Multivariate discriminant analysis of the electrocardiogram

Objectives. The article presents a study of heart rate variability using multivariate discriminant analysis. Representing an effective statistical method of classification, discriminant analysis can be used to divide objects into groups based on differences in the parameters characterizing these objects. The effectiveness of multivariate discriminant analysis, which is actively used in medicine to diagnose cardiovascular pathologies, is due to the wide range of analyzed parameters: statistical, spectral, and autocorrelation. The aim of the work is to identify the parameters of variational pulsometry, which provide the best distinction between healthy patients and patients with arrhythmia, by means of discriminant analysis.

Methods. The durations of cardiac intervals of patients aged 63–72 years, which had been placed in the open database of biomedical signals PhysioNet.org, were used as initial data. When selecting the arguments of the discriminant function, priority was given to parameters that were weakly correlated with each other, had a normal distribution, and differed between healthy and ill patients. The statistical significance of differences between the parameters of the two groups was tested using Student’s t-test and Mann–Whitney U test.

Results. Two discriminant functions were obtained: the first depended on three time-domain parameters, while the second included one spectral and one autocorrelation parameter in addition to time-domain parameters. In both cases, the average values of the discriminant function for healthy and sick patients were calculated. The statistical significance of differences in the average values of the discriminant function in the two groups was investigated using Student’s t-test.

Conclusions. The values of the first discriminant function are shown to differ insignificantly between healthy and sick patients, while the inclusion of autocorrelation and spectral parameters in the number of arguments of the discriminant function provides pronounced and statistically significant differences between patients of the two groups. Thus, the high significance of spectral and autocorrelation parameters in arrhythmia diagnosis was demonstrated.

1. Ermoshkin V.I. The proposed mechanism of arrhythmia human heart. Obrazovatel’nyi vestnik “Soznanie” = Educational Bulletin “Consciousness”. 2013;15(6):4–15 (in Russ.).

2. Getman S.I. Characteristics of Disturbances of Heart Rhythm and Conduction Among Patients Attending Consultation of a Cardiologist at Ambulatory Stage. Kardiologiya. 2018;58(6):20–28 (in Russ.). https://doi.org/10.18087/cardio.2018.6.10130

3. Arzykulov Zh.A., Omarov A.A., Kituev B.B., Tursunova F.A., Eshtai A.A., Pavlova N.G. Innovations in the treatment of cardiac arrhythmia. Vestnik khirurgii Kazakhstana = Bulletin of Surgery in Kazakhstan. 2012;4(32):4–5 (in Russ.).

4. Ziep B.M., Taratukhin E.О. Heart rate variability assessment and its potential. Rossiiskii kardiologicheskii zhurnal = Russian Journal of Cardiology. 2011;6:69–75 (in Russ.).

5. Babunts I.V., Miridzhanyan E.M., Mashaekh Yu.A. Azbuka analiza variabel’nosti serdechnogo ritma (The ABC of Heart Rate Variability Analysis). Stavropol: Print-Master; 2002. 112 p. (in Russ.).

6. Baevskii R.M., Ivanov G.G., Gavrilushkin A.P., et al. Analysis of heart rate variability using various electrocardiographic systems (Part 1). Vestnik aritmologii = Journal of Arrhythmology. 2002;24:65–86 (in Russ.).

7. Bykh A.I., Vysotskaya E.V., Porvan A.P., et al. Using of discriminant analysis for diagnosis chronic cardiac insufficiency on teenagers. Vestnik Natsional’nogo tekhnicheskogo universiteta Khar’kovskii politekhnicheskii institut. Seriya: Informatika i modelirovanie = Bulletin of the National Technical University Kharkov Polytechnic Institute. Series: Informatics and Modeling. 2010;31:16–22 (in Russ.).

8. Silkina U.I., Balandin V.A. Discriminant analysis of variational pulsometry parameters. Rossiiskii tekhnologicheskii zhurnal. 2020;8(3):81–91 (in Russ.). https://doi.org/10.32362/2500-316X-2020-8-3-81-91

9. Novikov A.A., Smolensky A.V., Mikhailova A.V. Approaches to assessing heart rate variability (literature review). Vestnik novykh meditsinskikh tekhnologii. Elektronnoe izdanie = J. New Medical Technologies. 2023;17(3):85–94 (in Russ.). https://doi.org/10.24412/2075-4094-2023-3-3-3

10. Baevsky R.M., Ivanov G.G. Cardiac Rhythm variability: theoretical aspects and opportunities of clinical application. Ul’trazvukovaya i funktsional’naya diagnostika = Ultrasonnd & Functional Diagnostics. 2001;3:108–127 (in Russ.).

11. Alejnikova T.V. Heart rate variability (literature review). Problemy zdorov’ya i ekologii = Health and Ecology Issues. 2012;1:17–23 (in Russ.). https://doi.org/10.51523/2708-6011.2012-9-1-3

12. Besedina S.A., Balandin V.A. Correlation of heart rhythm variability parameters. Nauchnyi dialog: Molodoi uchenyi = Scientific Dialog: Young Scientist. 2017. P. 33–37 (in Russ.). https://doi.org/10.18411/spc-22-11-2017-11

13. Kulikov A.L., Bezdushnii D.I., Osokin V.Yu. Application of linear discriminant analysis for classification of emergency grid emergency states. Vestnik Ivanovskogo gosudarstvennogo energeticheskogo universiteta = Vestnik of Ivanovo State Power Engineering University. 2020;5:38–47 (in Russ.). https://doi.org/10.17588/2072-2672.2020.5.038-047

14. Sukiasyan A.G., Markina V.S., Mitrofanov D.P., Shabalina U.M. Clustering departments of integrated groups of enterprises according to level of risk based on methods of multivariate statistical analysis. Fundamental’nye issledovaniya = Fundamental Research. 2019;5:115–125 (in Russ.).

15. Budko O.N., Senko E.V. Classification functions for express diagnostics of the degree of disease with arterial hypertension. In: BIG DATA Advanced Analytics: Collection of Materials of the Fourth International Scientific and Practical Conference. 2018. P. 360–365 (in Russ.). Available from URL: https://elib.grsu.by/doc/48339

16. Pavlenkov M.N., Smirnova N.A. Development of technology for the assessment of stability of an enterprise of the chemical complex. Statistika i Ekonomika = Statistics and Economics. 2013;3:66–69 (in Russ.).

17. Sizykh D.S., Sizykh N.V. Features of teaching methods of discriminant analysis for training specialists in the direction of “Business Informatics”. In: Isaev Y.N., Pavlov I.V. (Eds). Obrazovanie: opyt i perspektivy razvitiya (Education: Experience and Development Prospects). Cheboksary: Sreda; 2019. P. 107–133 (in Russ.). https://doi.org/10.31483/r-33128