Prediction of Gold Standard Gait Data from Inertial Data: A Machine Learning Approach
Resumo
Laboratórios de biomecânica normalmente utilizam câmeras cinemáticas e plataformas de força como padrão-ouro na avaliação da marcha. Contudo, tais sistemas são custosos e têm disponibilidade limitada. Dispositivos vestíveis podem conter sensores, principalmente inerciais, que capturam movimentos permitindo inferir o comportamento humano em uma marcha. Com o objetivo aumentar a qualidade das medições obtidas por vestíveis, este estudo investiga a viabilidade de prever parâmetros cinemáticos a partir de dados inerciais coletados por sensores vestíveis. O estudo utiliza técnicas de aprendizado de máquina, incluindo Random Forest, XGBoost e Gradient Boosting, que correlacionam medições inerciais com dados obtidos por sistemas tradicionais de captura de movimento. A análise de importância de características e SHAP destacou a relevância da velocidade e aceleração na predição dos parâmetros cinemáticos. Os resultados experimentais indicam que modelos baseados em árvores, especialmente Gradient Boosting e XGBoost, apresentaram os melhores desempenhos, com coeficientes de determinação próximos a 0,989, mostrando a viabilidade da abordagem proposta.
Referências
Benson, L., Clermont, C., Bošnjak, E., and Ferber, R. (2018). The use of wearable devices for walking and running gait analysis outside of the lab: A systematic review. Gait and Posture, 63:124–138.
BTS Bioengineering (2024a). BTS G-WALK - Wireless Sensor for Gait Analysis. [link]. Accessed: 2024-08-31.
BTS Bioengineering (2024b). BTS GAITLAB - 3D Motion Analysis System. [link]. Accessed: 2024-08-31.
da Rosa Tavares, J., Ullrich, M., Roth, N., Kluge, F., Eskofier, B., Gaßner, H., Klucken, J., Gladow, T., Marxreiter, F., da Costa, C., da Rosa Righi, R., and Victória Barbosa, J. (2023). utug: An unsupervised timed up and go test for parkinson’s disease. Biomedical Signal Processing and Control, 81:104394.
Delval, A., Betrouni, N., Tard, C., Devos, D., Dujardin, K., Defebvre, L., Labidi, J., and Moreau, C. (2021). Do kinematic gait parameters help to discriminate between fallers and non-fallers with parkinson’s disease? Clinical Neurophysiology, 132(2):536–541.
Desai, R., Martelli, D., Alomar, J., Agrawal, S., Quinn, L., and Bishop, L. (2024). Validity and reliability of inertial measurement units for gait assessment within a post stroke population. Topics in Stroke Rehabilitation, 31(3):235–243. PMID: 37545107.
He, Y., Chen, Y., Tang, L., Chen, J., Tang, J., Yang, X., Su, S., Zhao, C., and Xiao, N. (2024). Accuracy validation of a wearable imu-based gait analysis in healthy female. BMC Sports Science, Medicine and Rehabilitation, 16(1):2.
Jakob, V., Küderle, A., Kluge, F., Klucken, J., Eskofier, B., Winkler, J., Winterholler, M., and Gassner, H. (2021). Validation of a sensor-based gait analysis system with a gold-standard motion capture system in patients with parkinson’s disease. Sensors, 21(22).
Kotiadis, D., Hermens, H., and Veltink, P. (2010). Inertial gait phase detection for control of a drop foot stimulator: Inertial sensing for gait phase detection. Medical Engineering and Physics, 32(4):287–297.
Kvist, A., Tinmark, F., Bezuidenhout, L., Reimeringer, M., Conradsson, D., and Franzén, E. (2024). Validation of algorithms for calculating spatiotemporal gait parameters during continuous turning using lumbar and foot mounted inertial measurement units. Journal of Biomechanics, 162:111907.
Millecamps, A., Lowry, K., Brach, J., Perera, S., Redfern, M., and Sejdić, E. (2015). Understanding the effects of pre-processing on extracted signal features from gait accelerometry signals. Computers in Biology and Medicine, 62:164–174.
Parashar, A., Parashar, A., Ding, W., Shabaz, M., and Rida, I. (2023). Data preprocessing and feature selection techniques in gait recognition: A comparative study of machine learning and deep learning approaches. Pattern Recognition Letters, 172:65–73.
Ripic, Z., Nienhuis, M., Signorile, J., Best, T., Jacobs, K., and Eltoukhy, M. (2023). A comparison of three-dimensional kinematics between markerless and marker-based motion capture in overground gait. Journal of Biomechanics, 159:111793.
Rousanoglou, E., Foskolou, A., Emmanouil, A., and Boudolos, K. (2024). Inertial sensing of the abdominal wall kinematics during diaphragmatic breathing in head standing. Biomechanics, 4(1):63–83.
Silva, L. and Stergiou, N. (2020). Chapter 7 - the basics of gait analysis. In Stergiou, N., editor, Biomechanics and Gait Analysis, pages 225–250. Academic Press.
Tsakanikas, V., Ntanis, A., Rigas, G., Androutsos, C., Boucharas, D., Tachos, N., Skaramagkas, V., Chatzaki, C., Kefalopoulou, Z., Tsiknakis, M., and Fotiadis, D. (2023). Evaluating gait impairment in parkinson’s disease from instrumented insole and imu sensor data. Sensors, 23(8).
Zhang, Y., Wang, M., Awrejcewicz, J., Fekete, G., Ren, F., and Gu, Y. (2017). Using gold-standard gait analysis methods to assess experience effects on lower-limb mechanics during moderate high-heeled jogging and running. Journal of visualized experiments : JoVE, 127:55714.
