The University of Southampton
University of Southampton Institutional Repository

Estimates of load rates on the lower limb joints using smartphone accelerometers during physical activity

Estimates of load rates on the lower limb joints using smartphone accelerometers during physical activity
Estimates of load rates on the lower limb joints using smartphone accelerometers during physical activity
Although the causes and pathology of the progression of osteoarthritis are not entirely understood, an active lifestyle avoiding excessive load on the joints can control symptoms of osteoarthritis (e.g. joint pain and stiffness). The aim of this thesis was to develop, validate, and test an algorithm for estimating impact loading through the lower limbs using wearables (smartphones and smartwatches). The viscoelastic nature of articular cartilage means it is susceptible to high load rates, hence, the mean load rate magnitude was estimated from accelerometer recordings of wearables and used as a surrogate for estimating impact loading on the lower limb joints. The validity of the mean load rate magnitude was assessed against the gold standard equipment, the force plate (R2 = 0.77). Further, the mean load rate magnitude was used as a feature in the classification of everyday activities with support vector machine classifiers with an accuracy of 80%. An app was then developed which monitored mean load rate magnitude using Markov chain Monte Carlo methods for testing the reliability of monitoring over a period of seven days. The accumulated mean load rate magnitude was used to estimate the error, êsmartphone = 2.66%, for seven-day recordings. Finally, a function to score pain was added to the final version of the app, termed OApp™. A single case study assessed the ability of OApp™ to compare osteoarthritis-related pain to mean load rate magnitude with a low positive correlation of r = 0.38. To conclude, this thesis developed, assessed the validation, and tested a load rate magnitude algorithm, which estimated load rate on the lower limb joints with the accelerometer sensors of wearables. These results form the basis for further research to develop a clinical tool for monitoring load rate and supporting patients to maintain an active lifestyle by avoiding excessive load on their lower limb joints.
University of Southampton
Nazirizadeh, Susan
01e17b52-1df2-4cfa-a22d-1722e8f99635
Nazirizadeh, Susan
01e17b52-1df2-4cfa-a22d-1722e8f99635
Stokes, Maria
71730503-70ce-4e67-b7ea-a3e54579717f
Forrester, Alexander
176bf191-3fc2-46b4-80e0-9d9a0cd7a572
Arden, Nigel
23af958d-835c-4d79-be54-4bbe4c68077f

Nazirizadeh, Susan (2018) Estimates of load rates on the lower limb joints using smartphone accelerometers during physical activity. University of Southampton, Doctoral Thesis, 233pp.

Record type: Thesis (Doctoral)

Abstract

Although the causes and pathology of the progression of osteoarthritis are not entirely understood, an active lifestyle avoiding excessive load on the joints can control symptoms of osteoarthritis (e.g. joint pain and stiffness). The aim of this thesis was to develop, validate, and test an algorithm for estimating impact loading through the lower limbs using wearables (smartphones and smartwatches). The viscoelastic nature of articular cartilage means it is susceptible to high load rates, hence, the mean load rate magnitude was estimated from accelerometer recordings of wearables and used as a surrogate for estimating impact loading on the lower limb joints. The validity of the mean load rate magnitude was assessed against the gold standard equipment, the force plate (R2 = 0.77). Further, the mean load rate magnitude was used as a feature in the classification of everyday activities with support vector machine classifiers with an accuracy of 80%. An app was then developed which monitored mean load rate magnitude using Markov chain Monte Carlo methods for testing the reliability of monitoring over a period of seven days. The accumulated mean load rate magnitude was used to estimate the error, êsmartphone = 2.66%, for seven-day recordings. Finally, a function to score pain was added to the final version of the app, termed OApp™. A single case study assessed the ability of OApp™ to compare osteoarthritis-related pain to mean load rate magnitude with a low positive correlation of r = 0.38. To conclude, this thesis developed, assessed the validation, and tested a load rate magnitude algorithm, which estimated load rate on the lower limb joints with the accelerometer sensors of wearables. These results form the basis for further research to develop a clinical tool for monitoring load rate and supporting patients to maintain an active lifestyle by avoiding excessive load on their lower limb joints.

Text
Final_thesis - Version of Record
Available under License University of Southampton Thesis Licence.
Download (19MB)

More information

Published date: 26 April 2018

Identifiers

Local EPrints ID: 422272
URI: http://eprints.soton.ac.uk/id/eprint/422272
PURE UUID: d136de75-bd71-4a2c-91e6-cae78cf273e2
ORCID for Maria Stokes: ORCID iD orcid.org/0000-0002-4204-0890

Catalogue record

Date deposited: 20 Jul 2018 16:30
Last modified: 12 Dec 2021 03:21

Export record

Contributors

Author: Susan Nazirizadeh
Thesis advisor: Maria Stokes ORCID iD
Thesis advisor: Alexander Forrester
Thesis advisor: Nigel Arden

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×