Modeling biological individuality using machine learning: A study on human gait

Autoren

Fabian Horst
Djordje Slijepcevic
Marvin Simak
Brian Horsak
Wolfgang Immanuel Schöllhorn
Matthias Zeppelzauer

DOI

10.1016/j.csbj.2023.06.009

ISSN

2001-0370

Zeitschrift

Computational and Structural Biotechnology Journal

Sprache

en

Paginierung

3414 - 3423

Datum der Veröffentlichung

2023

Status

Published

Herausgeber

Elsevier BV

Herausgeber URL

http://dx.doi.org/10.1016/j.csbj.2023.06.009

Datum der Datenerfassung

2024

Titel

Modeling biological individuality using machine learning: A study on human gait

Ausgabe der Zeitschrift

21

Datenquelle: Crossref

Abstract

Human gait is a complex and unique biological process that can offer valuable insights into an individual's health and well-being. In this work, we leverage a machine learning-based approach to model individual gait signatures and identify factors contributing to inter-individual variability in gait patterns. We provide a comprehensive analysis of gait individuality by (1) demonstrating the uniqueness of gait signatures in a large-scale dataset and (2) highlighting the gait characteristics that are most distinctive to each individual. We utilized the data from three publicly available datasets comprising 5368 bilateral ground reaction force recordings during level overground walking from 671 distinct healthy individuals. Our results show that individuals can be identified with a prediction accuracy of 99.3% by using the bilateral signals of all three ground reaction force components, with only 10 out of 1342 recordings in our test data being misclassified. This indicates that the combination of bilateral ground reaction force signals with all three components provides a more comprehensive and accurate representation of an individual's gait signature. The highest accuracy was achieved by (linear) Support Vector Machines (99.3%), followed by Random Forests (98.7%), Convolutional Neural Networks (95.8%), and Decision Trees (82.8%). The proposed approach provides a powerful tool to better understand biological individuality and has potential applications in personalized healthcare, clinical diagnosis, and therapeutic interventions.

Addresses

Department of Training and Movement Science, Institute of Sport Science, Johannes Gutenberg-University Mainz, Mainz, Germany.

Autoren

Fabian Horst
Djordje Slijepcevic
Marvin Simak
Brian Horsak
Wolfgang Immanuel Schöllhorn
Matthias Zeppelzauer

DOI

10.1016/j.csbj.2023.06.009

eISSN

2001-0370

Externe Identifier

PubMed Identifier: 37416082
PubMed Central ID: PMC10319823

Open access

true

ISSN

2001-0370

Zeitschrift

Computational and structural biotechnology journal

Sprache

eng

Medium

Electronic-eCollection

Online publication date

2023

Open access status

Open Access

Paginierung

3414 - 3423

Datum der Veröffentlichung

2023

Status

Published

Publisher licence

CC BY-NC-ND

Datum der Datenerfassung

2023

Titel

Modeling biological individuality using machine learning: A study on human gait.

Sub types

research-article
Journal Article

Ausgabe der Zeitschrift

21

Files

http://www.csbj.org/article/S2001037023002222/pdf https://europepmc.org/articles/PMC10319823?pdf=render

Datenquelle: Europe PubMed Central

Abstract

Human gait is a complex and unique biological process that can offer valuable insights into an individual's health and well-being. In this work, we leverage a machine learning-based approach to model individual gait signatures and identify factors contributing to inter-individual variability in gait patterns. We provide a comprehensive analysis of gait individuality by (1) demonstrating the uniqueness of gait signatures in a large-scale dataset and (2) highlighting the gait characteristics that are most distinctive to each individual. We utilized the data from three publicly available datasets comprising 5368 bilateral ground reaction force recordings during level overground walking from 671 distinct healthy individuals. Our results show that individuals can be identified with a prediction accuracy of 99.3% by using the bilateral signals of all three ground reaction force components, with only 10 out of 1342 recordings in our test data being misclassified. This indicates that the combination of bilateral ground reaction force signals with all three components provides a more comprehensive and accurate representation of an individual's gait signature. The highest accuracy was achieved by (linear) Support Vector Machines (99.3%), followed by Random Forests (98.7%), Convolutional Neural Networks (95.8%), and Decision Trees (82.8%). The proposed approach provides a powerful tool to better understand biological individuality and has potential applications in personalized healthcare, clinical diagnosis, and therapeutic interventions.

Date of acceptance

2023

Autoren

Fabian Horst
Djordje Slijepcevic
Marvin Simak
Brian Horsak
Wolfgang Immanuel Schöllhorn
Matthias Zeppelzauer

Autoren-URL

https://www.ncbi.nlm.nih.gov/pubmed/37416082

DOI

10.1016/j.csbj.2023.06.009

Externe Identifier

PubMed Central ID: PMC10319823

ISSN

2001-0370

Zeitschrift

Comput Struct Biotechnol J

Schlüsselwörter

Biomechanics
Explainable artificial intelligence
Force-based gait recognition
Ground reaction forces
Human gait recognition
Layer-wise relevance propagation

Sprache

eng

Country

Netherlands

Paginierung

3414 - 3423

PII

S2001-0370(23)00222-2

Datum der Veröffentlichung

2023

Status

Published online

Titel

Modeling biological individuality using machine learning: A study on human gait.

Sub types

Journal Article

Ausgabe der Zeitschrift

21

Datenquelle: PubMed

Author's licence

CC-BY-NC-ND

Autoren

Fabian Horst
Djordje Slijepcevic
Marvin Simak
Brian Horsak
Wolfgang Immanuel Schöllhorn
Matthias Zeppelzauer

Hosting institution

Universitätsbibliothek Mainz

Sammlungen

DFG-491381577-G

Resource version

Published version

DOI

10.1016/j.csbj.2023.06.009

File(s) embargoed

false

Open access

true

Zeitschrift

Computational and Structural Biotechnology Journal

Schlüsselwörter

610 Medizin
610 Medical sciences
796 Sport
796 Athletic and outdoor sports and games

Sprache

eng

Open access status

Open Access

Paginierung

3414 - 3423

Datum der Veröffentlichung

2023

Public URL

https://openscience.ub.uni-mainz.de/handle/20.500.12030/9310

Herausgeber

Elsevier

Datum der Datenerfassung

2023

Datum, an dem der Datensatz öffentlich gemacht wurde

2023

Zugang

Public

Titel

Modeling biological individuality using machine learning : a study on human gait

Ausgabe der Zeitschrift

21

Files

modeling_biological_individua-20230718090723602.pdf

Datenquelle: OPENSCIENCE.UB

Modeling biological individuality using machine learning: A study on human gait

Files

Files

Werkzeuge