Polina A. Kiseleva

Polina A. Kiseleva

Auto-generated profile, based on publicly available information

Polina A. Kiseleva

Ryazan State Medical University

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 March 2026 in Nauka Molodykh (Eruditio Juvenium)
Verified
Journal Article
Closed access
ACAleksandr A. Chekushin
Aleksandr A. Chekushin
AFAndrey V. Fedoseev
Andrey V. Fedoseev
AKAnna V. Kulakova
Anna V. Kulakova
PKPolina A. Kiseleva
Polina A. Kiseleva
AAAlexey V. Alpatov
Alexey V. Alpatov
PFPavel S. Filonenko
Pavel S. Filonenko
BACKGROUND: In recent years, alternative methods based on video recording and machine learning (ML) have been actively developed. These methods allow for objective assessment of movement parameters using a single device, significantly reducing time and cost. However, for the differential diagnosis of normal and pathological conditions, clinical validation of such approaches is required. AIM: To demonstrate the potentials of the developed gait video analysis program based on the MediaPipe Pose platform for quantitative assessment and comparison of spatiotemporal gait parameters in a healthy volunteer and a female patient with osteoarthritis (OA) of the knee joints. METHODS: The study was conducted on a stand (a treadmill, a GoPro 4K/60fps camera). The program based on MediaPipe Pose identified 33 key body points with calculation of knee joint angles, step timing characteristics, symmetry coefficients, and variability. Two clinical cases are presented. CONCLUSION: A video analysis program based on MediaPipe Pose allows for quantitative differentiation between pathological and normal walking pattern. Changes identified in a patient with gonarthrosis are consistent with the clinical picture and can serve as objective markers of disorders. The method holds promise for clinical application as an accessible screening tool. Further work to improve the program will focus on studying flexion angles in the lower extremity joints relative to gait events, examining their interrelationships to obtain more accurate results.

30 June 2026 in I.P. Pavlov Russian Medical Biological Herald
Verified
Journal Article
Open access
ACAleksandr A. Chekushin
Aleksandr A. Chekushin
AFAndrey V. Fedoseev
Andrey V. Fedoseev
AKAnna V. Kulakova
Anna V. Kulakova
PKPolina A. Kiseleva
Polina A. Kiseleva
AAAlexey V. Alpatov
Alexey V. Alpatov
MAMaria S. Ashapkina
Maria S. Ashapkina
BACKGROUND: Human gait is of scientific and practical interest in medical knowledge system, since standardized gait parameters can help assess the results of conservative or surgical treatment in various categories of patients. Digital study methods allow for an objective assessment of the lower limb functions in locomotion. AIM: To conduct a comparative analysis of digital gait assessment methods in terms of their advantages, limitations and scope of application. This article systematizes the main digital methods for studying gait, provides their original classification, examples of ready-made solutions available on the market, and identifies key trends in gait study. It demonstrates that the 'gold standard' for studying gait is the use of optical systems. The method gaining popularity among researchers, is the use of inertial sensors based on microelectromechanical systems, but it often requires validation. Pedobarography is a valuable tool for identifying key step events and load distribution during walking. Electromyography, electrogoniometry, and electroencephalography are auxiliary methods. A relevant area of research is machine learning technologies facilitating work with large amounts of data obtained in research. CONCLUSION: Digital gait analysis methods are a diverse group comprising various technologies, the leading ones being optical systems and inertial sensors based on microelectromechanical systems. Promising direction of research are methods of gadget minimization and machine learning.