Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Nov 10;21(22):7458.
doi: 10.3390/s21227458.

A Machine Learning Classification Model for Monitoring the Daily Physical Behaviour of Lower-Limb Amputees

Benjamin Griffiths  1 , Laura Diment  2 , Malcolm H Granat  1
Affiliations

A Machine Learning Classification Model for Monitoring the Daily Physical Behaviour of Lower-Limb Amputees

Benjamin Griffiths et al. Sensors (Basel). .

Abstract

There are currently limited data on how prosthetic devices are used to support lower-limb prosthesis users in their free-living environment. Possessing the ability to monitor a patient's physical behaviour while using these devices would enhance our understanding of the impact of different prosthetic products. The current approaches for monitoring human physical behaviour use a single thigh or wrist-worn accelerometer, but in a lower-limb amputee population, we have the unique opportunity to embed a device within the prosthesis, eliminating compliance issues. This study aimed to develop a model capable of accurately classifying postures (sitting, standing, stepping, and lying) by using data from a single shank-worn accelerometer. Free-living posture data were collected from 14 anatomically intact participants and one amputee over three days. A thigh worn activity monitor collected labelled posture data, while a shank worn accelerometer collected 3-axis acceleration data. Postures and the corresponding shank accelerations were extracted in window lengths of 5-180 s and used to train several machine learning classifiers which were assessed by using stratified cross-validation. A random forest classifier with a 15 s window length provided the highest classification accuracy of 93% weighted average F-score and between 88 and 98% classification accuracy across all four posture classes, which is the best performance achieved to date with a shank-worn device. The results of this study show that data from a single shank-worn accelerometer with a machine learning classification model can be used to accurately identify postures that make up an individual's daily physical behaviour. This opens up the possibility of embedding an accelerometer-based activity monitor into the shank component of a prosthesis to capture physical behaviour information in both above and below-knee amputees. The models and software used in this study have been made open source in order to overcome the current restrictions of applying activity monitoring methods to lower-limb prosthesis users.

Keywords: accelerometer; activity monitor; classification; lower-limb amputee; machine learning; physical behaviour monitoring.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; or in the decision to publish the results.

Figures

Figure 1
Figure 1
Experiment setup for activPAL PAL 3 in both positions: (a) thigh worn PAL3 for measuring postures; (b) shank worn PAL3 for measuring 3-axis accelerations.
Figure 2
Figure 2
F-scores for each algorithm across all window lengths.
Figure 3
Figure 3
Confusion matrices for each classifier utilizing a 15 s window length: (a) KNN, (b) LDA, (c) SVM, (d) RF, (e) ET, (f) LR, (g) NB, and (h) QDA.
Figure 3
Figure 3
Confusion matrices for each classifier utilizing a 15 s window length: (a) KNN, (b) LDA, (c) SVM, (d) RF, (e) ET, (f) LR, (g) NB, and (h) QDA.
Figure 4
Figure 4
Confusion matrices for the RF classifier across the different window lengths: (a) 5, (b) 15, (c) 30, (d) 60, and (e) 120, (f) 180.
Figure 4
Figure 4
Confusion matrices for the RF classifier across the different window lengths: (a) 5, (b) 15, (c) 30, (d) 60, and (e) 120, (f) 180.
See this image and copyright information in PMC

References

    1. World Health Organisation . WHO Standards for Prosthetics and Orthotics. WHO; Geneva, Switzerland: 2017.
    1. Albert M.V., McCarthy C., Valentin J., Herrmann M., Kording K., Jayaraman A. Monitoring Functional Capability of Individuals with Lower Limb Amputations Using Mobile Phones. PLoS ONE. 2013;8:e65340. doi: 10.1371/journal.pone.0065340. - DOI - PMC - PubMed
    1. Chadwell A., Diment L., Mico-Amigo M., Ramirez D.Z.M., Dickinson A., Granat M., Kenney L., Kheng S., Sobuh M., Ssekitoleko R., et al. Technology for monitoring everyday prosthesis use: A systematic review. J. NeuroEng. Rehabil. 2020;17:26. doi: 10.1186/s12984-020-00711-4. - DOI - PMC - PubMed
    1. Salih S.A., Peel N.M., Burgess K. Monitoring activity of inpatient lower limb prosthetic users in rehabilitation using accelerometry: Validation study. J. Rehabil. Assist. Technol. Eng. 2016;3:2055668316642387. doi: 10.1177/2055668316642387. - DOI - PMC - PubMed
    1. Stepien J.M., Cavenett S., Taylor L., Crotty M. Activity levels among lower-limb amputees: Self-report versus step activity monitor. Arch. Phys. Med. Rehabil. 2007;88:896–900. doi: 10.1016/j.apmr.2007.03.016. - DOI - PubMed