Smart Insole Gait Evaluation Using Machine Learning Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for monitoring and evaluating gait in individuals with multiple sclerosis (MS) are burdensome, subjective, and lack objective data, particularly in assessing kinematic, kinetic, and spatiotemporal metrics.
Innovation Solution
A computer-implemented method and system using smart insoles with sensors and machine learning algorithms to segment and process gait data, calculating a composite gait quality score based on gait patterns, parameters, and phenotypes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If clinical walking tests are used to assess gait, then the tests are quick to administer and require minimal equipment, but the results are subjective and lack objective kinematic, kinetic, and spatiotemporal metrics
Solution Approach 1:
The patent replaces complex mechanical motion capture systems with wearable inertial sensors (accelerometers, gyroscopes, magnetometers) that can be integrated into shoe insoles. This substitution maintains measurement precision for kinematic, kinetic, and spatiotemporal metrics while dramatically reducing device complexity and making the system portable for clinical use
Solution Approach 2:
The wearable sensor system automatically captures and processes gait data without requiring complex external equipment or laboratory infrastructure. The system self-calibrates and processes data through embedded algorithms, enabling objective gait assessment in natural walking conditions without the need for sophisticated motion capture laboratories
2Measurement precision
If motion capture laboratories with complex equipment are used, then objective gait metrics can be captured, but the equipment is prohibitively expensive and not accessible to most clinicians
Solution Approach 1:
The patent employs inexpensive wearable sensor units that can be mass-produced and distributed widely. These disposable or reusable sensor insoles cost a fraction of motion capture laboratory equipment, making objective gait analysis accessible to routine clinical practice while maintaining measurement precision through advanced inertial measurement units
Solution Approach 2:
The system creates a portable, simplified copy of laboratory-grade motion capture capabilities using wearable sensors. By replicating the essential measurement functions in a compact, wearable form factor, the system brings laboratory-quality gait analysis to clinical settings without requiring actual motion capture infrastructure
3Loss of information
If traditional walking tests are used, then they evaluate gross walking ability, but they cannot analyze detailed kinematic, kinetic, and spatiotemporal metrics
Solution Approach 1:
The patent segments the foot into multiple sensing zones within the insole, with sensors distributed across different regions to capture localized pressure, acceleration, and orientation data. This segmentation enables detailed analysis of kinematic, kinetic, and spatiotemporal metrics throughout the gait cycle while keeping each individual sensor simple and the overall system manageable
Data Source
AI summary
Disclosed herein are systems and methods for monitoring and evaluating a user's gait. In one embodiment, the method comprises training one or more human activity recognition (HAR) models, each HAR model comprising at least one artificial neural network (ANN) trained on a general or phenotype-specific population. The HAR models are used to identify one or more ambulatory activities in sensor data measured by one or more sensors from a pair of smart insoles worn by the individual. The data is segmented into one or more segments in accordance with the identified ambulatory activities. A gait detection algorithm is used to characterize a gait event with one or more spatiotemporal metrics. The spatiotemporal metrics are classified via one or more machine learning algorithms to produce a gait quality index (CI) score.