Stroke-Associated Hemiparesis Detection Using Body Joints and Support Vector Machines. Ramesh, V., Agrawal, K., Meyer, B., Cauwenberghs, G., & Weibel, N. In Proceedings of the 12th EAI International Conference on Pervasive Computing Technologies for Healthcare, of PervasiveHealth '18, pages 55–58, New York, NY, USA, 2018. ACM. ![Stroke-Associated Hemiparesis Detection Using Body Joints and Support Vector Machines [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Hemiparesis, the weakness of one side of the body, affects the ability of stroke survivors to move and walk. It is generally diagnosed through motor tests performed as part of neurological examinations such as the NIH Stroke Scale (NIHSS), a subjective evaluation that requires the presence of an experienced neurologist. Here we report on an alternative way for computationally identifying hemiparesis that leverages body joint position data captured by the Microsoft Kinect. We employed support vector machines with 14 stroke subjects and 21 controls to characterize hemiparesis based on 4 core body angles recorded while the participants were simply sitting at rest, waiting for their neurologist. When comparing our results to neurologists' NIHSS scores, we were able to always identify right-side hemiparesis, left-side hemiparesis, or no hemiparesis using a leave-one-subject-out analysis. With additional data, our ultimate aim is to include the hemiparesis detection system presented here in a larger, multimodal tool that characterizes stroke based on several stroke-associated deficits. We envision deploying this tool in emergency settings for faster and more precise stroke severity assessments done in real-time.
@inproceedings{ramesh_stroke-associated_2018,
address = {New York, NY, USA},
series = {{PervasiveHealth} '18},
title = {Stroke-{Associated} {Hemiparesis} {Detection} {Using} {Body} {Joints} and {Support} {Vector} {Machines}},
isbn = {978-1-4503-6450-8},
url = {http://doi.acm.org/10.1145/3240925.3240979},
doi = {10.1145/3240925.3240979},
abstract = {Hemiparesis, the weakness of one side of the body, affects the ability of stroke survivors to move and walk. It is generally diagnosed through motor tests performed as part of neurological examinations such as the NIH Stroke Scale (NIHSS), a subjective evaluation that requires the presence of an experienced neurologist. Here we report on an alternative way for computationally identifying hemiparesis that leverages body joint position data captured by the Microsoft Kinect. We employed support vector machines with 14 stroke subjects and 21 controls to characterize hemiparesis based on 4 core body angles recorded while the participants were simply sitting at rest, waiting for their neurologist. When comparing our results to neurologists' NIHSS scores, we were able to always identify right-side hemiparesis, left-side hemiparesis, or no hemiparesis using a leave-one-subject-out analysis. With additional data, our ultimate aim is to include the hemiparesis detection system presented here in a larger, multimodal tool that characterizes stroke based on several stroke-associated deficits. We envision deploying this tool in emergency settings for faster and more precise stroke severity assessments done in real-time.},
urldate = {2018-12-06},
booktitle = {Proceedings of the 12th {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 = {2018},
keywords = {Body-Tracking, Hemiparesis, Kinect, Machine Learning, Posture Detection, Stroke, Support Vector Machines},
pages = {55--58},
}
Downloads: 0
{"_id":"C69fwTDi7NCAis7bS","bibbaseid":"ramesh-agrawal-meyer-cauwenberghs-weibel-strokeassociatedhemiparesisdetectionusingbodyjointsandsupportvectormachines-2018","downloads":0,"creationDate":"2018-12-07T17:45:10.750Z","title":"Stroke-Associated Hemiparesis Detection Using Body Joints and Support Vector Machines","author_short":["Ramesh, V.","Agrawal, K.","Meyer, B.","Cauwenberghs, G.","Weibel, N."],"year":2018,"bibtype":"inproceedings","biburl":"https://api.zotero.org/users/5376753/collections/9SI3B7P5/items?key=sMSKMYtS5TTzmqcTdEPwcbfC&format=bibtex&limit=100","bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"New York, NY, USA","series":"PervasiveHealth '18","title":"Stroke-Associated Hemiparesis Detection Using Body Joints and Support Vector Machines","isbn":"978-1-4503-6450-8","url":"http://doi.acm.org/10.1145/3240925.3240979","doi":"10.1145/3240925.3240979","abstract":"Hemiparesis, the weakness of one side of the body, affects the ability of stroke survivors to move and walk. It is generally diagnosed through motor tests performed as part of neurological examinations such as the NIH Stroke Scale (NIHSS), a subjective evaluation that requires the presence of an experienced neurologist. Here we report on an alternative way for computationally identifying hemiparesis that leverages body joint position data captured by the Microsoft Kinect. We employed support vector machines with 14 stroke subjects and 21 controls to characterize hemiparesis based on 4 core body angles recorded while the participants were simply sitting at rest, waiting for their neurologist. When comparing our results to neurologists' NIHSS scores, we were able to always identify right-side hemiparesis, left-side hemiparesis, or no hemiparesis using a leave-one-subject-out analysis. With additional data, our ultimate aim is to include the hemiparesis detection system presented here in a larger, multimodal tool that characterizes stroke based on several stroke-associated deficits. We envision deploying this tool in emergency settings for faster and more precise stroke severity assessments done in real-time.","urldate":"2018-12-06","booktitle":"Proceedings of the 12th EAI International Conference on Pervasive Computing Technologies for Healthcare","publisher":"ACM","author":[{"propositions":[],"lastnames":["Ramesh"],"firstnames":["Vishwajith"],"suffixes":[]},{"propositions":[],"lastnames":["Agrawal"],"firstnames":["Kunal"],"suffixes":[]},{"propositions":[],"lastnames":["Meyer"],"firstnames":["Brett"],"suffixes":[]},{"propositions":[],"lastnames":["Cauwenberghs"],"firstnames":["Gert"],"suffixes":[]},{"propositions":[],"lastnames":["Weibel"],"firstnames":["Nadir"],"suffixes":[]}],"year":"2018","keywords":"Body-Tracking, Hemiparesis, Kinect, Machine Learning, Posture Detection, Stroke, Support Vector Machines","pages":"55–58","bibtex":"@inproceedings{ramesh_stroke-associated_2018,\n\taddress = {New York, NY, USA},\n\tseries = {{PervasiveHealth} '18},\n\ttitle = {Stroke-{Associated} {Hemiparesis} {Detection} {Using} {Body} {Joints} and {Support} {Vector} {Machines}},\n\tisbn = {978-1-4503-6450-8},\n\turl = {http://doi.acm.org/10.1145/3240925.3240979},\n\tdoi = {10.1145/3240925.3240979},\n\tabstract = {Hemiparesis, the weakness of one side of the body, affects the ability of stroke survivors to move and walk. It is generally diagnosed through motor tests performed as part of neurological examinations such as the NIH Stroke Scale (NIHSS), a subjective evaluation that requires the presence of an experienced neurologist. Here we report on an alternative way for computationally identifying hemiparesis that leverages body joint position data captured by the Microsoft Kinect. We employed support vector machines with 14 stroke subjects and 21 controls to characterize hemiparesis based on 4 core body angles recorded while the participants were simply sitting at rest, waiting for their neurologist. When comparing our results to neurologists' NIHSS scores, we were able to always identify right-side hemiparesis, left-side hemiparesis, or no hemiparesis using a leave-one-subject-out analysis. With additional data, our ultimate aim is to include the hemiparesis detection system presented here in a larger, multimodal tool that characterizes stroke based on several stroke-associated deficits. We envision deploying this tool in emergency settings for faster and more precise stroke severity assessments done in real-time.},\n\turldate = {2018-12-06},\n\tbooktitle = {Proceedings of the 12th {EAI} {International} {Conference} on {Pervasive} {Computing} {Technologies} for {Healthcare}},\n\tpublisher = {ACM},\n\tauthor = {Ramesh, Vishwajith and Agrawal, Kunal and Meyer, Brett and Cauwenberghs, Gert and Weibel, Nadir},\n\tyear = {2018},\n\tkeywords = {Body-Tracking, Hemiparesis, Kinect, Machine Learning, Posture Detection, Stroke, Support Vector Machines},\n\tpages = {55--58},\n}\n\n","author_short":["Ramesh, V.","Agrawal, K.","Meyer, B.","Cauwenberghs, G.","Weibel, N."],"key":"ramesh_stroke-associated_2018","id":"ramesh_stroke-associated_2018","bibbaseid":"ramesh-agrawal-meyer-cauwenberghs-weibel-strokeassociatedhemiparesisdetectionusingbodyjointsandsupportvectormachines-2018","role":"author","urls":{"Paper":"http://doi.acm.org/10.1145/3240925.3240979"},"keyword":["Body-Tracking","Hemiparesis","Kinect","Machine Learning","Posture Detection","Stroke","Support Vector Machines"],"metadata":{"authorlinks":{"weibel, n":"https://bibbase.org/show?bib=http%3A%2F%2Fhci4h.ucsd.edu%2Fdata%2Fuploads%2Fhci4h_refs.bib"}},"html":""},"search_terms":["stroke","associated","hemiparesis","detection","using","body","joints","support","vector","machines","ramesh","agrawal","meyer","cauwenberghs","weibel"],"keywords":["body-tracking","hemiparesis","kinect","machine learning","posture detection","stroke","support vector machines"],"authorIDs":["PYquZbYP3E3vCc4gZ"],"dataSources":["9Wy88DxpeiPRcYJ3H"]}