Smartphone- and Smartwatch-Based Remote Characterisation of Ambulation in Multiple Sclerosis During the Two-Minute Walk Test. Creagh, A. P., Simillion, C., Bourke, A. K., Scotland, A., Lipsmeier, F., Bernasconi, C., Beek, J. v., Baker, M., Gossens, C., Lindemann, M., & Vos, M. D. IEEE Journal of Biomedical and Health Informatics, 25(3):838–849, March, 2021. Conference Name: IEEE Journal of Biomedical and Health Informaticsdoi abstract bibtex Leveraging consumer technology such as smartphone and smartwatch devices to objectively assess people with multiple sclerosis (PwMS) remotely could capture unique aspects of disease progression. This study explores the feasibility of assessing PwMS and Healthy Control's (HC) physical function by characterising gaitrelated features, which can be modelled using machine learning (ML) techniques to correctly distinguish subgroups of PwMS from healthy controls. A total of 97 subjects (24 HC subjects, 52 mildly disabled (PwMSmild, EDSS [0-3]) and 21 moderately disabled (PwMSmod, EDSS [3.5- 5.5]) contributed data which was recorded from a TwoMinute Walk Test (2MWT) performed out-of-clinic and daily over a 24-week period. Signal-based features relating to movement were extracted from sensors in smartphone and smartwatch devices. A large number of features (n = 156) showed fair-to-strong (R \textgreater 0.3) correlations with clinical outcomes. LASSO feature selection was applied to select and rank subsets of features used for dichotomous classification between subject groups, which were compared using Logistic Regression (LR), Support Vector Machines (SVM) and Random Forest (RF) models. Classifications of subject types were compared using data obtained from smartphone, smartwatch and the fusion of features from both devices. Models built on smartphone features alone achieved the highest classification performance, indicating that accurate and remote measurement of the ambulatory characteristics of HC and PwMS can be achieved with only one device. It was observed however that smartphonebased performance was affected by inconsistent placement location (running belt versus pocket). Results show that PwMSmod could be distinguished from HC subjects (Acc. 82.2 ± 2.9%, Sen. 80.1 ± 3.9%, Spec. 87.2 ± 4.2%, F1 84.3 ± 3.8), and PwMSmild (Acc. 82.3 ± 1.9%, Sen. 71.6 ± 4.2%, Spec. 87.0 ± 3.2%, F1 75.1 ± 2.2) using an SVM classifier with a Radial Basis Function (RBF). PwMSmild were shown to exhibit HC-like behaviour and were thus less distinguishable from HC (Acc. 66.4 ± 4.5%, Sen. 67.5 ± 5.7%, Spec. 60.3 ± 6.7%, F1 58.6 ± 5.8). Finally, it was observed that subjects in this study demonstrated low intraand high inter-subject variability which was representative of subject-specific gait characteristics.
@article{creagh_smartphone-_2021,
title = {Smartphone- and {Smartwatch}-{Based} {Remote} {Characterisation} of {Ambulation} in {Multiple} {Sclerosis} {During} the {Two}-{Minute} {Walk} {Test}},
volume = {25},
issn = {2168-2208},
doi = {10.1109/JBHI.2020.2998187},
abstract = {Leveraging consumer technology such as smartphone and smartwatch devices to objectively assess people with multiple sclerosis (PwMS) remotely could capture unique aspects of disease progression. This study explores the feasibility of assessing PwMS and Healthy Control's (HC) physical function by characterising gaitrelated features, which can be modelled using machine learning (ML) techniques to correctly distinguish subgroups of PwMS from healthy controls. A total of 97 subjects (24 HC subjects, 52 mildly disabled (PwMSmild, EDSS [0-3]) and 21 moderately disabled (PwMSmod, EDSS [3.5- 5.5]) contributed data which was recorded from a TwoMinute Walk Test (2MWT) performed out-of-clinic and daily over a 24-week period. Signal-based features relating to movement were extracted from sensors in smartphone and smartwatch devices. A large number of features (n = 156) showed fair-to-strong (R {\textgreater} 0.3) correlations with clinical outcomes. LASSO feature selection was applied to select and rank subsets of features used for dichotomous classification between subject groups, which were compared using Logistic Regression (LR), Support Vector Machines (SVM) and Random Forest (RF) models. Classifications of subject types were compared using data obtained from smartphone, smartwatch and the fusion of features from both devices. Models built on smartphone features alone achieved the highest classification performance, indicating that accurate and remote measurement of the ambulatory characteristics of HC and PwMS can be achieved with only one device. It was observed however that smartphonebased performance was affected by inconsistent placement location (running belt versus pocket). Results show that PwMSmod could be distinguished from HC subjects (Acc. 82.2 ± 2.9\%, Sen. 80.1 ± 3.9\%, Spec. 87.2 ± 4.2\%, F1 84.3 ± 3.8), and PwMSmild (Acc. 82.3 ± 1.9\%, Sen. 71.6 ± 4.2\%, Spec. 87.0 ± 3.2\%, F1 75.1 ± 2.2) using an SVM classifier with a Radial Basis Function (RBF). PwMSmild were shown to exhibit HC-like behaviour and were thus less distinguishable from HC (Acc. 66.4 ± 4.5\%, Sen. 67.5 ± 5.7\%, Spec. 60.3 ± 6.7\%, F1 58.6 ± 5.8). Finally, it was observed that subjects in this study demonstrated low intraand high inter-subject variability which was representative of subject-specific gait characteristics.},
number = {3},
journal = {IEEE Journal of Biomedical and Health Informatics},
author = {Creagh, A. P. and Simillion, C. and Bourke, A. K. and Scotland, A. and Lipsmeier, F. and Bernasconi, C. and Beek, J. van and Baker, M. and Gossens, C. and Lindemann, M. and Vos, M. De},
month = mar,
year = {2021},
note = {Conference Name: IEEE Journal of Biomedical and Health Informatics},
keywords = {Entropy, Feature extraction, Gait, Legged locomotion, ML, Machine Learning, Multiple sclerosis, Pulse width modulation, Sensors, multiple sclerosis, sensor-based measure, smartphone, smartwatch},
pages = {838--849},
}
Downloads: 0
{"_id":"kKpEwDRFj8WWveeWw","bibbaseid":"creagh-simillion-bourke-scotland-lipsmeier-bernasconi-beek-baker-etal-smartphoneandsmartwatchbasedremotecharacterisationofambulationinmultiplesclerosisduringthetwominutewalktest-2021","author_short":["Creagh, A. P.","Simillion, C.","Bourke, A. K.","Scotland, A.","Lipsmeier, F.","Bernasconi, C.","Beek, J. v.","Baker, M.","Gossens, C.","Lindemann, M.","Vos, M. D."],"bibdata":{"bibtype":"article","type":"article","title":"Smartphone- and Smartwatch-Based Remote Characterisation of Ambulation in Multiple Sclerosis During the Two-Minute Walk Test","volume":"25","issn":"2168-2208","doi":"10.1109/JBHI.2020.2998187","abstract":"Leveraging consumer technology such as smartphone and smartwatch devices to objectively assess people with multiple sclerosis (PwMS) remotely could capture unique aspects of disease progression. This study explores the feasibility of assessing PwMS and Healthy Control's (HC) physical function by characterising gaitrelated features, which can be modelled using machine learning (ML) techniques to correctly distinguish subgroups of PwMS from healthy controls. A total of 97 subjects (24 HC subjects, 52 mildly disabled (PwMSmild, EDSS [0-3]) and 21 moderately disabled (PwMSmod, EDSS [3.5- 5.5]) contributed data which was recorded from a TwoMinute Walk Test (2MWT) performed out-of-clinic and daily over a 24-week period. Signal-based features relating to movement were extracted from sensors in smartphone and smartwatch devices. A large number of features (n = 156) showed fair-to-strong (R \\textgreater 0.3) correlations with clinical outcomes. LASSO feature selection was applied to select and rank subsets of features used for dichotomous classification between subject groups, which were compared using Logistic Regression (LR), Support Vector Machines (SVM) and Random Forest (RF) models. Classifications of subject types were compared using data obtained from smartphone, smartwatch and the fusion of features from both devices. Models built on smartphone features alone achieved the highest classification performance, indicating that accurate and remote measurement of the ambulatory characteristics of HC and PwMS can be achieved with only one device. It was observed however that smartphonebased performance was affected by inconsistent placement location (running belt versus pocket). Results show that PwMSmod could be distinguished from HC subjects (Acc. 82.2 ± 2.9%, Sen. 80.1 ± 3.9%, Spec. 87.2 ± 4.2%, F1 84.3 ± 3.8), and PwMSmild (Acc. 82.3 ± 1.9%, Sen. 71.6 ± 4.2%, Spec. 87.0 ± 3.2%, F1 75.1 ± 2.2) using an SVM classifier with a Radial Basis Function (RBF). PwMSmild were shown to exhibit HC-like behaviour and were thus less distinguishable from HC (Acc. 66.4 ± 4.5%, Sen. 67.5 ± 5.7%, Spec. 60.3 ± 6.7%, F1 58.6 ± 5.8). Finally, it was observed that subjects in this study demonstrated low intraand high inter-subject variability which was representative of subject-specific gait characteristics.","number":"3","journal":"IEEE Journal of Biomedical and Health Informatics","author":[{"propositions":[],"lastnames":["Creagh"],"firstnames":["A.","P."],"suffixes":[]},{"propositions":[],"lastnames":["Simillion"],"firstnames":["C."],"suffixes":[]},{"propositions":[],"lastnames":["Bourke"],"firstnames":["A.","K."],"suffixes":[]},{"propositions":[],"lastnames":["Scotland"],"firstnames":["A."],"suffixes":[]},{"propositions":[],"lastnames":["Lipsmeier"],"firstnames":["F."],"suffixes":[]},{"propositions":[],"lastnames":["Bernasconi"],"firstnames":["C."],"suffixes":[]},{"propositions":[],"lastnames":["Beek"],"firstnames":["J.","van"],"suffixes":[]},{"propositions":[],"lastnames":["Baker"],"firstnames":["M."],"suffixes":[]},{"propositions":[],"lastnames":["Gossens"],"firstnames":["C."],"suffixes":[]},{"propositions":[],"lastnames":["Lindemann"],"firstnames":["M."],"suffixes":[]},{"propositions":[],"lastnames":["Vos"],"firstnames":["M.","De"],"suffixes":[]}],"month":"March","year":"2021","note":"Conference Name: IEEE Journal of Biomedical and Health Informatics","keywords":"Entropy, Feature extraction, Gait, Legged locomotion, ML, Machine Learning, Multiple sclerosis, Pulse width modulation, Sensors, multiple sclerosis, sensor-based measure, smartphone, smartwatch","pages":"838–849","bibtex":"@article{creagh_smartphone-_2021,\n\ttitle = {Smartphone- and {Smartwatch}-{Based} {Remote} {Characterisation} of {Ambulation} in {Multiple} {Sclerosis} {During} the {Two}-{Minute} {Walk} {Test}},\n\tvolume = {25},\n\tissn = {2168-2208},\n\tdoi = {10.1109/JBHI.2020.2998187},\n\tabstract = {Leveraging consumer technology such as smartphone and smartwatch devices to objectively assess people with multiple sclerosis (PwMS) remotely could capture unique aspects of disease progression. This study explores the feasibility of assessing PwMS and Healthy Control's (HC) physical function by characterising gaitrelated features, which can be modelled using machine learning (ML) techniques to correctly distinguish subgroups of PwMS from healthy controls. A total of 97 subjects (24 HC subjects, 52 mildly disabled (PwMSmild, EDSS [0-3]) and 21 moderately disabled (PwMSmod, EDSS [3.5- 5.5]) contributed data which was recorded from a TwoMinute Walk Test (2MWT) performed out-of-clinic and daily over a 24-week period. Signal-based features relating to movement were extracted from sensors in smartphone and smartwatch devices. A large number of features (n = 156) showed fair-to-strong (R {\\textgreater} 0.3) correlations with clinical outcomes. LASSO feature selection was applied to select and rank subsets of features used for dichotomous classification between subject groups, which were compared using Logistic Regression (LR), Support Vector Machines (SVM) and Random Forest (RF) models. Classifications of subject types were compared using data obtained from smartphone, smartwatch and the fusion of features from both devices. Models built on smartphone features alone achieved the highest classification performance, indicating that accurate and remote measurement of the ambulatory characteristics of HC and PwMS can be achieved with only one device. It was observed however that smartphonebased performance was affected by inconsistent placement location (running belt versus pocket). Results show that PwMSmod could be distinguished from HC subjects (Acc. 82.2 ± 2.9\\%, Sen. 80.1 ± 3.9\\%, Spec. 87.2 ± 4.2\\%, F1 84.3 ± 3.8), and PwMSmild (Acc. 82.3 ± 1.9\\%, Sen. 71.6 ± 4.2\\%, Spec. 87.0 ± 3.2\\%, F1 75.1 ± 2.2) using an SVM classifier with a Radial Basis Function (RBF). PwMSmild were shown to exhibit HC-like behaviour and were thus less distinguishable from HC (Acc. 66.4 ± 4.5\\%, Sen. 67.5 ± 5.7\\%, Spec. 60.3 ± 6.7\\%, F1 58.6 ± 5.8). Finally, it was observed that subjects in this study demonstrated low intraand high inter-subject variability which was representative of subject-specific gait characteristics.},\n\tnumber = {3},\n\tjournal = {IEEE Journal of Biomedical and Health Informatics},\n\tauthor = {Creagh, A. P. and Simillion, C. and Bourke, A. K. and Scotland, A. and Lipsmeier, F. and Bernasconi, C. and Beek, J. van and Baker, M. and Gossens, C. and Lindemann, M. and Vos, M. De},\n\tmonth = mar,\n\tyear = {2021},\n\tnote = {Conference Name: IEEE Journal of Biomedical and Health Informatics},\n\tkeywords = {Entropy, Feature extraction, Gait, Legged locomotion, ML, Machine Learning, Multiple sclerosis, Pulse width modulation, Sensors, multiple sclerosis, sensor-based measure, smartphone, smartwatch},\n\tpages = {838--849},\n}\n\n","author_short":["Creagh, A. P.","Simillion, C.","Bourke, A. K.","Scotland, A.","Lipsmeier, F.","Bernasconi, C.","Beek, J. v.","Baker, M.","Gossens, C.","Lindemann, M.","Vos, M. D."],"key":"creagh_smartphone-_2021","id":"creagh_smartphone-_2021","bibbaseid":"creagh-simillion-bourke-scotland-lipsmeier-bernasconi-beek-baker-etal-smartphoneandsmartwatchbasedremotecharacterisationofambulationinmultiplesclerosisduringthetwominutewalktest-2021","role":"author","urls":{},"keyword":["Entropy","Feature extraction","Gait","Legged locomotion","ML","Machine Learning","Multiple sclerosis","Pulse width modulation","Sensors","multiple sclerosis","sensor-based measure","smartphone","smartwatch"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/iagogv","dataSources":["ovn29uG6Mbp3JWCRR"],"keywords":["entropy","feature extraction","gait","legged locomotion","ml","machine learning","multiple sclerosis","pulse width modulation","sensors","multiple sclerosis","sensor-based measure","smartphone","smartwatch"],"search_terms":["smartphone","smartwatch","based","remote","characterisation","ambulation","multiple","sclerosis","during","two","minute","walk","test","creagh","simillion","bourke","scotland","lipsmeier","bernasconi","beek","baker","gossens","lindemann","vos"],"title":"Smartphone- and Smartwatch-Based Remote Characterisation of Ambulation in Multiple Sclerosis During the Two-Minute Walk Test","year":2021}