Gait-based Frailty Assessment using Image Representation of IMU Signals and Deep CNN

被引:14
作者
Arshad, Muhammad Zeeshan [1 ]
Jung, Dawoon [1 ]
Park, Mina [1 ]
Shin, Hyungeun [2 ]
Kiml, Jinwook [1 ]
Mun, Kyung-Ryoul [1 ]
机构
[1] KIST, Ctr Artificial Intelligence, Seoul, South Korea
[2] Kyung Hee Univ, Grad Sch, Dept Biomed Sci & Technol, Seoul, South Korea
来源
2021 43RD ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY (EMBC) | 2021年
关键词
OLDER-ADULTS; DISABILITY; PEOPLE;
D O I
10.1109/EMBC46164.2021.9630976
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Frailty is a common and critical condition in elderly adults, which may lead to further deterioration of health. However, difficulties and complexities exist in traditional frailty assessments based on activity-related questionnaires. These can be overcome by monitoring the effects of frailty on the gait. In this paper, it is shown that by encoding gait signals as images, deep learning-based models can be utilized for the classification of gait type. Two deep learning models (a) SS-CNN, based on single stride input images, and (b) MS-CNN, based on 3 consecutive strides were proposed. It was shown that MS-CNN performs best with an accuracy of 85.1%, while SS-CNN achieved an accuracy of 77.3%. This is because MS-CNN can observe more features corresponding to stride-to-stride variations which is one of the key symptoms of frailty. Gait signals were encoded as images using STFT, CWT, and GAF. While the MS-CNN model using GAF images achieved the best overall accuracy and precision, CWT has a slightly better recall. This study demonstrates how image encoded gait data can be used to exploit the full potential of deep learning CNN models for the assessment of frailty.
引用
收藏
页码:1874 / 1879
页数:6
相关论文
共 25 条
[1]   Unstable disability and the fluctuations of frailty [J].
Campbell, AJ ;
Buchner, DM .
AGE AND AGEING, 1997, 26 (04) :315-318
[2]  
D. of Economic and S. Affairs, 2020, TECH REP
[3]   Comparison of 2 frailty indexes for prediction of falls, disability, fractures, and death in older women [J].
Ensrud, Kristine E. ;
Ewing, Susan K. ;
Taylor, Brent C. ;
Fink, Howard A. ;
Cawthon, Peggy M. ;
Stone, Katie L. ;
Hillier, Teresa A. ;
Cauley, Jane A. ;
Hochberg, Marc C. ;
Rodondi, Nicolas ;
Tracy, J. Kathleen ;
Cummings, Steven R. .
ARCHIVES OF INTERNAL MEDICINE, 2008, 168 (04) :382-389
[4]   Frailty in older adults: Evidence for a phenotype [J].
Fried, LP ;
Tangen, CM ;
Walston, J ;
Newman, AB ;
Hirsch, C ;
Gottdiener, J ;
Seeman, T ;
Tracy, R ;
Kop, WJ ;
Burke, G ;
McBurnie, MA .
JOURNALS OF GERONTOLOGY SERIES A-BIOLOGICAL SCIENCES AND MEDICAL SCIENCES, 2001, 56 (03) :M146-M156
[5]   The effect of social comparison information on the life satisfaction of frail older persons [J].
Frieswijk, N ;
Buunk, BP ;
Steverink, N ;
Slaets, JPJ .
PSYCHOLOGY AND AGING, 2004, 19 (01) :183-190
[6]  
Gabor D., 1946, J. Inst. Electr. Eng. Part I Gen, V93, P429, DOI [10.1049/ji-3-2.1946.0074, DOI 10.1049/JI-1.1947.0015, 10.1049/ji-3-2.1946.0076, DOI 10.1049/JI-3-2.1946.0074]
[7]   Two recruitment strategies for a clinical trial of physically frail community-living older persons [J].
Gill, TM ;
McGloin, JM ;
Gahbauer, EA ;
Shepard, DM ;
Bianco, LM .
JOURNAL OF THE AMERICAN GERIATRICS SOCIETY, 2001, 49 (08) :1039-1045
[8]   Wearables for independent living in older adults: Gait and falls [J].
Godfrey, A. .
MATURITAS, 2017, 100 :16-26
[9]   Frailty status can be accurately assessed using inertial sensors and the TUG test [J].
Greene, Barry R. ;
Doheny, Emer P. ;
O'Halloran, Aisling ;
Kenny, Rose Anne .
AGE AND AGEING, 2014, 43 (03) :406-411
[10]  
Grochenig K., 2001, Foundations of Time-Frequency Analysis, DOI DOI 10.1007/978-1-4612-0003-1