Modeling biological individuality using machine learning: A study on human gait
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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-01-01
|
| Series: | Computational and Structural Biotechnology Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2001037023002222 |
| _version_ | 1797384064949288960 |
|---|---|
| author | Fabian Horst Djordje Slijepcevic Marvin Simak Brian Horsak Wolfgang Immanuel Schöllhorn Matthias Zeppelzauer |
| author_facet | Fabian Horst Djordje Slijepcevic Marvin Simak Brian Horsak Wolfgang Immanuel Schöllhorn Matthias Zeppelzauer |
| author_sort | Fabian Horst |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-08T21:30:06Z |
| format | Article |
| id | doaj.art-61c3a247c28e4e10995aa02ea5d8d83c |
| institution | Directory Open Access Journal |
| issn | 2001-0370 |
| language | English |
| last_indexed | 2024-03-08T21:30:06Z |
| publishDate | 2023-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Computational and Structural Biotechnology Journal |
| spelling | doaj.art-61c3a247c28e4e10995aa02ea5d8d83c2023-12-21T07:31:40ZengElsevierComputational and Structural Biotechnology Journal2001-03702023-01-012134143423Modeling biological individuality using machine learning: A study on human gaitFabian Horst0Djordje Slijepcevic1Marvin Simak2Brian Horsak3Wolfgang Immanuel Schöllhorn4Matthias Zeppelzauer5Department of Training and Movement Science, Institute of Sport Science, Johannes Gutenberg-University Mainz, Mainz, Germany; Corresponding author.Institute of Creative Media Technologies, Department of Media & Digital Technologies, St. Pölten University of Applied Sciences, St. Pölten, AustriaDepartment of Training and Movement Science, Institute of Sport Science, Johannes Gutenberg-University Mainz, Mainz, GermanyCenter for Digital Health & Social Innovation, Department of Health Sciences, St. Pölten University of Applied Sciences, St. Pölten, Austria; Institute of Health Sciences, St. Pölten University of Applied Sciences, St. Pölten, AustriaDepartment of Training and Movement Science, Institute of Sport Science, Johannes Gutenberg-University Mainz, Mainz, GermanyInstitute of Creative Media Technologies, Department of Media & Digital Technologies, St. Pölten University of Applied Sciences, St. Pölten, AustriaHuman 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.http://www.sciencedirect.com/science/article/pii/S2001037023002222Human gait recognitionBiomechanicsGround reaction forcesExplainable artificial intelligenceLayer-wise relevance propagationForce-based gait recognition |
| spellingShingle | Fabian Horst Djordje Slijepcevic Marvin Simak Brian Horsak Wolfgang Immanuel Schöllhorn Matthias Zeppelzauer Modeling biological individuality using machine learning: A study on human gait Computational and Structural Biotechnology Journal Human gait recognition Biomechanics Ground reaction forces Explainable artificial intelligence Layer-wise relevance propagation Force-based gait recognition |
| title | Modeling biological individuality using machine learning: A study on human gait |
| title_full | Modeling biological individuality using machine learning: A study on human gait |
| title_fullStr | Modeling biological individuality using machine learning: A study on human gait |
| title_full_unstemmed | Modeling biological individuality using machine learning: A study on human gait |
| title_short | Modeling biological individuality using machine learning: A study on human gait |
| title_sort | modeling biological individuality using machine learning a study on human gait |
| topic | Human gait recognition Biomechanics Ground reaction forces Explainable artificial intelligence Layer-wise relevance propagation Force-based gait recognition |
| url | http://www.sciencedirect.com/science/article/pii/S2001037023002222 |
| work_keys_str_mv | AT fabianhorst modelingbiologicalindividualityusingmachinelearningastudyonhumangait AT djordjeslijepcevic modelingbiologicalindividualityusingmachinelearningastudyonhumangait AT marvinsimak modelingbiologicalindividualityusingmachinelearningastudyonhumangait AT brianhorsak modelingbiologicalindividualityusingmachinelearningastudyonhumangait AT wolfgangimmanuelschollhorn modelingbiologicalindividualityusingmachinelearningastudyonhumangait AT matthiaszeppelzauer modelingbiologicalindividualityusingmachinelearningastudyonhumangait |