Smart Insole Gait Evaluation With Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for evaluating gait in multiple sclerosis patients are burdensome, subjective, and lack the ability to capture essential kinematic, kinetic, and spatiotemporal metrics due to the need for expensive lab equipment, making it difficult for clinicians to assess disease progression and fall risk accurately.
Innovation Solution
A system using smart insoles with sensors and machine learning algorithms to process gait data, providing a composite gait quality score and actionable insights through a user interface, enabling continuous monitoring and evaluation of gait patterns outside a lab setting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If motion cameras and complex equipment are used in lab settings, then measurement precision of gait metrics is improved, but device complexity and cost increase significantly
Solution Approach 1:
The patent replaces complex mechanical motion capture systems with inertial measurement units (IMUs) containing accelerometers, gyroscopes, and magnetometers. These electronic sensors measure gait parameters through motion detection and signal processing, eliminating the need for complex optical cameras and laboratory equipment while maintaining measurement precision for spatiotemporal gait metrics.
Solution Approach 2:
The patent uses wearable sensor copies that replicate the measurement capabilities of laboratory motion capture systems. The IMUs capture gait data in real-world settings, creating a portable copy of lab-based measurement functionality that can be used outside controlled environments without requiring access to expensive equipment.
2Measurement precision
If clinical walking tests are conducted in-person at clinician offices, then objective measurements are recorded, but patient burden increases due to travel requirements
Solution Approach 1:
The patent enables patients to conduct their own gait assessments at home using wearable smart insoles and a mobile application. The system automatically collects, processes, and analyzes gait data without requiring clinician presence or patient travel to medical offices. Patients can complete assessments in their daily environments, eliminating travel burden while maintaining objective measurement capabilities through automated sensor data collection.
3Productivity
If traditional walking tests are used, then gross walking ability is evaluated quickly, but kinematic and kinetic metrics are not captured
Solution Approach 1:
The patent segments gait analysis into multiple measurement dimensions using wearable sensors. The smart insoles capture spatiotemporal parameters (step length, step time, cadence, velocity), pressure distribution, and kinematic data simultaneously during natural walking. This segmentation of measurement capabilities allows comprehensive gait assessment including detailed kinematic and kinetic metrics while maintaining quick testing procedures in real-world settings.
4Measurement precision
If expensive motion capture laboratory equipment is accessed, then comprehensive gait data is collected, but accessibility for most clinicians is prohibitively expensive
Solution Approach 1:
The patent employs cost-effective wearable smart insoles with integrated sensors that can be used by any clinician without requiring expensive laboratory equipment. The system uses affordable accelerometers, gyroscopes, and pressure sensors embedded in insoles, replacing prohibitively expensive motion capture systems. This enables comprehensive gait data collection at a fraction of the cost, making advanced gait analysis accessible to routine clinical practice.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables objective, continuous, and understandable gait evaluation, allowing clinicians to track disease progression and fall risk, and empowering patients to monitor their walking quality and advocate for healthcare.
Implementation Method 1
Wearable devices are body-worn equipment typically in the form of an inertial measurement unit (IMU; accelerometer, gyroscope, magnetometer (not always present))
Implementation Method 2
In some cases, pressure sensor data can be leveraged to detect gait events, be used as a substitute for ground reaction forces
Implementation Method 3
Wearable devices are body-worn equipment typically in the form of an inertial measurement unit (IMU; accelerometer, gyroscope, magnetometer (not always present))
Data Source
Figure 1
Figure 2
Figure 3A~3B
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.