Video Motion Tracking for Objective Bradykinesia Behavior Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for evaluating patient movement disorders, such as Parkinson's disease, are inaccurate, inconsistent, and unreliable due to reliance on clinician training and limited clinical visits, leading to suboptimal therapy delivery.
Innovation Solution
A system analyzes video information to objectively identify patient behaviors by calculating movement parameters from video frames, comparing them to predefined criteria, and controlling therapy based on identified behaviors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If clinician-based evaluation methods are used to assess patient movement disorders, then the evaluation process is simple to implement, but the accuracy and reliability of behavior identification deteriorates
Solution Approach 1:
The patent replaces the manual mechanical evaluation process (clinician observation and scoring) with an automated optical system. Video cameras capture patient movements, and image processing algorithms automatically analyze motion parameters to identify behaviors such as bradykinesia, tremor, and rigidity. This substitution eliminates human subjectivity while maintaining system accessibility through standard video equipment.
Solution Approach 2:
The system enables self-assessment capability where the automated analysis performs the evaluation function independently without requiring continuous clinician intervention. The image processing system automatically detects anatomical regions, tracks motion across video frames, and generates behavior identification results, allowing the system to serve itself in the evaluation process.
2Reliability
If frequent and continuous patient assessment is implemented, then therapy delivery accuracy improves, but the time and resource requirements increase
Solution Approach 1:
The patent implements continuous assessment by analyzing video frames in real-time as the patient performs motor tasks. Rather than discrete periodic measurements, the system continuously tracks anatomical region motion across multiple video frames, providing ongoing behavior identification that maintains accurate therapy delivery without interruption or time loss between assessments.
Solution Approach 2:
The system performs preliminary identification of anatomical regions in the video feed before detailed motion analysis. By pre-processing the video data to locate and define regions of interest (such as head, torso, or extremities), the system prepares the data structure in advance, enabling rapid subsequent analysis of motion parameters without adding assessment time.
3Measurement precision
If automated video analysis is used to identify patient behaviors, then measurement precision improves, but the difficulty of detecting and measuring motion parameters increases
Solution Approach 1:
The patent divides the complex motion analysis task into separate processing stages: video frame acquisition, anatomical region detection, motion parameter calculation, and behavior identification. By segmenting the analysis pipeline, each component can be optimized independently, reducing the overall difficulty of implementing precise motion measurement while maintaining comprehensive behavior assessment capability.
Data Source
AI summary
Devices, systems, and techniques for analyzing video information to objectively identify patient behavior are disclosed. A system may analyze obtained video information of patient motion during a period of time to track one or more anatomical regions through a plurality of frames of the video information and calculate one or more movement parameters of the one or more anatomical regions. The system may also compare the one or more movement parameters to respective criteria for each of a plurality of predetermined patient behaviors and identify the patient behaviors that occurred during the period of time. In some examples, a device may control therapy delivery according to the identified patient behaviors and/or sensed parameters previously calibrated based on the identified patient behaviors.