A new machine-learning algorithm for assessing the left ventricular diastolic dysfunction by a single-channel ECG monitor

Kuznetsova N.O.

Sechenov First Moscow State Medical University

Sagirova Zh.N.

Sechenov First Moscow State Medical University

Gubina A.Yu.

Sechenov First Moscow State Medical University

Zakharov I.P.

Sechenov First Moscow State Medical University

Fashafsha Z-Z.A.

Sechenov First Moscow State Medical University

Syrkina E.A.

The first Moscow State Medical University named after I.M. Sechenov (Sechenov University)

Chomakhidze P.Sh.

Sechenov First Moscow State Medical University

SPIN RSCI: 6230-5610
Scopus AuthorID: 56037717000
ORCID: 0000-0003-1485-6072

Kopylov F.Yu.

Sechenov First Moscow State Medical University

Scopus AuthorID: 6507736224
ORCID: 0000-0001-5124-6383

A new machine-learning algorithm for assessing the left ventricular diastolic dysfunction by a single-channel ECG monitor

Authors:

Kuznetsova N.O., Sagirova Zh.N., Gubina A.Yu., Zakharov I.P., Fashafsha Z-Z.A., Syrkina E.A., Chomakhidze P.Sh., Kopylov F.Yu.

More about the authors

Journal: Russian Journal of Cardiology and Cardiovascular Surgery. 2022;15(5): 496‑500

DOI: 10.17116/kardio202215051496

Downloaded: 177

Download PDF (RU)

Contact the author

Table of contents

To cite this article:

Kuznetsova NO, Sagirova ZhN, Gubina AYu, et al. . A new machine-learning algorithm for assessing the left ventricular diastolic dysfunction by a single-channel ECG monitor. Russian Journal of Cardiology and Cardiovascular Surgery. 2022;15(5):496‑500. (In Russ.)
https://doi.org/10.17116/kardio202215051496

Close metadata

OBJECTIVE

Analysis of a new algorithm based on machine learning elements to determine significant (grade 2 or 3) left ventricular diastolic dysfunction using a single-channel electrocardiography (ECG).

MATERIAL AND METHODS

The study prospectively included 200 patients over 18 years old. Each one underwent transthoracic echocardiography with analysis of left ventricular diastolic dysfunction by high-speed and tissue Doppler ultrasound. ECG was recorded using a single-channel monitor. After spectral analysis of ECG, we calculated the time, amplitude and frequency parameters. The modernized algorithm for determining significant left ventricular diastolic dysfunction was evaluated considering the results obtained on the training sample of patients.

RESULTS

Mean age of patients was 53.2±18.1 years. Moderate-to-severe left ventricular diastolic dysfunction was found in 31% of patients. Sensitivity and specificity of the algorithm in determining moderate left ventricular diastolic dysfunction were 98.3% and 97.8%, severe dysfunction — 87.5% and 99.5%, moderate-to-severe diastolic dysfunction — 95.6% and 97.7%, respectively. Diagnostic accuracy was 97.5%, 99.0% and 96.5%, respectively.

CONCLUSION

The achieved results substantiate fundamental possibility of remote screening of left ventricular diastolic dysfunction based on ECG parameters.

Keywords:

diastolic function

portable ECG monitor

electrocardiogram

echocardiography

heart failure

machine learning

Authors:

Kuznetsova N.O.

Sechenov First Moscow State Medical University

Sagirova Zh.N.

Sechenov First Moscow State Medical University

Gubina A.Yu.

Sechenov First Moscow State Medical University

Zakharov I.P.

Sechenov First Moscow State Medical University

Fashafsha Z-Z.A.

Sechenov First Moscow State Medical University

Syrkina E.A.

The first Moscow State Medical University named after I.M. Sechenov (Sechenov University)

Chomakhidze P.Sh.

Sechenov First Moscow State Medical University

SPIN RSCI: 6230-5610
Scopus AuthorID: 56037717000
ORCID: 0000-0003-1485-6072

Kopylov F.Yu.

Sechenov First Moscow State Medical University

Scopus AuthorID: 6507736224
ORCID: 0000-0001-5124-6383

Received:

10.03.2022

Accepted:

22.04.2022

List of references:

Luthra A. Echo made easy. Translated by Vasyuk YuA, 3rd edition. M.: Practical Medicine; 2017:60-61. (In Russ.).
Clinical guidelines “Chronic heart failure” of the Ministry of Health of the Russian Federation 2016. (In Russ.).
Fomin IV. Chronic Heart Failure In Russian Federation: What Do We Know And What To Do. Russian Journal of Cardiology. 2016;8:7-13. (In Russ.). https://doi.org/10.15829/1560-4 071-2016-8-7-13
McDonagh TA, Metra M, Adamo M, et al. 2021 ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure. European Heart Journal. 2021;42(36):3599-3726. Published: 27 August 2021. https://doi.org/10.1093/eurheartj/ehab368
Vinogradova NG. City Center for the Treatment of Chronic Heart Failure: organization of work and effectiveness of treatment of chronic heart failure. Kardiologiya. 2019;59(2S):31-39. (In Russ.). https://doi.org/10.18087/cardio.2621
Tsai W-Ch, Lee K-T, Wu M-T, et al. Significant Correlation of P-Wave Parameters With Left Atrial Volume Index and Left Ventricular Diastolic Function. The American Journal of the Medical Sciences. 2013;346(1):45-51.
Çanga A, Kocaman SA, Durakoğlugil ME, et al. Relationship between fragmented QRS complexes and left ventricular systolic and diastolic functions. Herz. 2013;38(6):665-670.
Kang JG, Chang Y, Sung K-Ch, et al. Association of isolated minor nonspecific ST-T abnormalities with left ventricular hypertrophy and diastolic dysfunction. Sci Rep. 2018;8(1):8791. https://doi.org/10.1038/s41598-018-27028-61-7
Sauer A, Wilcox JE, Andrei A-C, et al. Diastolic Electromechanical Coupling: Association of the ECG T-Peak to T-End Interval With Echocardiographic Markers of Diastolic Dysfunction. Circulation: Arrhythmia and Electrophysiology. 2012;5(3):537-543. https://doi.org/10.1161/circep.111.969717
Attia ZI, Kapa S, Lopez-Jimenez F, et al. Screening for cardiac contractile dysfunction using an artificial intelligence — enabled electrocardiogram. Nature Medicine. 2019;25(1):70-74. https://doi.org/10.1038/s41591-018-0240-2
Sengupta PP, Kulkarni H, Narula J. Prediction of Abnormal Myocardial Relaxation From Signal Processed Surface ECG. Journal of the American College of Cardiology. 2018;71(15):1650-1660. https://doi.org/10.1016/j.jacc.2018.02.024
Kagiyama N, Piccirilli M, Yanamala N, et al. Machine Learning Assessment of Left Ventricular Diastolic Function Based on Electrocardiographic Features. Journal of the American College of Cardiology. 2020;76(8):930-941. https://doi.org/10.1016/j.jacc.2020.06.061
Bax JJ, Van der Bijl P, Delgado V. Machine Learning for Electrocardiographic Diagnosis of Left Ventricular Early Diastolic Dysfunction. Journal of the American College of Cardiology. 2018; 71(15):1661-1662. https://doi.org/10.1016/j.jacc.2018.02.041
Sherif FN, Otto AS, et al. Recommendations for the Evaluation of Left Ventricular Diastolic Function by Echocardiography: An Update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging. Journal of the American Society of Echocardiography. 2016;29:277-314.
Berliner D, Hänselmann A, Dtsch A. The Treatment of Heart Failure with Reduced Ejection Fraction. Int. 2020;117(21):376-386. https://doi.org/10.3238/arztebl.2020.0376
Tomasoni D, Adamo M, Lombardi CM, Metra M. Highlights in heart failure ESC. Heart Fail. 2019;6(6):1105-1127.
Tamer T, Sayed Kh, Saad M, et al. How accurate can electrocardiogram predict left ventricular diastolic dysfunction? The Egyptian Heart Journal (EHJ): official bulletin of the Egyptian Society of Cardiology. 2016;68:117-123.
Boles U, Almuntaser I, Brown A, et al. Ventricular Activation Time as a Marker for Diastolic Dysfunction in Early Hypertension. American Journal of Hypertension. 2010;23(7):781-785.
Onoue Y, Izumiya Y, Hanatani Sh, et al. Fragmented QRS complex is a diagnostic tool in patients with left ventricular diastolic dysfunction. Heart and Vessels. 2016;31(4):563-567. https://doi.org/10.1007/s00380-015-0651-7
Gunduz H, Binak E, Arinc H, et al. The Relationship between P Wave Dispersion and Diastolic Dysfunction. Texas Heart Institute Journal. 2005;32(2):163-167.

Close metadata