Prediction of knee adduction moment using innovative instrumented insole and deep learning neural networks in healthy female individuals

Samantha J Snyder; Edward Chu; Jumyung Um; Yun Jung Heo; Ross H Miller; Jae Kun Shim

doi:10.1016/j.knee.2022.12.007

Prediction of knee adduction moment using innovative instrumented insole and deep learning neural networks in healthy female individuals

Knee. 2023 Mar:41:115-123. doi: 10.1016/j.knee.2022.12.007. Epub 2023 Jan 17.

Authors

Samantha J Snyder¹, Edward Chu², Jumyung Um³, Yun Jung Heo⁴, Ross H Miller⁵, Jae Kun Shim⁶

Affiliations

¹ Department of Kinesiology, University of Maryland, College Park, MD, USA. Electronic address: snyder36@terpmail.umd.edu.
² Department of Kinesiology, University of Maryland, College Park, MD, USA. Electronic address: edchux@umd.edu.
³ Department of Industrial & Management Systems Engineering, Kyung Hee University, Yongin-Si, Gyeonggi-do, South Korea. Electronic address: jayum@khu.ac.kr.
⁴ Department of Mechanical Engineering, Kyung Hee University, Yongin-Si, Gyeonggi-do, South Korea; Integrated Education Institute for Frontier Science & Technology, Kyung Hee University, Gyeonggi-do 17104, South Korea. Electronic address: yunjheo@khu.ac.kr.
⁵ Department of Kinesiology, University of Maryland, College Park, MD, USA; Neuroscience and Cognitive Science Program, University of Maryland, College Park, MD, USA. Electronic address: rosshm@umd.edu.
⁶ Department of Kinesiology, University of Maryland, College Park, MD, USA; Department of Mechanical Engineering, Kyung Hee University, Yongin-Si, Gyeonggi-do, South Korea; Neuroscience and Cognitive Science Program, University of Maryland, College Park, MD, USA; Fischell Department of Bioengineering, University of Maryland, College Park, MD, USA. Electronic address: jkshim@umd.edu.

PMID: 36657209
DOI: 10.1016/j.knee.2022.12.007

Abstract

Background: The knee adduction moment, a biomechanical risk factor of knee osteoarthritis, is typically measured in a gait laboratory with expensive equipment and inverse dynamics modeling software. We aimed to develop a framework for a portable knee adduction moment estimation for healthy female individuals using deep learning neural networks and custom instrumented insole and evaluated its accuracy compared to the standard inverse dynamics approach.

Methods: Feed-forward, convolutional, and recurrent neural networks were applied to the data extracted from five piezo-resistive force sensors attached to the insole of a shoe.

Results: All models predicted knee adduction moment variables during walking with high correlation coefficients, r > 0.72, and low root mean squared errors (RMSE), ranging from 0.5% to 1.2%. The convolutional neural network is the most accurate predictor of average knee adduction moment (r = 0.96; RMSE = 0.5%) followed by the recurrent and feed-forward neural networks.

Conclusion: These findings and the methods presented in the current study are expected to facilitate a cost-effective clinical analysis of knee adduction moment for healthy female individuals and to facilitate future research on prediction of other biomechanical risk factors using similar methods.

Keywords: Knee adduction moment; Knee osteoarthritis; Machine learning; Neural network.

MeSH terms

Biomechanical Phenomena
Deep Learning*
Female
Gait
Humans
Knee Joint
Neural Networks, Computer
Osteoarthritis, Knee*
Shoes
Walking