Explaining the differences of gait patterns between high and low-mileage runners with machine learning

Datao Xu, Wenjing Quan, Huiyu Zhou, Dong Sun, Julien S. Baker*, Yaodong Gu*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

Running gait patterns have implications for revealing the causes of injuries between higher-mileage runners and low-mileage runners. However, there is limited research on the possible relationships between running gait patterns and weekly running mileages. In recent years, machine learning algorithms have been used for pattern recognition and classification of gait features to emphasize the uniqueness of gait patterns. However, they all have a representative problem of being a black box that often lacks the interpretability of the predicted results of the classifier. Therefore, this study was conducted using a Deep Neural Network (DNN) model and Layer-wise Relevance Propagation (LRP) technology to investigate the differences in running gait patterns between higher-mileage runners and low-mileage runners. It was found that the ankle and knee provide considerable information to recognize gait features, especially in the sagittal and transverse planes. This may be the reason why high-mileage and low-mileage runners have different injury patterns due to their different gait patterns. The early stages of stance are very important in gait pattern recognition because the pattern contains effective information related to gait. The findings of the study noted that LRP completes a feasible interpretation of the predicted results of the model, thus providing more interesting insights and more effective information for analyzing gait patterns.

Original languageEnglish
Article number2981
Number of pages12
JournalScientific Reports
Volume12
Issue number1
DOIs
Publication statusPublished - 22 Feb 2022

Scopus Subject Areas

  • General

Fingerprint

Dive into the research topics of 'Explaining the differences of gait patterns between high and low-mileage runners with machine learning'. Together they form a unique fingerprint.

Cite this