Clinical Disorder Assessment Through Interpretable Submovement Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current tools for assessing clinical disorders, particularly neurological disorders, are subjective, imprecise, and unable to account for day-to-day variability in disease state, behavioral task performance, and measurement error, making them ineffective for determining therapy efficacy.
Innovation Solution
A system and method for clinical disorder assessment using interpretable submovement features extracted from sensor data, such as those from wearable devices and video, to objectively analyze motor function and generate reports on potential disorders.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If clinician-performed therapies are used to assess clinical disorders, then the assessment can be performed with simple tools, but the assessment is subjective, imprecise, and cannot account for day-to-day variability
Solution Approach 1:
The patent replaces clinician-performed mechanical assessments with an automated computer vision system that uses cameras to capture movement data. The system processes video feeds through image processing algorithms to extract movement features, eliminating subjectivity and improving precision while reducing dependence on clinician expertise.
Solution Approach 2:
The system enables self-assessment by allowing patients to perform motor tasks independently while the system automatically captures and analyzes their movement. The automated feature extraction and disease state determination eliminate the need for continuous clinician involvement, providing objective measurements that account for day-to-day variability.
2Reliability
If in-person assessments are performed infrequently, then the assessment process remains simple, but the tools cannot account for day-to-day and moment-to-moment variability
Solution Approach 1:
The system enables continuous or frequent assessment through automated video capture that can operate multiple times per day without requiring clinician presence. This continuous monitoring allows the system to capture day-to-day and moment-to-moment variability in disease state, improving reliability while the automated nature eliminates time loss associated with repeated in-person visits.
Solution Approach 2:
The system introduces an automated intermediary between patient and clinician - a computer vision system that continuously captures movement data and processes it through image processing algorithms. This intermediary enables frequent, objective measurements of disease state without requiring direct clinician-patient interaction, thereby improving reliability while minimizing time investment.
3Loss of information
If traditional assessment tools are used, then the assessment process remains straightforward, but it is unclear whether measured characteristics reflect aspects of behavioral change meaningful to patients
Solution Approach 1:
The system focuses on specific local movement characteristics (joint angles, movement velocity, movement trajectory) that are directly relevant to patient-reported functional abilities. By extracting and analyzing these specific local features rather than general movement patterns, the system identifies measurements that reflect meaningful behavioral changes to patients while maintaining manageable system complexity through targeted feature extraction.
Data Source
AI summary
A system and method for clinical disorder assessment are disclosed. The method and the medical assessment system using the method include: obtaining sensor data indicative of movement of a user; generating a movement dataset by reducing dimensions of the sensor data; generating a plurality of submovement datasets based on the movement dataset; extracting a movement feature from a first subset of the plurality of submovement datasets; analyzing the movement feature from the first subset of the plurality of submovement datasets to a reference to determine a potential clinical disorder of the user; and generating a report that includes an indication and severity of the potential clinical disorder of the user. Other aspects, embodiments, and features are also claimed and described.