Evaluation of Patients' Levels of Walking Independence Using Inertial Sensors and Neural Networks in an Acute-Care Hospital.

This study aimed to evaluate walking independence in acute-care hospital patients using neural networks based on acceleration and angular velocity from two walking tests. Forty patients underwent the 10-m walk test and the Timed Up-and-Go test at normal speed, with or without a cane. Physiotherapists divided the patients into two groups: 24 patients who were monitored or independent while walking with a cane or without aids in the ward, and 16 patients who were not. To classify these groups, the Transformer model analyzes the left gait cycle data from eight inertial sensors. The accuracy using all the sensor data was 0.836. When sensor data from the right ankle, right wrist, and left wrist were excluded, the accuracy decreased the most. When analyzing the data from these three sensors alone, the accuracy was 0.795. Further reducing the number of sensors to only the right ankle and wrist resulted in an accuracy of 0.736. This study demonstrates the potential of a neural network-based analysis of inertial sensor data for clinically assessing a patient's level of walking independence.

Effects of the walking independence on lower extremity and trunk muscle activity during straight-leg raising following incomplete cervical cord injury.

The purpose of this study was to compare the acceleration and surface electromyography (EMG) of the lower extremity and trunk muscles during straight-leg raising (SLR) in patients with incomplete cervical cord injury according to their levels of walking independence. Twenty-four patients were measured acceleration and EMG during SLR held for 10 s. Data were analyzed separately for the dominant and nondominant sides and compared between the nonindependent (NI) and independent (ID) groups based on their levels of walking independence. Frequency analysis of the EMG showed that the high-frequency (HF) band of the contralateral biceps femoris (BF) in the ID group and bands below the medium-frequency (MF) of the BF and the HF and MF bands of the rectus abdominis in the NI group were significantly higher during dominant and nondominant SLR. During the nondominant SLR, the low-frequency band of the internal oblique and the MF band of the external oblique were significantly higher in the NI group. The ID group mobilized muscle fiber type 2 of the BF, whereas the NI group mobilized type 1 of the BF and types 2 and 1 of the trunk muscles to stabilize the pelvis. This result was more pronounced during the nondominant SLR.