. It was founded opportunities to improve the specificity of the HILB algorithm by introducing additional features of the phase-space plot, such as the center of mass and the standard deviation of points. The software for analyzing the one lead ECG signal was developed. The software implements preliminary filtration of the signal and the proposed method for detecting ventricular fibrillation.

Validation of the method was performed based on well-known open databases such as MIT-BIH Arrhythmia Database, American Heart Association Database (AHA), Creighton University Ventricular Tachyarrhythmia Database (CU). Sensitivity obtained for CU database is 83% and positive predictive value is 93%, for MIT-BIH — 100% and 100%, for AHA — 90% and 98%, respectively.

Comparison of results with TCI, VF, SPEC, CPLX and HILB algorithms was performed. Sensitivity and positive predictive value of the proposed method are better than known algorithms.


Keywords Electrocardiogram, Ventricular fibrillation, Hilbert transform, Aautomatic ECG analysis, MIT-BIH database


References

1. Cardiovascular diseases (CVDs). WHO, 2017. Available: http://www.who.int/mediacentre/factsheets/fs317/en/index.htm

2. Boreiko M., Budnyk M. Development of software and hardware system for monitoring the physiological condition of yachtsmen. Vcheni zapysky Tavriys'koho nats. un-tu im. V. I. Vernads'koho. Seriya: Tekhnichni nauky [Notes of the V. I. Vernadsky Taurida Nat. Univ., Series: Technical Sciences], 2018, vol. 29 (68), no. 3, Part 1, pp. 101-104. (In Ukr.).

3. Boreyko M., Сhaikovsky I. Evaluation of pain syndrome based on analysis of heart rhythm variability. Abstracts of the 4th All-Ukrain. Sci.-practical Conf. "Joint actions of military formations and law-enforcement bodies of the state: problems and prospects", 7–8.09.2017. Military Academy. Odessa. pp. 216–217. (In Ukr.).

4. Biletsky I., Chaikovsky I. Determination of respiratory rate on the basis of ECG and study of its connection with the degree of post-traumatic stress disorder in military personnel. Abstracts of the 4th All-Ukrain. Sci.-practical Conf. "Joint actions of military formations and law-enforcement bodies of the state: problems and prospects", 7–8.09.2017. Military Academy. Odessa. pp. 215–216. (In Ukr.).

5. Weaver W. D., Cobb L., Hallstrom A., Copass M., Ray R., Emery M. et al. Considerations for improving survival from out-of-hospital cardiac arrest. Ann. Emerg. Med., 1986, iss. 15, pp. 1181–1186.
https://doi.org/10.1016/S0196-0644(86)80862-9

6. Goldberger A., Amaral L., Glass L., Hausdorff J., Ivanov P., Mark R. et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation, 2000, iss. 101, pp. E215–20.
https://doi.org/10.1161/01.CIR.101.23.e215

7. Amann A., Tratnig R., Unterkofler K. Reliability of old and new ventricular fibrillation detection algorithms for automated external defibrillators. Biomed Eng. Online., 2005, iss. 4, p. 60.
https://doi.org/10.1186/1475-925X-4-60
PMid:16253134 PMCid:PMC1283146

8. Amann A., Tratnig R., Unterkofler K. A new ventricular fibrillation detection algorithm for automated external defibrillators. Computers in Cardiology, 2005, pp. 559–562.
https://doi.org/10.1109/CIC.2005.1588162

9. Amann A., Tratnig R., Unterkofler K. Detection of ventricular fibrillation by time-delay methods. IEEE Trans Biomed Eng., 2007, iss. 54, pp. 174–177.
https://doi.org/10.1109/TBME.2006.880909
PMid:17260872

10. Ismail A., Fries M. Validating the Reliability of Five Ventricular Fibrillation Detecting Algorithms. Springer, Brlin Heidelberg, 2009, pp. 26–29.
https://doi.org/10.1007/978-3-540-89208-3_8

11. Anas E., Lee S., Hasan M. Sequential algorithm for life threatening cardiac pathologies detection based on mean signal strength and EMD functions. Biomed. Eng. Online, 2010, no. 9, p. 43.
https://doi.org/10.1186/1475-925X-9-43
PMid:20815909 PMCid:PMC2944264

12. Arafat M., Chowdhury A., Hasan M. A simple time domain algorithm for the detection of ventricular fibrillation in an electrocardiogram. J. VLSI Signal Process. Syst. Signal Image Video Technol., 2011, iss. 5, pp. 1–10.
https://doi.org/10.1007/s11760-009-0136-1

13. Thakor N., Zhu Y., Pan K. Ventricular tachycardia and fibrillation detection by a sequential hypothesis testing algorithm. IEEE Trans Biomed Eng., 1990, vol. 37, pp. 837–843.
https://doi.org/10.1109/10.58594
PMid:2227970

14. Kuo S. Computer detection of ventricular fibrillation. Proc of Computers in Cardiology, IEEE Comupter Society, 1978, pp. 347–349.

15. Hilbert Transform. In: Wikipedia [Internet]. [cited 23 Jun 2019]. URL: https://en.wikipedia.org/wiki/Hilbert_transform

16. IEC 60601-2-47:2012. Medical electrical equipment — Part 2–47: Particular requirements for the basic safety and essential performance of ambulatory electrocardiographic systems. In: Webstore IEC [Internet]. [cited 23 Jun 2019]. URL: https://webstore.iec.ch/publication/2666

17. Cardiolyse. In Cardiolyse [Internet]. [cited 23 Jun 2019]. URL: https://cardiolyse.com


Full-text version http://kit-journal.com.ua/en/viewer_en.html?doc/2019_15/004.pdf