Normal view MARC view ISBD view

Using Wearable Sensors and Machine Learning Models to Separate Functional Upper Extremity Use From Walking-Associated Arm Movements.

MedStar author(s):

Citation: Archives of Physical Medicine & Rehabilitation. 97(2):224-31, 2016 Feb.PMID: 26435302Institution: MedStar National Rehabilitation Network | MedStar National Rehabilitation Network | MedStar National Rehabilitation NetworkForm of publication: Journal ArticleMedline article type(s): Journal Article | Research Support, Non-U.S. Gov't | Research Support, U.S. Gov't, Non-P.H.S. | Video-Audio MediaSubject headings: *Artificial Limbs | *Machine Learning | *Movement/ph [Physiology] | *Transducers | *Upper Extremity/ph [Physiology] | *Walking/ph [Physiology] | Adult | Case-Control Studies | Feasibility Studies | Humans | Middle Aged | Models, Statistical | Young AdultYear: 2016 Local holdings: Available online from MWHC library: 2000 - present, Available in print through MWHC library:1999-2007ISSN:

0003-9993

Name of journal: Archives of physical medicine and rehabilitationAbstract: CONCLUSIONS: We have demonstrated that computationally lightweight classification models can use inertial data collected from wrist-worn sensors to reliably distinguish prosthetic UE movements during functional use from walking-associated movement. This approach has promise in objectively measuring real-world UE use of prosthetic limbs and may be helpful in clinical trials and in measuring response to treatment of other UE pathologies.Copyright © 2016 American Congress of Rehabilitation Medicine. Published by Elsevier Inc. All rights reserved.DESIGN: Comparison of machine learning classification models with criterion standard of manually scored videos of performance in UE prosthesis users.INTERVENTIONS: Participants were filmed executing a series of functional activities; a trained observer annotated each frame to indicate either UE movement directed at functional activity or walking. Synchronized data from an inertial sensor attached to the dominant wrist were similarly classified as indicating either a functional use or walking. These data were used to train 3 classification models to predict the functional versus walking state given the associated sensor information. Models were trained over 4 trials: on UE amputees and controls and both within subject and across subject. Model performance was also examined with and without preprocessing (centering) in the across-subject trials.MAIN OUTCOME MEASURE: Percent correct classification.OBJECTIVE: To improve measurement of upper extremity (UE) use in the community by evaluating the feasibility of using body-worn sensor data and machine learning models to distinguish productive prehensile and bimanual UE activity use from extraneous movements associated with walking.PARTICIPANTS: Convenience sample of UE prosthesis users (n=5) and controls (n=13) similar in age and hand dominance (N=18).RESULTS: With the exception of the amputee/across-subject trial, at least 1 model classified >95% of test data correctly for all trial types. The top performer in the amputee/across-subject trial classified 85% of test examples correctly.SETTING: Rehabilitation hospital training apartment.All authors: Bochniewicz EM, Dromerick AW, Emmer G, Holley RJ, Lum PS, McLeod AFiscal year: FY2016Digital Object Identifier:

http://dx.doi.org/10.1016/j.apmr.2015.08.435

Date added to catalog: 2016-06-13

Holdings ( 1 )
Title notes ( 10 )

Holdings
Item type	Current library	Collection	Call number	Status	Date due	Barcode
Journal Article	MedStar Authors Catalog	Article	26435302	Available		26435302

Available online from MWHC library: 2000 - present, Available in print through MWHC library:1999-2007

CONCLUSIONS: We have demonstrated that computationally lightweight classification models can use inertial data collected from wrist-worn sensors to reliably distinguish prosthetic UE movements during functional use from walking-associated movement. This approach has promise in objectively measuring real-world UE use of prosthetic limbs and may be helpful in clinical trials and in measuring response to treatment of other UE pathologies.Copyright © 2016 American Congress of Rehabilitation Medicine. Published by Elsevier Inc. All rights reserved.

DESIGN: Comparison of machine learning classification models with criterion standard of manually scored videos of performance in UE prosthesis users.

INTERVENTIONS: Participants were filmed executing a series of functional activities; a trained observer annotated each frame to indicate either UE movement directed at functional activity or walking. Synchronized data from an inertial sensor attached to the dominant wrist were similarly classified as indicating either a functional use or walking. These data were used to train 3 classification models to predict the functional versus walking state given the associated sensor information. Models were trained over 4 trials: on UE amputees and controls and both within subject and across subject. Model performance was also examined with and without preprocessing (centering) in the across-subject trials.

MAIN OUTCOME MEASURE: Percent correct classification.

OBJECTIVE: To improve measurement of upper extremity (UE) use in the community by evaluating the feasibility of using body-worn sensor data and machine learning models to distinguish productive prehensile and bimanual UE activity use from extraneous movements associated with walking.

PARTICIPANTS: Convenience sample of UE prosthesis users (n=5) and controls (n=13) similar in age and hand dominance (N=18).

RESULTS: With the exception of the amputee/across-subject trial, at least 1 model classified >95% of test data correctly for all trial types. The top performer in the amputee/across-subject trial classified 85% of test examples correctly.

SETTING: Rehabilitation hospital training apartment.

English