The Library
Capturing accelerometer outputs in healthy volunteers under normal and simulated-pathological conditions using ML classifiers*
Tools
Filippou, V., Redmond, A.C., Bennion, J., Backhouse, Michael and Wong, D. (2020) Capturing accelerometer outputs in healthy volunteers under normal and simulated-pathological conditions using ML classifiers*. In: 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, Canada, 20-24 Jul 2020. Published in: 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) pp. 4604-4607. ISBN 9781728119915. doi:10.1109/embc44109.2020.9176201
Research output not available from this repository.
Request-a-Copy directly from author or use local Library Get it For Me service.
Official URL: http://dx.doi.org/10.1109/embc44109.2020.9176201
Abstract
Wearable devices offer a possible solution for acquiring objective measurements of physical activity. Most current algorithms are derived using data from healthy volunteers. It is unclear whether such algorithms are suitable in specific clinical scenarios, such as when an individual has altered gait. We hypothesized that algorithms trained on healthy population will result in less accurate results when tested in individuals with altered gait. We further hypothesized that algorithms trained on simulated-pathological gait would prove better at classifying abnormal activity. We studied healthy volunteers to assess whether activity classification accuracy differed for those with healthy and simulated-pathological conditions. Healthy participants (n=30) were recruited from the University of Leeds to perform nine predefined activities under healthy and simulated-pathological conditions. Activities were captured using a wrist-worn MOX accelerometer (Maastricht Instruments, NL). Data were analyzed based on the Activity-Recognition-Chain process. We trained a Neural-Network, Random-Forests, k-Nearest-Neighbors (k-NN), Support-Vector-Machines (SVM) and Naive Bayes models to classify activity. Algorithms were trained four times; once with `healthy' data, and once with `simulated-pathological data' for each of activity-type and activity-task classification. In activity-type instances, the SVM provided the best results; the accuracy was 98.4% when the algorithm was trained and then tested with unseen data from the same group of healthy individuals. Accuracy dropped to 52.8% when tested on simulated-pathological data. When the model was retrained with simulated-pathological data, prediction accuracy for the corresponding test set was 96.7%. Algorithms developed on healthy data are less accurate for pathological conditions. When evaluating pathological conditions, classifier algorithms developed using data from a target sub-population can restore accuracy to above 95%.
Item Type: | Conference Item (Paper) | ||||
---|---|---|---|---|---|
Divisions: | Faculty of Science, Engineering and Medicine > Medicine > Warwick Medical School > Clinical Trials Unit Faculty of Science, Engineering and Medicine > Medicine > Warwick Medical School |
||||
Journal or Publication Title: | 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) | ||||
Publisher: | IEEE | ||||
ISBN: | 9781728119915 | ||||
Book Title: | 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) | ||||
Official Date: | August 2020 | ||||
Dates: |
|
||||
Page Range: | pp. 4604-4607 | ||||
DOI: | 10.1109/embc44109.2020.9176201 | ||||
Publication Status: | Published | ||||
Access rights to Published version: | Open Access (Creative Commons) | ||||
Conference Paper Type: | Paper | ||||
Title of Event: | 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) | ||||
Type of Event: | Conference | ||||
Location of Event: | Montreal, Canada | ||||
Date(s) of Event: | 20-24 Jul 2020 | ||||
Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |