Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Patterns of Muscle Health in Single- and Multi-Site Chronic Pain: A UK Biobank Normative Modeling Study.

medRxiv : the preprint server for health sciences·2026

Same author

Neural Shape Modeling Reveals Early and Progressive Femoral Bone Shape and Cartilage Thickness Changes After Anterior Cruciate Ligament Reconstruction.

medRxiv : the preprint server for health sciences·2026

Same author

Perturbation Recovery Time Identifies Subtle Human Balance Impairments and Features.

IEEE transactions on bio-medical engineering·2026

Same author

The menstrual cycle through the lens of a wearable device: insights into physiology, sleep, and cycle variability.

NPJ digital medicine·2026

Same author

BMI and Varus Malalignment Compound to Define a High-Risk Phenotype for Compartment-Specific Knee Osteoarthritis Progression.

medRxiv : the preprint server for health sciences·2026

Same author

Estimating Magnetic Field at Joint Centers Reduces Kinematic Errors in Inertial Motion Capture.

Research square·2026

Search research articles

Related Experiment Video

Updated: Jan 13, 2026

Using Gold-standard Gait Analysis Methods to Assess Experience Effects on Lower-limb Mechanics During Moderate High-heeled Jogging and Running

Using Gold-standard Gait Analysis Methods to Assess Experience Effects on Lower-limb Mechanics During Moderate High-heeled Jogging and Running

Published on: September 14, 2017

GaitDynamics: a generative foundation model for analyzing human walking and running.

Tian Tan^1,2, Tom Van Wouwe³, Keenon F Werling⁴

¹Department of Bioengineering, Stanford University, Stanford, CA, USA. alanttan@stanford.edu.

Nature Biomedical Engineering

|January 6, 2026

Summary

This summary is machine-generated.

We developed GaitDynamics, a novel deep learning model trained on diverse human gait data. This foundation model accurately predicts gait forces and motions, aiding mobility and injury prevention.

More Related Videos

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Published on: April 13, 2016

Postural Organization of Gait Initiation for Biomechanical Analysis Using Force Platform Recordings

Postural Organization of Gait Initiation for Biomechanical Analysis Using Force Platform Recordings

Published on: July 26, 2022

Related Experiment Videos

Last Updated: Jan 13, 2026

Using Gold-standard Gait Analysis Methods to Assess Experience Effects on Lower-limb Mechanics During Moderate High-heeled Jogging and Running

Using Gold-standard Gait Analysis Methods to Assess Experience Effects on Lower-limb Mechanics During Moderate High-heeled Jogging and Running

Published on: September 14, 2017

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Published on: April 13, 2016

Postural Organization of Gait Initiation for Biomechanical Analysis Using Force Platform Recordings

Postural Organization of Gait Initiation for Biomechanical Analysis Using Force Platform Recordings

Published on: July 26, 2022

Area of Science:

Biomechanics
Artificial Intelligence
Human Mobility

Background:

Understanding human gait dynamics (motion and forces) is crucial for mobility.
Existing deep learning models for gait analysis are limited by small, homogeneous datasets and single-output predictions.
Costly lab experiments and simulations are traditional methods for gait analysis.

Purpose of the Study:

To develop a versatile generative foundation model for human gait analysis.
To enable flexible inputs and outputs for diverse clinical applications.
To overcome limitations of existing deep learning models in gait research.

Main Methods:

Developed GaitDynamics, a generative foundation model.
Trained the model on a large, diverse dataset of human gait patterns.
Utilized deep learning for flexible input/output predictions.

Main Results:

GaitDynamics accurately estimates ground reaction forces from kinematics, even with missing data.
The model predicts the effects of gait modifications on knee loading without extensive experiments.
It predicts kinematic and force changes associated with varying running speeds.

Conclusions:

GaitDynamics demonstrates high accuracy and efficiency in gait analysis.
The model has potential for assessing and optimizing gait for injury prevention, disease treatment, and performance coaching.
Publicly shared data, code, and models facilitate further research and application.