Wearable Movement Analysis for Cognitive and Motion Disease Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining diseases related to cognition and motion, such as dementia and Parkinson's disease, impose a significant burden on subjects and require costly processing, leading to potential inaccuracies in determination results.
Innovation Solution
An information processing apparatus that utilizes a wearable device to measure movement data, distinguishing between sections of walking and non-walking to acquire feature amounts, and applies machine learning models to derive determination criteria for diseases like MCI and Parkinson's disease.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the subject performs specific motions such as drawing or pressing figures, then disease determination can be performed, but the burden on the subject becomes large
Solution Approach 1:
The system automatically captures movement data from the subject's daily activities without requiring the subject to perform specific prescribed motions. The wearable device continuously monitors natural movements, and the processing apparatus automatically analyzes the data to determine disease status, eliminating the need for the subject to actively participate in specific tasks.
Solution Approach 2:
The system segments the analysis into different movement sections (first section and second section with different detection targets) and processes them separately through feature amount acquisition and disease determination. This allows comprehensive analysis of various movement types without requiring the subject to perform all movements deliberately.
2Reliability
If factor information is determined using regression models, then disease determination can be performed, but processing cost increases
Solution Approach 1:
The system extracts and analyzes specific feature amounts from movement data (such as movement range, speed, and pattern features) rather than processing all raw sensor data through complex regression models. By identifying and focusing on key diagnostic features, the system achieves accurate disease determination with reduced computational complexity.
3Adaptability or versatility
If a two-stage determination process is used to determine mild cognitive impairment, then determination can be performed, but determination accuracy decreases due to accumulated errors
Solution Approach 1:
The system merges the determination of multiple disease types (cognitive disease and motion disease) into a single integrated determination process. By simultaneously analyzing movement data for both cognitive and motion aspects using the same feature extraction and determination framework, the system avoids the error accumulation that occurs in sequential two-stage determination processes.
Data Source
AI summary
A processor is configured to specify a first section and a second section in which a detection target of movement of a subject is different, based on a measurement value of the movement of the subject measured by a device that is mountable on the subject; acquire at least one feature amount representing a feature of a disease related to at least one of cognition or motion based on each of a measurement value of the first section and a measurement value of the second section; and acquire a determination result of the disease based on the feature amount and a predetermined determination criterion.