Understanding Stroke Rehabilitation Through Wearable Sensors

Published on September 8, 2022

Stroke rehabilitation is like climbing a mountain. With the increasing number of stroke patients, there is a pressing need for an accessible, scientific, and reliable evaluation method to guide their recovery journey. Just as climbers rely on GPS trackers to navigate their way up, researchers have developed a method using wearable sensors to evaluate the Brunnstrom recovery stage of the lower limb (BRS-L). In this study, motion and pressure data were collected from stroke patients and healthy individuals using special sensors. By analyzing these data, researchers were able to extract important gait features and improve the interpretability of the machine learning-based evaluation method. Interestingly, the results showed that the k-Nearest Neighbor model had the best prediction accuracy of 94.2% when fed with 18 carefully selected features. This exciting finding suggests that wearable sensor technology holds great promise for providing precise rehabilitation and enabling home-based care for hemiplegic patients. To learn more about this research and delve into the details, check out the full article!

With the increasing number of stroke patients, there is an urgent need for an accessible, scientific, and reliable evaluation method for stroke rehabilitation. Although many rehabilitation stage evaluation methods based on the wearable sensors and machine learning algorithm have been developed, the interpretable evaluation of the Brunnstrom recovery stage of the lower limb (BRS-L) is still lacking. The paper propose an interpretable BRS-L evaluation method based on wearable sensors. We collected lower limb motion data and plantar pressure data of 20 hemiplegic patients and 10 healthy individuals using seven Inertial Measurement Units (IMUs) and two plantar pressure insoles. Then we extracted gait features from the motion data and pressure data. By using feature selection based on feature importance, we improved the interpretability of the machine learning-based evaluation method. Several machine learning models are evaluated on the dataset, the results show that k-Nearest Neighbor has the best prediction performance and achieves 94.2% accuracy with an input of 18 features. Our method provides a feasible solution for precise rehabilitation and home-based rehabilitation of hemiplegic patients.

Read Full Article (External Site)

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes:

<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>