Explaining the unique nature of individual gait patterns with deep learning

Fabian Horst, Sebastian Lapuschkin, Wojciech Samek, Klaus Muller, Wolfgang I. Schöllhorn

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Machine learning (ML) techniques such as (deep) artificial neural networks (DNN) are solving very successfully a plethora of tasks and provide new predictive models for complex physical, chemical, biological and social systems. However, in most cases this comes with the disadvantage of acting as a black box, rarely providing information about what made them arrive at a particular prediction. This black box aspect of ML techniques can be problematic especially in medical diagnoses, so far hampering a clinical acceptance. The present paper studies the uniqueness of individual gait patterns in clinical biomechanics using DNNs. By attributing portions of the model predictions back to the input variables (ground reaction forces and full-body joint angles), the Layer-Wise Relevance Propagation (LRP) technique reliably demonstrates which variables at what time windows of the gait cycle are most relevant for the characterisation of gait patterns from a certain individual. By measuring the time-resolved contribution of each input variable to the prediction of ML techniques such as DNNs, our method describes the first general framework that enables to understand and interpret non-linear ML methods in (biomechanical) gait analysis and thereby supplies a powerful tool for analysis, diagnosis and treatment of human gait.

Original languageEnglish
Article number2391
JournalScientific Reports
Volume9
Issue number1
DOIs
Publication statusPublished - 2019 Dec 1

Fingerprint

Gait
Learning
Biomechanical Phenomena
Joints
Machine Learning

ASJC Scopus subject areas

  • General

Cite this

Horst, F., Lapuschkin, S., Samek, W., Muller, K., & Schöllhorn, W. I. (2019). Explaining the unique nature of individual gait patterns with deep learning. Scientific Reports, 9(1), [2391]. https://doi.org/10.1038/s41598-019-38748-8

Explaining the unique nature of individual gait patterns with deep learning. / Horst, Fabian; Lapuschkin, Sebastian; Samek, Wojciech; Muller, Klaus; Schöllhorn, Wolfgang I.

In: Scientific Reports, Vol. 9, No. 1, 2391, 01.12.2019.

Research output: Contribution to journalArticle

Horst, F, Lapuschkin, S, Samek, W, Muller, K & Schöllhorn, WI 2019, 'Explaining the unique nature of individual gait patterns with deep learning', Scientific Reports, vol. 9, no. 1, 2391. https://doi.org/10.1038/s41598-019-38748-8
Horst, Fabian ; Lapuschkin, Sebastian ; Samek, Wojciech ; Muller, Klaus ; Schöllhorn, Wolfgang I. / Explaining the unique nature of individual gait patterns with deep learning. In: Scientific Reports. 2019 ; Vol. 9, No. 1.
@article{19467bc316414bb1beb432fff06a9049,
title = "Explaining the unique nature of individual gait patterns with deep learning",
abstract = "Machine learning (ML) techniques such as (deep) artificial neural networks (DNN) are solving very successfully a plethora of tasks and provide new predictive models for complex physical, chemical, biological and social systems. However, in most cases this comes with the disadvantage of acting as a black box, rarely providing information about what made them arrive at a particular prediction. This black box aspect of ML techniques can be problematic especially in medical diagnoses, so far hampering a clinical acceptance. The present paper studies the uniqueness of individual gait patterns in clinical biomechanics using DNNs. By attributing portions of the model predictions back to the input variables (ground reaction forces and full-body joint angles), the Layer-Wise Relevance Propagation (LRP) technique reliably demonstrates which variables at what time windows of the gait cycle are most relevant for the characterisation of gait patterns from a certain individual. By measuring the time-resolved contribution of each input variable to the prediction of ML techniques such as DNNs, our method describes the first general framework that enables to understand and interpret non-linear ML methods in (biomechanical) gait analysis and thereby supplies a powerful tool for analysis, diagnosis and treatment of human gait.",
author = "Fabian Horst and Sebastian Lapuschkin and Wojciech Samek and Klaus Muller and Sch{\"o}llhorn, {Wolfgang I.}",
year = "2019",
month = "12",
day = "1",
doi = "10.1038/s41598-019-38748-8",
language = "English",
volume = "9",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Explaining the unique nature of individual gait patterns with deep learning

AU - Horst, Fabian

AU - Lapuschkin, Sebastian

AU - Samek, Wojciech

AU - Muller, Klaus

AU - Schöllhorn, Wolfgang I.

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Machine learning (ML) techniques such as (deep) artificial neural networks (DNN) are solving very successfully a plethora of tasks and provide new predictive models for complex physical, chemical, biological and social systems. However, in most cases this comes with the disadvantage of acting as a black box, rarely providing information about what made them arrive at a particular prediction. This black box aspect of ML techniques can be problematic especially in medical diagnoses, so far hampering a clinical acceptance. The present paper studies the uniqueness of individual gait patterns in clinical biomechanics using DNNs. By attributing portions of the model predictions back to the input variables (ground reaction forces and full-body joint angles), the Layer-Wise Relevance Propagation (LRP) technique reliably demonstrates which variables at what time windows of the gait cycle are most relevant for the characterisation of gait patterns from a certain individual. By measuring the time-resolved contribution of each input variable to the prediction of ML techniques such as DNNs, our method describes the first general framework that enables to understand and interpret non-linear ML methods in (biomechanical) gait analysis and thereby supplies a powerful tool for analysis, diagnosis and treatment of human gait.

AB - Machine learning (ML) techniques such as (deep) artificial neural networks (DNN) are solving very successfully a plethora of tasks and provide new predictive models for complex physical, chemical, biological and social systems. However, in most cases this comes with the disadvantage of acting as a black box, rarely providing information about what made them arrive at a particular prediction. This black box aspect of ML techniques can be problematic especially in medical diagnoses, so far hampering a clinical acceptance. The present paper studies the uniqueness of individual gait patterns in clinical biomechanics using DNNs. By attributing portions of the model predictions back to the input variables (ground reaction forces and full-body joint angles), the Layer-Wise Relevance Propagation (LRP) technique reliably demonstrates which variables at what time windows of the gait cycle are most relevant for the characterisation of gait patterns from a certain individual. By measuring the time-resolved contribution of each input variable to the prediction of ML techniques such as DNNs, our method describes the first general framework that enables to understand and interpret non-linear ML methods in (biomechanical) gait analysis and thereby supplies a powerful tool for analysis, diagnosis and treatment of human gait.

UR - http://www.scopus.com/inward/record.url?scp=85061838354&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061838354&partnerID=8YFLogxK

U2 - 10.1038/s41598-019-38748-8

DO - 10.1038/s41598-019-38748-8

M3 - Article

C2 - 30787319

AN - SCOPUS:85061838354

VL - 9

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 2391

ER -