Exploring Stroke-associated Hemiparesis Assessment with Support Vector Machines. Ramesh, V.; Agrawal, K.; Meyer, B.; Cauwenberghs, G.; and Weibel, N. In Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare, of PervasiveHealth '17, pages 464–467, New York, NY, USA, 2017. ACM.
Exploring Stroke-associated Hemiparesis Assessment with Support Vector Machines [link]Paper  doi  abstract   bibtex   
Hemiparesis, the weakness of one side of the body, affects the ability of stroke survivors to move and walk. With prevalence in 80% of survivors, hemiparesis is an important measure for stroke severity. It is generally diagnosed through motor tests performed as part of the National Institute of Health Stroke Scale (NIHSS). Here we report on initial work for an alternate way of identifying hemiparesis that leverages body joint position data captured by the Microsoft Kinect v2 of people resting while waiting for the neurological examination. We employ support vector machines with 10 stroke patients and 9 healthy controls to characterize hemiparesis based on the lower core body angles of the participants, and compare our results to neurologists' diagnoses. We were able to identify left-side hemiparesis, right-side hemiparesis, or no hemiparesis with \textgreater 89% accuracy when looking at the lower body angles and observing the patients for 1 minute.
@inproceedings{ramesh_exploring_2017,
	address = {New York, NY, USA},
	series = {{PervasiveHealth} '17},
	title = {Exploring {Stroke}-associated {Hemiparesis} {Assessment} with {Support} {Vector} {Machines}},
	isbn = {978-1-4503-6363-1},
	url = {http://doi.acm.org/10.1145/3154862.3154894},
	doi = {10.1145/3154862.3154894},
	abstract = {Hemiparesis, the weakness of one side of the body, affects the ability of stroke survivors to move and walk. With prevalence in 80\% of survivors, hemiparesis is an important measure for stroke severity. It is generally diagnosed through motor tests performed as part of the National Institute of Health Stroke Scale (NIHSS). Here we report on initial work for an alternate way of identifying hemiparesis that leverages body joint position data captured by the Microsoft Kinect v2 of people resting while waiting for the neurological examination. We employ support vector machines with 10 stroke patients and 9 healthy controls to characterize hemiparesis based on the lower core body angles of the participants, and compare our results to neurologists' diagnoses. We were able to identify left-side hemiparesis, right-side hemiparesis, or no hemiparesis with {\textgreater} 89\% accuracy when looking at the lower body angles and observing the patients for 1 minute.},
	urldate = {2018-12-06},
	booktitle = {Proceedings of the 11th {EAI} {International} {Conference} on {Pervasive} {Computing} {Technologies} for {Healthcare}},
	publisher = {ACM},
	author = {Ramesh, Vishwajith and Agrawal, Kunal and Meyer, Brett and Cauwenberghs, Gert and Weibel, Nadir},
	year = {2017},
	keywords = {body-tracking, hemiparesis, Kinect, machine learning, posture, stroke, support vector machines},
	pages = {464--467},
	file = {ACM Full Text PDF:/Users/weibel/Zotero/storage/DWI8B4J9/Ramesh et al. - 2017 - Exploring Stroke-associated Hemiparesis Assessment.pdf:application/pdf}
}
Downloads: 0