Predição de Congelamento de Marcha por Meio da Detecção de Eventos de Pré-Congelamento

• João Pedro A. Amoedo UFAM
• Paulo H. N. Gonçalves UFAM
• Rafael Albuquerque UFAM
• Eulanda M. dos Santos UFAM
• Rafael Giusti UFAM
• Renato C. F. Junior UFAM

DOI: https://doi.org/10.5753/sbcas.2023.229854

Abstract

Freezing of gait (FOG) is a debilitating symptom commonly observed in patients with Parkinson’s disease. Using data usually captured by inertial sensors, the automatic prediction of FOG may help to improve patients’ quality of life—e.g., by preventing falls. Among the strategies applied to predict FOG, machine learning methods are used to solve a classification problem involving three classes: FOG, Non-FOG and Pre-FOG. The Pre-FOG class refers to time series segments immediately preceding the occurrence of a FOG event. It is expected that Pre-FOG instances present unique features that allow identifying signs of an impending FOG episode. However, the Pre-FOG class is neither well defined nor well characterized in the literature due to its transitional nature. In this paper we analyze the behavior of the Pre-FOG class using two machine learning models, SVM and the combination of CNN with LSTM, on data collected from accelerometers and gyroscopes. The results show that the Pre-FOG class can be detected, although with low recognition rates, which indicates the lack of well-defined patterns to discriminate this class from the two remaining classes.

References

Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P. (2002). Smote: Synthetic minority over-sampling technique. Journal of artificial intelligence research, 16:321–357.

Filtjens, B., Ginis, P., Nieuwboer, A., Afzal, M. R., Spildooren, J., Vanrumste, B., and Slaets, P. (2021). Modelling and identification of characteristic kinematic features preceding freezing of gait with convolutional neural networks and layer-wise relevance propagation. BMC medical informatics and decision making, 21(1):1–11.

Hu, K., Wang, Z., Wang, W., Martens, K. A. E., Wang, L., Tan, T., Lewis, S. J., and Feng, D. D. (2019). Graph sequence recurrent neural network for vision-based freezing of gait detection. IEEE Transactions on Image Processing, 29:1890–1901.

Li, B., Yao, Z., Wang, J., Wang, S., Yang, X., and Sun, Y. (2020). Improved deep learning technique to detect freezing of gait in parkinson’s disease based on wearable sensors. Electronics, 9(11):1919.

Mazilu, S., Calatroni, A., Gazit, E., Mirelman, A., Hausdorff, J. M., and Tröster, G. (2015). Prediction of freezing of gait in parkinson’s from physiological wearables: an exploratory study. IEEE journal of biomedical and health informatics, 19(6):1843–1854.

Mazilu, S., Calatroni, A., Gazit, E., Roggen, D., Hausdorff, J. M., and Tröster, G. (2013). Feature learning for detection and prediction of freezing of gait in parkinson’s disease. In Machine Learning and Data Mining in Pattern Recognition: 9th International Conference, MLDM 2013, New York, NY, USA, July 19-25, 2013. Proceedings 9, pages 144–158. Springer.

Naghavi, N., Miller, A., and Wade, E. (2019). Towards real-time prediction of freezing of gait in patients with parkinson’s disease: addressing the class imbalance problem. Sensors, 19(18):3898.

Ordóñez, F. J. and Roggen, D. (2016). Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition. Sensors, 16(1).

Pardoel, S., Kofman, J., Nantel, J., and Lemaire, E. D. (2019). Wearable-sensor-based detection and prediction of freezing of gait in parkinson’s disease: a review. Sensors, 19(23):5141.

Pardoel, S., Nantel, J., Kofman, J., and Lemaire, E. D. (2022). Prediction of freezing of gait in parkinson’s disease using unilateral and bilateral plantar-pressure data. Frontiers in Neurology, 13.

Pardoel, S., Shalin, G., Nantel, J., Lemaire, E. D., and Kofman, J. (2021). Early detection of freezing of gait during walking using inertial measurement unit and plantar pressure distribution data. Sensors, 21(6):2246.

Polat, K. (2019). Freezing of gait (fog) detection using logistic regression in parkinson’s disease from acceleration signals. In 2019 Scientific Meeting on Electrical-Electronics & Biomedical Engineering and Computer Science (EBBT), pages 1–4. Ieee.

Reches, T., Dagan, M., Herman, T., Gazit, E., Gouskova, N. A., Giladi, N., Manor, B., and Hausdorff, J. M. (2020). Using wearable sensors and machine learning to automatically detect freezing of gait during a fog-provoking test. Sensors, 20(16):4474.

Rezvanian, S. and Lockhart, T. E. (2016). Towards real-time detection of freezing of gait using wavelet transform on wireless accelerometer data. Sensors, 16(4):475.

Ribeiro De Souza, C., Miao, R., Ávila De Oliveira, J., Cristina De Lima-Pardini, A., Fragoso De Campos, D., Silva-Batista, C., Teixeira, L., Shokur, S., Mohamed, B., and Coelho, D. B. (2022). A public data set of videos, inertial measurement unit, and clinical scales of freezing of gait in individuals with parkinson’s disease during a turning-in-place task. Frontiers in Neuroscience, 16:832463.

Shalin, G., Pardoel, S., Lemaire, E. D., Nantel, J., and Kofman, J. (2021). Prediction and detection of freezing of gait in parkinson’s disease from plantar pressure data using long short-term memory neural-networks. Journal of neuroengineering and rehabilitation, 18(1):1–15.

Sigcha, L., Costa, N., Pavón, I., Costa, S., Arezes, P., López, J. M., and De Arcas, G. (2020). Deep learning approaches for detecting freezing of gait in parkinson’s disease patients through on-body acceleration sensors. Sensors, 20(7):1895.

Tahafchi, P., Molina, R., Roper, J. A., Sowalsky, K., Hass, C. J., Gunduz, A., Okun, M. S., and Judy, J. W. (2017). Freezing-of-gait detection using temporal, spatial, and physiological features with a support-vector-machine classifier. In 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pages 2867–2870. IEEE.

Zhang, W., Huang, D., Li, H., Wang, L., Wei, Y., Pan, K., Ma, L., Feng, H., Pan, J., and Guo, Y. (2021). Sensoring and application of multimodal data for the detection of freezing of gait in parkinson’s disease. arXiv preprint arXiv:2110.04444.

Zhang, Y. and Gu, D. (2019). A deep convolutional-recurrent neural network for freezing of gait detection in patients with parkinson’s disease. In 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), pages 1–6. IEEE.

Zhao, Y., Tonn, K., Niazmand, K., Fietzek, U. M., D’Angelo, L. T., Ceballos-Baumann, A., and Lueth, T. C. (2012). Online fog identification in parkinson’s disease with a time-frequency combined algorithm. In Proceedings of 2012 IEEE-EMBS International Conference on Biomedical and Health Informatics, pages 192–195. IEEE.