MhNet: Multi-scale spatio-temporal hierarchical network for real-time wearable fall risk assessment of the elderly

Shibin Wu; Jianlin Ou; Lin Shu; Guohua Hu; Zhen Song; Xiangmin Xu; Zhuoming Chen

doi:10.1016/j.compbiomed.2022.105355

MhNet: Multi-scale spatio-temporal hierarchical network for real-time wearable fall risk assessment of the elderly

Comput Biol Med. 2022 May:144:105355. doi: 10.1016/j.compbiomed.2022.105355. Epub 2022 Mar 8.

Authors

Shibin Wu¹, Jianlin Ou², Lin Shu³, Guohua Hu⁴, Zhen Song⁴, Xiangmin Xu⁵, Zhuoming Chen²

Affiliations

¹ School of Future Technology, South China University of Technology, Guangzhou, 511442, China; School of Electronic and Information Engineering, South China University of Technology, Guangzhou, 510641, China.
² The First Affiliated Hospital of Jinan University, Guangzhou, 510630, China.
³ School of Future Technology, South China University of Technology, Guangzhou, 511442, China; School of Electronic and Information Engineering, South China University of Technology, Guangzhou, 510641, China. Electronic address: shul@scut.edu.cn.
⁴ School of Electronic and Information Engineering, South China University of Technology, Guangzhou, 510641, China.
⁵ School of Future Technology, South China University of Technology, Guangzhou, 511442, China; School of Electronic and Information Engineering, South China University of Technology, Guangzhou, 510641, China; Institute of Modern Industrial Technology of SCUT in Zhongshan, Zhongshan, 528400, China.

PMID: 35286891
DOI: 10.1016/j.compbiomed.2022.105355

Abstract

Continuous fall risk assessment and real-time high falling risk warning are extremely necessary for the elderly, to protect their lives and ensure their quality of life. Wearable in-shoe pressure sensors have the potential to achieve these targets, due to their adequate wearing comfort. However, it is a great challenge to remove the individual differences of foot pressure data and identify the accurate fall risk from fewer gait cycles to realize real-time warning. We explored a hierarchical deep learning network named MhNet for real-time fall risk assessment, which utilized the advantages of two-layer network, to reach hierarchical tasks to reduce probability of misidentification of high fall risk subjects, by establishing a borderline category using the rehabilitation labels, and extracting multi-scale spatio-temporal features. It was trained by using a wearable plantar pressure dataset collected from 48 elderly subjects. This method could achieve a real time fall risk identification accuracy of 73.27% by using only 9 gaits, which was superior to traditional methods. Moreover, the sensitivity reached 76.72%, proving its strength in identifying high risk samples. MhNet might be a promising way in real-time fall risk assessment for the elderly in their daily activities.

Keywords: Cross-subject; Hierarchical network; Plantar pressure; Real-time fall risk assessment; Wearable.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Aged
Deep Learning*
Gait
Humans
Quality of Life
Risk Assessment
Wearable Electronic Devices*