UDC

612.17:612.81

DOI

https://doi.org/10.37482/2687-1491-Z064

Authors

Dmitriy A. Dimitriev* ORCID: https://orcid.org/0000-0002-8102-7074
Elena V. Saperova* ORCID: https://orcid.org/0000-0001-5335-3238
Aleksey D. Dimitriev** ORCID: https://orcid.org/0000-0002-3793-2894
El’dar R. Salimov* ORCID: https://orcid.org/0000-0002-8291-2171
*Chuvash I. Yakovlev State Pedagogical University (Cheboksary, Chuvash Republic, Russian Federation)
**Cheboksary Cooperative Institute of the Russian University of Cooperation (Cheboksary, Chuvash Republic, Russian Federation)
Corresponding author: Elena Saperova, address: ul. K. Marksa 38, Cheboksary, 428000, Chuvashskaya Respublika, Russian Federation; e-mail: saperova_elena@mail.ru

Abstract

This paper presents a stress detection algorithm using heart rate variability (HRV) parameters. Five-minute electrocardiograms were recorded at rest and under exam stress (252 students were involved). The determined HRV parameters were applied to detect stress by means of several classification algorithms. We analysed linear indices in the time (standard deviation of NN intervals (SDNN) and root mean square of successive RR interval differences (RMSSD)) and frequency domains (low frequency (LF) and high frequency (HF) power as well as LF/HF ratio). To study nonlinear HRV indices, we evaluated approximate entropy (ApEn), sample entropy (SampEn), α1 (DFA1) and α2 (DFA2) scaling exponents, correlation dimension D2, and recurrence plot quantification measures (recurrence rate (REC), mean diagonal line length (L_mean), maximum diagonal line length (L_max), determinism (DET), and Shannon entropy (ShanEn)). Receiver operating characteristic (ROC) was used to test the performance of the classifiers derived from HRV. The highest area under the ROC curve (AUC), sensitivity, and specificity were found for mean RR-interval, DFA1, DFA2, RMSSD, and L_max. These parameters were used for stress/rest classification with the help of algorithms that are common in clinical and physiological applications, i.e. logistic regression (LR) and linear discriminant analysis (LDA). Classification performance for stress was quantified using accuracy, sensitivity and specificity measures. The LR achieved an accuracy of 68.25 % at an optimal cutoff value of 0.57. LDA determined stress with 67.46 % accuracy. Thus, HRV parameters can serve as an objective tool for stress detection.
For citation: Dimitriev D.A., Saperova E.V., Dimitriev A.D., Salimov E.R. The Use of Nonlinear Parameters of Heart Rate Variability for Stress Detection. Journal of Medical and Biological Research, 2021, vol. 9, no. 3, pp. 265–274. DOI: 10.37482/2687-1491-Z064

Keywords

heart rate variability, stress diagnosis, logistic regression, linear discriminant analysis

References

1. Valenza G., Sclocco R., Duggento A., Passamonti L., Napadow V., Barbieri R., Toschi N. The Central Autonomic Network at Rest: Uncovering Functional MRI Correlates of Time-Varying Autonomic Outflow. Neuroimage, 2019, vol. 197, pp. 383–390. DOI: 10.1016/j.neuroimage.2019.04.075
2. Odinak M.M., Shustov E.B., Kolomentsev S.V. Metodologiya instrumental’nogo izucheniya vegetativnoy nervnoy sistemy v norme i patologii [Methodology of the Instrumental Study of the Autonomic Nervous System in Norm and Pathology]. Vestnik Rossiyskoy voenno-meditsinskoy akademii, 2012, no. 2, pp. 145–152.
3. Hughes B.M., Lü W., Howard S. Cardiovascular Stress-Response Adaptation: Conceptual Basis, Empirical Findings, and Implications for Disease Processes. Int. J. Psychophysiol., 2018, vol. 131, pp. 4–12. DOI: 10.1016/j.ijpsycho.2018.02.003
4. Smith R., Thayer J.F., Khalsa S.S., Lane R.D. The Hierarchical Basis of Neurovisceral Integration. Neurosci.Biobehav. Rev., 2017, vol. 75, pp. 274–296. DOI: 10.1016/j.neubiorev.2017.02.003
5. Mironova T.F., Mironov V.A., Obukhova T.Yu., Shmonina O.G., Mordas E.Yu., Kudrina K.S., Milovankina N.O., Milashchenko A.I. Vegetativnaya regulyatsiya serdechnogo ritma (obzor) [Autonomic Regulation of Heart Rhythm (Review)]. Ural’skiy meditsinskiy zhurnal, 2018, no. 10, pp. 90–105. DOI: 10.25694/URMJ.2018.10.28
6. Silva L.E.V., Lataro R.M., Castania J.A., Silva C.A.A., Salgado H.C., Fazan R. Jr., Porta A. Nonlinearities of Heart Rate Variability in Animal Models of Impaired Cardiac Control: Contribution of Different Time Scales. J. Appl. Physiol. (1985), 2017, vol. 123, no. 2, pp. 344–351. DOI: 10.1152/japplphysiol.00059.2017
7. Silva L.E.V., Lataro R.M., Castania J.A., da Silva C.A.A., Valencia J.F., Murta L.O. Jr., Salgado H.C., Fazan R. Jr., Porta A. Multiscale Entropy Analysis of Heart Rate Variability in Heart Failure, Hypertensive, and Sinoaortic-Denervated Rats: Classical and Refined Approaches. Am. J. Physiol. Regul. Integr. Comp. Physiol., 2016, vol. 311, no. 1, pp. 150–156. DOI: 10.1152/ajpregu.00076.2016
8. Pincus S.M. Approximate Entropy as a Measure of System Complexity. Proc. Natl. Acad. Sci. USA, 1991, vol. 88, no. 6, pp. 2297–2301. DOI: 10.1073/pnas.88.6.2297
9. Richman J.S., Moorman J.R. Physiological Time-Series Analysis Using Approximate Entropy and Sample Entropy. Am. J. Physiol. Heart Circ. Physiol., 2000, vol. 278, no. 6, pp. H2039–H2049. DOI: 10.1152/ajpheart.2000.278.6.H2039
10. Costa M.D., Goldberger A.L. Generalized Multiscale Entropy Analysis: Application to Quantifying the Complex Volatility of Human Heartbeat Time Series. Entropy (Basel), 2015, vol. 17, no. 3, pp. 1197–1203. DOI: 10.3390/e17031197
11. Brindle R.C., Ginty A.T., Phillips A.C., Fisher J.P., McIntyre D., Carroll D. Heart Rate Complexity: A Novel Approach to Assessing Cardiac Stress Reactivity. Psychophysiology, 2016, vol. 53, no. 4, pp. 465–472. DOI: 10.1111/psyp.12576
12. Pham T.D. Fuzzy Recurrence Plots. Fuzzy Recurrence Plots and Networks with Applications in Biomedicine. Cham, 2020, pp. 29–55.
13. Iwaniec J., Iwaniec M. Application of Recurrence-Based Methods to Heart Work Analysis. Timofiejczuk A., Łazarz B., Chaari F., Burdzik R. (eds.). International Congress on Technical Diagnostic. Cham, 2016, pp. 343–352. DOI: 10.1007/978-3-319-62042-8_31
14. Kitlas Golińska A. Detrended Fluctuation Analysis (DFA) in Biomedical Signal Processing: Selected Examples. Stud. Logic Gramm. Rhetor., 2012, vol. 29, pp. 107–115.
15. Uçar M.K., Bozkurt M.R., Bilgin C., Polat K. Automatic Sleep Staging in Obstructive Sleep Apnea Patients Using Photoplethysmography, Heart Rate Variability Signal and Machine Learning Techniques. Neural Comput. Appl., 2018, vol. 29, no. 8, pp. 1–16. DOI: 10.1007/s00521-016-2365-x
16. Melillo P., Bracale M., Pecchia L. Nonlinear Heart Rate Variability Features for Real-Life Stress Detection. Case Study: Students Under Stress Due to University Examination. Biomed. Eng. Online, 2011, vol. 10, no. 1. Art. no. 96. DOI: 10.1186/1475-925X-10-96
17. Notova S.V., Davydova N.O., Cheremushnikova I.I. Kompleksnyy podkhod k opredeleniyu urovnya adaptatsii k usloviyam universiteta u studentov raznykh sotsial’nykh grupp [A Comprehensive Approach to Determination of Adaptation Level in University Students of Different Social Groups]. Vestnik Severnogo (Arkticheskogo) federal’nogo universiteta. Ser.: Mediko-biologicheskie nauki, 2014, no. 2, pp. 56–62.
18. Gevorkyan E.S., Dayan A.V., Adamyan Ts.I., Grigoryan S.S., Minasyan S.M. Influence of Examination Stress on Psychophysiological Characteristics and Heart Rate in Students. Zhurnal vysshey nervnoy deyatel’nosti im. I.P. Pavlova, 2003, vol. 53, no. 1, pp. 46–50.
19. Mulcahy J.S., Larsson D.E.O., Garfinkel S.N., Critchley H.D. Heart Rate Variability as a Biomarker in Health and Affective Disorders: A Perspective on Neuroimaging Studies. Neuroimage, 2019, vol. 202. Art. no. 116072. DOI: 10.1016/j.neuroimage.2019.116072
20. Silva L.E.V., Silva C.A.A., Salgado H.C., Fazan R. Jr. The Role of Sympathetic and Vagal Cardiac Control on Complexity of Heart Rate Dynamics. Am. J. Physiol. Heart Circ. Physiol., 2017, vol. 312, pp. H469–H477. DOI: 10.1152/ajpheart.00507.2016
21. Muaremi A., Arnrich B., Tröster G. Towards Measuring Stress with Smartphones and Wearable Devices During Workday and Sleep. BioNanoScience, 2013, vol. 3, pp. 172–183. DOI: 10.1007/s12668-013-0089-2
22. Sun G., Shinba T., Kirimoto T., Matsui T. An Objective Screening Method for Major Depressive Disorder Using Logistic Regression Analysis of Heart Rate Variability Data Obtained in a Mental Task Paradigm. Front. Psychiatry, 2016, vol. 7. Art. no. 180. DOI: 10.3389/fpsyt.2016.00180