Video Body Landmark Tracking for Objective Movement Disorder Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for diagnosing movement disorders, such as Parkinson's Disease, rely on subjective clinical ratings and lack objective tools, leading to misdiagnosis and limited accessibility, especially for consumers without specialized equipment.
Innovation Solution
A computing system utilizing machine-learned body landmark models to analyze video data from consumer devices, identifying body landmarks and biomarkers to predict movement health conditions, incorporating IMU data for quantified assessments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If subjective clinical ratings are used for movement disorder diagnosis, then medical expertise can be applied, but objectivity and consistency of diagnosis deteriorate
Solution Approach 1:
The patent replaces subjective mechanical clinical assessment with an automated computer vision system that uses machine learning models to objectively analyze video data of patient movements, eliminating human subjectivity while maintaining diagnostic capability
Solution Approach 2:
The patent creates a digital copy of the clinical assessment process through virtual body landmarks and synthetic skeletal models that replicate human movement analysis, allowing automated processing without requiring specialized medical equipment
2Measurement precision
If automated body landmark tracking is implemented, then diagnosis objectivity is improved, but computational complexity increases
Solution Approach 1:
The patent segments the complex diagnostic task into distinct machine learning components: a body landmark model for detecting anatomical points, a biomarker extraction model for identifying movement patterns, and a diagnostic model for interpreting results, allowing each component to be optimized independently
Solution Approach 2:
The patent introduces virtual body landmarks as intermediary elements that bridge raw video data and clinical interpretation, serving as intermediate representations that simplify the computational pipeline and improve processing efficiency
3Measurement precision
If frequent in-person neurologist visits are required for assessment, then diagnostic accuracy can be maintained, but patient accessibility and convenience deteriorate
Solution Approach 1:
The patent enables patients to perform self-assessment by recording their own movement videos using personal devices, eliminating the need for frequent clinic visits while maintaining diagnostic quality through automated analysis
Solution Approach 2:
The patent designs a universal assessment system that can be deployed on common consumer devices like smartphones and tablets, making the diagnostic tool accessible to any patient regardless of location or specialized equipment availability
Data Source
AI summary
A method for facilitating a Parkinson's Disease (“PD”) assessment of a patient includes capturing first video of a patient performing first test movements while holding the mobile device; capturing second video of the patient performing second test movements while maintaining the mobile device on their person; capturing third video of the patient performing third test movements including standing and walking; capturing one or more IMU readings using an IMU of the mobile device; processing the first video, the second video, and the third video according to (i) a hand landmark model to generate one or more hand biomarkers, (ii) a face landmark model to generate one or more face biomarkers, and (iii) a body landmark model to generate one or more body biomarkers; and determining an assessment score based on a standardized PD assessment by processing the biomarkers.