Publications by authors named "H G Hiden"
Background: Wrist-worn inertial sensors are used in digital health for evaluating mobility in real-world environments. Preceding the estimation of spatiotemporal gait parameters within long-term recordings, gait detection is an important step to identify regions of interest where gait occurs, which requires robust algorithms due to the complexity of arm movements. While algorithms exist for other sensor positions, a comparative validation of algorithms applied to the wrist position on real-world data sets across different disease populations is missing.
View Article and Find Full Text PDFArticle Synopsis
- - The study evaluated the accuracy of a wearable device designed to estimate walking speed in individuals, including those with various health conditions and healthy older adults, over a 2.5-hour period in both laboratory and real-world settings.
- - Results showed that the device's walking speed estimates had a mean absolute error ranging from 0.06 to 0.13 m/s, indicating good to excellent agreement with a multi-sensor reference system, particularly for participants without significant gait impairments.
- - The findings underscore the importance of validating technology for clinical use, as accuracy varied with factors like task complexity and walking duration, suggesting the need for thorough testing before implementation in real-world mobility assessments.
Article Synopsis
- The study highlights a shift in gait analysis from traditional supervised tests to unsupervised monitoring using inertial measurement units (IMUs), improving ecological validity.
- A deep learning algorithm was developed to accurately detect gait events (like initial and final contacts) in diverse populations by analyzing data from pressure insoles and IMUs over 2.5 hours.
- The algorithm demonstrated high accuracy in detecting these events and produced gait parameters closely aligned with established pressure insole references, suggesting its effectiveness in real-world settings.