3D Motion Capture Assessment for Remote Musculoskeletal Screening
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional musculoskeletal assessments, such as the Star Excursion Balance Test (SEBT), suffer from poor accuracy, reliability, and repeatability due to manual scoring and require costly motion capture systems and specialized environments, limiting their widespread adoption in clinical settings.
Innovation Solution
A method utilizing three-dimensional posture and time series motion data, combined with kinematic modeling and dimensionality reduction techniques, to provide robust and objective biomechanical assessments, adaptable for remote implementation and reduced costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If manual scoring is used for SEBT, then the assessment can be performed without specialized equipment, but the accuracy and reliability of the assessment deteriorates
Solution Approach 1:
The patent replaces manual mechanical scoring with an automated computer vision system that captures motion data and automatically analyzes it. The system uses machine learning models to process video recordings and generate objective assessments, eliminating the need for manual measurement while significantly improving accuracy and reliability of the SEBT results.
2Measurement precision
If high-cost motion capture systems are used, then measurement precision improves, but device complexity and cost increase
Solution Approach 1:
The patent employs inexpensive, readily available devices such as smartphones and standard video cameras instead of expensive motion capture systems. The system processes standard video footage using computer vision algorithms, achieving comparable or superior measurement precision without requiring specialized expensive equipment or complex calibration procedures.
Solution Approach 2:
The patent creates a virtual model of the patient's movement by extracting and analyzing key pose information from video recordings. Instead of directly measuring physical motion with complex sensors, the system captures visual copies of movement and processes them through machine learning models to derive biomechanical parameters.
3Measurement precision
If multiple markers are required for motion capture, then measurement precision improves, but ease of operation and accessibility deteriorates
Solution Approach 1:
The system automatically detects and tracks body landmarks by processing video data through trained machine learning models. The algorithm independently identifies key anatomical points without requiring the patient to attach or position any markers, making the assessment process self-sufficient and eliminating preparation steps that burden the patient or require specialized personnel.
Data Source
AI summary
The inventors discovered that three-dimensional posture and time series motion data are capable of providing robust, accurate and objective assessments of patient musculoskeletal health. Through the coupling of novel kinematic modeling and dimensionality reduction techniques, the invention is able to utilize posture and motion trajectory data in order to identify various neuromuscular and musculoskeletal conditions previously indistinguishable through the use of conventional clinical assessments. Further, by leveraging recent advancements in motion capture technologies, the invention provides approaches and systems adapted for remote implementation, allowing for quantitative and objective assessments to be collected over time and at reduced cost. Methods of generating a biomechanical assessment for a patient are provided.