Using Machine Learning Algorithms to Determine the Post-COVID State of a Person by Their Rhythmogram

Sergey V Stasenko; Andrey V Kovalchuk; Evgeny V Eremin; Olga V Drugova; Natalya V Zarechnova; Maria M Tsirkova; Sergey A Permyakov; Sergey B Parin; Sofia A Polevaya

doi:10.3390/s23115272

Using Machine Learning Algorithms to Determine the Post-COVID State of a Person by Their Rhythmogram

Sensors (Basel). 2023 Jun 1;23(11):5272. doi: 10.3390/s23115272.

Authors

Sergey V Stasenko¹, Andrey V Kovalchuk², Evgeny V Eremin³, Olga V Drugova⁴, Natalya V Zarechnova⁵, Maria M Tsirkova⁶, Sergey A Permyakov³, Sergey B Parin³, Sofia A Polevaya³

Affiliations

¹ Neurotechnology Department, Institute of Biology and Biomedicine, Lobachevsky State University of Nizhny Novgorod, 603022 Nizhny Novgorod, Russia.
² Laboratory of Autowave Processes, Institute of Applied Physics, Russian Academy of Sciences, 603950 Nizhny Novgorod, Russia.
³ Faculty of Social Sciences, Lobachevsky State University of Nizhny Novgorod, 603022 Nizhny Novgorod, Russia.
⁴ Department of Medical Biophysics, Privolzhsky Research Medical University, 603005 Nizhny Novgorod, Russia.
⁵ GBUZ NO "Nizhny Novgorod Regional Clinical Oncological Dispensary", 603126 Nizhny Novgorod, Russia.
⁶ Clinical Hospital No. 2, Privolzhsky District Medical Center, 603032 Nizhny Novgorod, Russia.

Abstract

This study introduces a novel method for detecting the post-COVID state using ECG data. By leveraging a convolutional neural network, we identify "cardiospikes" present in the ECG data of individuals who have experienced a COVID-19 infection. With a test sample, we achieve an 87 percent accuracy in detecting these cardiospikes. Importantly, our research demonstrates that these observed cardiospikes are not artifacts of hardware-software signal distortions, but rather possess an inherent nature, indicating their potential as markers for COVID-specific modes of heart rhythm regulation. Additionally, we conduct blood parameter measurements on recovered COVID-19 patients and construct corresponding profiles. These findings contribute to the field of remote screening using mobile devices and heart rate telemetry for diagnosing and monitoring COVID-19.

Keywords: COVID-19; data analysis; electrocardiogram; machine learning algorithms; post-COVID state.

MeSH terms

Algorithms
COVID-19* / diagnosis
Electrocardiography*
Humans
Machine Learning
Neural Networks, Computer

Abstract

MeSH terms

Grants and funding