Authors:
Sandra Hellmers
1
;
Tobias Kromke
1
;
Lena Dasenbrock
1
;
Andrea Heinks
1
;
Jürgen M. Bauer
2
;
Andreas Hein
1
and
Sebastian Fudickar
1
Affiliations:
1
Carl von Ossietzky University Oldenburg, Germany
;
2
Heidelberg University, Germany
Keyword(s):
Stair Climb Power, Inertial Measurement Unit (IMU), Power, Stair Ascending, Machine Learning, Clinical Assessment, Unsupervised, Wearable Sensors.
Related
Ontology
Subjects/Areas/Topics:
Biomedical Engineering
;
Biomedical Signal Processing
;
Devices
;
Distributed and Mobile Software Systems
;
Health Engineering and Technology Applications
;
Health Information Systems
;
Human-Computer Interaction
;
Mobile Technologies
;
Mobile Technologies for Healthcare Applications
;
Neural Rehabilitation
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition and Machine Learning
;
Physiological Computing Systems
;
Software Engineering
;
Wearable Sensors and Systems
Abstract:
In order to initiate interventions at an early stage of functional decline and thus, to extend independent living,
the early detection of changes in functional ability is important. The Stair Climb Power Test (SCPT) is a
standard test in geriatric assessments for strength as one of the essential components of functional ability. This
test is also well suited for regular and frequent power measurements in daily life since the activity of climbing
stairs is usually frequently performed.
We introduce an automated assessment of the SCPT based on inertial measurement units (IMU) in a study
of 83 participants aged 70-87 years. For power evaluations of the lower extremities, the activity of climbing
stairs was automatically classified via machine learning and the power was calculated based on the test duration
and covered height. Climbing stairs was correctly classified in 93% of the cases. We also achieved a good
correlation of the power calculations with the conventional stop wat
ch measurements with a mean deviation of
2.35%. The system’s sensitivity to detect the transition towards frailty has been confirmed. Furthermore, we
discussed the general suitability of the automated stair climb power algorithm in unsupervised, standardized
home-assessments.
(More)