Research and development of methods for determining flat valgus foot deformity using a podometric measuring system

The relevance of this study stems from the need to develop methods for processing podometric images characterizing the distribution of patient foot pressure on a sensitive platform. Currently, musculoskeletal disorders are diagnosed manually using foot prints (plantography), whereas podometry provides computer images suitable for automated processing. Despite the obvious advantages of this approach, not all traditional plantographic methods are applicable to podometry, necessitating the development of new ones. This article examines existing methods and develops new ones aimed at identifying flat-valgus foot deformities. An analysis of relevant studies is conducted, identifying the most promising method based on convolutional neural networks, which is compared with the same set of podometric images (dataset). The stages of developing our own methods for comparison with existing ones are described, the limitations of the dataset used are identified, and the application of various machine learning methods to solve the problem is discussed. The best results are demonstrated using a naive Bayes classifier, which achieves an accuracy of 71 %. A conclusion is drawn about the dataset's limitations and ways to improve future results. The materials are of practical value to developers in the field of medical instrumentation, as well as to physicians who use podometric measurement systems in their practice.

1. GBD 2021 Other Musculoskeletal Disorders Collaborators. Global, regional, and national burden of other musculoskeletal disorders, 1990–2020, and projections to 2050: a systematic analysis of the Global Burden of Disease Study 2021. The Lancet Rheumatology. 2023;5(11):e670–e682. https://doi.org/10.1016/S2665-9913(23)00232-1

2. Kalinina M.L., Shekhtman A.G., Zheleznov L.M. Functional methods of research of the foot in modern medical practice. Modern problems of science and education. 2015;(3):203. (In Russ.). URL: https://science-education.ru/en/article/view?id=19966

3. Boyko N.A., Kerimov H.F. Assessment of the foot arch condition in elementary school-aged students with disabilities by plantography. Scientific Notes of P.F. Lesgaft University. 2023;(5):88–92. (In Russ.).

4. Cavanagh P.R., Rodgers M.M. The arch index: a useful measure from footprints. Journal of Biomechanics. 1987;20(5):547–551. https://doi.org/10.1016/0021-9290(87)90255-7

5. Telfer S., Woodburn J. The use of 3D surface scanning for the measurement and assessment of the human foot. Journal of Foot and Ankle Research. 2010;3(1):19. https://doi.org/10.1186/1757-1146-3-19

6. Hofmann U.K., Götze M., Wiesenreiter K., et al. Transfer of plantar pressure from the medial to the central forefoot in patients with hallux valgus. BMC Musculoskeletal Disorders. 2019;20(1):149. https://doi.org/10.1186/s12891-019-2531-2

7. Galica A.M., Hagedorn Th.J., Dufour A.B., et al. Hallux valgus and plantar pressure loading: the Framingham foot study. Journal of Foot and Ankle Research. 2013;6(1):42. https://doi.org/10.1186/1757-1146-6-42

8. Rodríguez-Quiñonez J.C., Ortiz-Villaseñor D., Trujillo-Hernández G., et al. Method and system for the classification of tibial-calcaneal angle using FSR sensors and convolutional neural networks. IET Image Processing. 2025;19(1):e70244. https://doi.org/10.1049/ipr2.70244

9. Tyurin E.A., Lange P.K., Yaroslavkina E.E. System for diagnosing non-uniformity of weight pressure distribution based on strain gauge method. Mathematical Methods in Technologies and Technics. 2025;(12-1):55–59. (In Russ.).

10. Géron A. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. Sebastopol: O'Reilly Media; 2019. 856 p.

11. Booth B.G., Hoefnagels E., Huysmans T., et al. PAPPI: Personalized analysis of plantar pressure images using statistical modelling and parametric mapping. PLoS ONE. 2020;15(2):e0229685. https://doi.org/10.1371/journal.pone.0229685

12. Schwachmeyer V., Kutzner I., Bornschein J., et al. Medial and lateral foot loading and its effect on knee joint loading. Clinical Biomechanics. 2015;30(8):860–866. https://doi.org/10.1016/j.clinbiomech.2015.06.002