Biomechanical monitoring and machine learning for the detection of lying postures
Biomechanical monitoring and machine learning for the detection of lying postures
Background: pressure mapping technology has been adapted to monitor over prolonged periods to evaluate pressure ulcer risk in individuals during extended lying postures. However, temporal pressure distribution signals are not currently used to identify posture or mobility. The present study was designed to examine the potential of an automated approach for the detection of a range of static
lying postures and corresponding transitions between postures.
Methods: healthy subjects (n=19) adopted a range of sagittal and lateral lying postures. Parameters reflecting both the interactions at the support surface and body movements were continuously monitored. Subsequently, the derivative of each signal was examined to identify transitions between postures. Three machine learning algorithms, namely Naïve-Bayes, k-Nearest Neighbors and Support Vector Machine classifiers, were assessed to predict a range of static postures, established with a training model (n=9) and validated with new input from test data (n=10).
Findings: results showed that the derivative signals provided a means to detect transitions between postures, with actimetry providing the most distinct signal perturbations. The accuracy in predicting the range of postures from new test data ranged between 82%-100%, 70%-98% and 69%-100% for Naïve-Bayes, k-Nearest Neighbors and Support Vector Machine classifiers, respectively.
Interpretation: the present study demonstrated that detection of both static postures and their corresponding transitions was achieved by combining machine learning algorithms with robust parameters from two monitoring systems. This approach has the potential to provide reliable indicators of posture and mobility, to support personalized pressure ulcer prevention strategies.
Actimetry systems, Continuous pressure monitoring, Machine learning, Postures detection, Pressure ulcers
Caggiari, Silvia
58f49054-6ca6-429b-b499-49b93357e5ba
Worsley, Peter R.
6d33aee3-ef43-468d-aef6-86d190de6756
Payan, Yohan
55fc7e8b-b78d-4b0c-97f1-1846b8b86e77
Bucki, Marek
86d62178-50ca-424b-a13c-6cbe5440b06c
Bader, Dan L.
9884d4f6-2607-4d48-bf0c-62bdcc0d1dbf
1 December 2020
Caggiari, Silvia
58f49054-6ca6-429b-b499-49b93357e5ba
Worsley, Peter R.
6d33aee3-ef43-468d-aef6-86d190de6756
Payan, Yohan
55fc7e8b-b78d-4b0c-97f1-1846b8b86e77
Bucki, Marek
86d62178-50ca-424b-a13c-6cbe5440b06c
Bader, Dan L.
9884d4f6-2607-4d48-bf0c-62bdcc0d1dbf
Caggiari, Silvia, Worsley, Peter R., Payan, Yohan, Bucki, Marek and Bader, Dan L.
(2020)
Biomechanical monitoring and machine learning for the detection of lying postures.
Clinical Biomechanics, 80, [105181].
(doi:10.1016/j.clinbiomech.2020.105181).
Abstract
Background: pressure mapping technology has been adapted to monitor over prolonged periods to evaluate pressure ulcer risk in individuals during extended lying postures. However, temporal pressure distribution signals are not currently used to identify posture or mobility. The present study was designed to examine the potential of an automated approach for the detection of a range of static
lying postures and corresponding transitions between postures.
Methods: healthy subjects (n=19) adopted a range of sagittal and lateral lying postures. Parameters reflecting both the interactions at the support surface and body movements were continuously monitored. Subsequently, the derivative of each signal was examined to identify transitions between postures. Three machine learning algorithms, namely Naïve-Bayes, k-Nearest Neighbors and Support Vector Machine classifiers, were assessed to predict a range of static postures, established with a training model (n=9) and validated with new input from test data (n=10).
Findings: results showed that the derivative signals provided a means to detect transitions between postures, with actimetry providing the most distinct signal perturbations. The accuracy in predicting the range of postures from new test data ranged between 82%-100%, 70%-98% and 69%-100% for Naïve-Bayes, k-Nearest Neighbors and Support Vector Machine classifiers, respectively.
Interpretation: the present study demonstrated that detection of both static postures and their corresponding transitions was achieved by combining machine learning algorithms with robust parameters from two monitoring systems. This approach has the potential to provide reliable indicators of posture and mobility, to support personalized pressure ulcer prevention strategies.
Text
Biomechanical monitoring and machine learning for the detection of lying postures
- Accepted Manuscript
More information
Accepted/In Press date: 16 September 2020
e-pub ahead of print date: 20 September 2020
Published date: 1 December 2020
Keywords:
Actimetry systems, Continuous pressure monitoring, Machine learning, Postures detection, Pressure ulcers
Identifiers
Local EPrints ID: 444508
URI: http://eprints.soton.ac.uk/id/eprint/444508
ISSN: 0268-0033
PURE UUID: 1f9a71f9-a5f2-4593-8809-78bf082edb64
Catalogue record
Date deposited: 22 Oct 2020 16:31
Last modified: 18 Mar 2024 05:26
Export record
Altmetrics
Contributors
Author:
Yohan Payan
Author:
Marek Bucki
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
