Kinematic Sensor Falls Risk Assessment via TUG Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current falls risk assessments, such as the timed up and go (TUG) test, have limitations in predicting falls risk due to a lack of understanding of specific segments that contribute to its predictive power, and there is a need for more detailed and automated methods to evaluate balance and gait parameters in elderly individuals.
Innovation Solution
A system using body-worn kinematic sensors, including tri-axial accelerometers and gyroscopes, to calculate TUG time segments and derived parameters like temporal gait and angular velocity-based parameters, which generate a falls risk assessment by detecting heel-strike and toe-off points and applying adaptive thresholds to ensure accurate data analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the traditional TUG test is used for falls risk assessment, then the assessment process is simple and easy to administer, but the measurement precision and understanding of specific predictive segments are limited
Solution Approach 1:
The patent segments the TUG test into multiple distinct phases (rising from chair, walking, turning, returning, sitting down) and further divides each phase into sub-segments using kinematic sensors. This segmentation allows for precise measurement of specific movements and identification of which segments contribute most to falls risk prediction, thereby improving measurement precision while managing complexity through systematic breakdown of the assessment protocol.
Solution Approach 2:
The patent replaces the manual timing and observation method of the traditional TUG test with an automated electronic system using tri-axial accelerometers and gyroscopes. This substitution of mechanical/manual assessment with electronic sensing and computational analysis significantly improves measurement precision by providing objective, continuous data capture, while the automated processing helps manage the inherent complexity of the enhanced assessment system.
2Measurement precision
If body-worn kinematic sensors are used to calculate TUG time segments and derived parameters, then the measurement precision and detail of balance and gait parameters are improved, but the device complexity and data processing requirements increase
Solution Approach 1:
The patent employs multi-functional kinematic sensors (tri-axial accelerometers and gyroscopes) that simultaneously capture multiple types of motion data (linear acceleration, angular velocity) and can analyze various aspects of gait and balance within a single integrated system. This multi-functionality improves measurement precision across multiple parameters while reducing the overall device complexity compared to using separate specialized sensors for each measurement type.
Solution Approach 2:
The system incorporates automated algorithms that self-process the raw sensor data to calculate TUG time segments, detect heel-strike and toe-off events, compute derived parameters, and generate falls risk assessments without requiring manual intervention. This self-service capability manages the complexity of data processing by automating the entire analysis pipeline, allowing the system to handle complex computations while maintaining ease of use.
3Productivity
If automated detection of heel-strike and toe-off points with adaptive thresholds is implemented, then the productivity and accuracy of data analysis are improved, but the computational requirements and system complexity increase
Solution Approach 1:
The system pre-establishes adaptive thresholds based on population norms and individual baseline measurements before conducting the TUG test. These pre-computed thresholds are stored and applied during real-time data analysis, enabling rapid automated detection of heel-strike and toe-off points. This preliminary action improves productivity by avoiding complex real-time calculations during the actual test, while the threshold-based approach manages computational complexity through simplified comparison operations.
Solution Approach 2:
The system implements feedback mechanisms where the detected gait parameters and timing data are continuously compared against adaptive thresholds, and the results feed into the falls risk assessment algorithm. This feedback loop enables automated, iterative refinement of the analysis, improving productivity through systematic processing while managing complexity through structured feedback pathways that guide the computational workflow.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system provides a more detailed and automated falls risk assessment, enabling healthcare practitioners to identify deficits in balance, vestibular impairment, and muscular strength, and demonstrates strong correlation with manual TUG times and Berg balance scale scores, improving the prediction of falls risk in elderly individuals.
Implementation Method 1
A plurality of kinematic sensors 14 (14a-14b) are coupled to a corresponding plurality of shanks 16 (16a-16b) of an individual 10 and output angular velocity data
Implementation Method 2
body-worn kinematic sensors, including tri-axial accelerometers and gyroscopes, to calculate TUG time segments and derived parameters
Data Source
AI summary
Methods and systems may provide for a plurality of kinematic sensors to be coupled to a corresponding plurality of shanks of an individual, a processor, and a memory to store a set of instructions. If executed by the processor, the instructions can cause the system to calculate a timed up and go (TUG) time segment based on angular velocity data from the plurality of kinematic sensors. The instructions may also cause the system to calculate a derived parameter based on the angular velocity data, and generate a falls risk assessment based on at least one of the TUG time segment and the derived parameter.