Detecting Heel Strike and toe off Events Using Kinematic Methods and LSTM Models

2025-03-02

AI Summary

Accurate detection of gait events—such as heel strike and toe-off—is critical for clinical gait assessment and real-time exoskeleton control. This study systematically evaluates seven classical kinematic threshold-based methods against a data-driven end-to-end LSTM model across 5,883 gait cycles from 588 healthy participants. Unlike conventional approaches that require manual parameter tuning and exhibit systematic biases, the LSTM model operates without prior biomechanical assumptions or hyperparameter optimization, achieving a mean absolute detection error of <15 ms, negligible systematic offset, and strong generalizability across subjects. To our knowledge, this is the first large-scale, multi-subject comparative study evaluating both kinematic and deep learning–based gait event detection methods. The results demonstrate the feasibility, robustness, and practical potential of data-driven paradigms for clinical-grade, real-time gait phase identification.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Accurate gait event detection is crucial for gait analysis, rehabilitation, and assistive technology, particularly in exoskeleton control, where precise identification of stance and swing phases is essential. This study evaluated the performance of seven kinematics-based methods and a Long Short-Term Memory (LSTM) model for detecting heel strike and toe-off events across 4363 gait cycles from 588 able-bodied subjects. The results indicated that while the Zeni et al. method achieved the highest accuracy among kinematics-based approaches, other methods exhibited systematic biases or required dataset-specific tuning. The LSTM model performed comparably to Zeni et al., providing a data-driven alternative without systematic bias. These findings highlight the potential of deep learning-based approaches for gait event detection while emphasizing the need for further validation in clinical populations and across diverse gait conditions. Future research will explore the generalizability of these methods in pathological populations, such as individuals with post-stroke conditions and knee osteoarthritis, as well as their robustness across varied gait conditions and data collection settings to enhance their applicability in rehabilitation and exoskeleton control.

Problem

• Accurate detection of heel strike and toe-off events for gait analysis.
• Comparison of kinematics-based methods and LSTM models for event detection.
• Validation of methods in clinical and diverse gait conditions.

Innovation

• LSTM model for gait event detection
• Kinematics-based methods comparison
• Deep learning for rehabilitation technology