Estimating physical ability of stroke patients without specific tests. Derungs, A., Seiter, J., Schuster-Amft, C., & Amft, O. In ISWC 2015: Proceedings of the 2015 ACM International Symposium on Wearable Computers, In press. ACM. abstract bibtex We estimate the Extended Barthel Index (EBI) in patients after stroke using inertial sensor measurements acquired during daily activity, rather than specific assessments. The EBI is a standard clinical assessment showing patient independence in handling everyday tasks. Our work aims at providing a continuous ability estimate for patients and therapists that could be used without expert supervision. We extract nine activity primitives (AP), including sit, stand, transition, etc. from the continuous sensor data using basic rules that do not require data-based training. Using the relative duration of activity primitives, we evaluate the EBI score estimation using two regression methods: Generalised Linear Models (GLM) and Support-Vector Regression (SVR). We evaluated our approaches in full-day study recordings from 11 stroke patients with totally 102 days in ambulatory rehabilitation in a daycare centre. Our results show that EBI can be estimated from the activity primitives with approx. 12% relative error on average for all study participants using SVR. For GLM 7 out of 11 patient estimates show relative RMSE below 20%, while for SVR yields below 15% for 8 out of 11 patients. Our results indicate that EBI can be estimated in daily life activity, thus supporting patients and therapists in tracking rehab progress.
@InProceedings{Derungs2015-P_ISWC,
Title = {Estimating physical ability of stroke patients without specific tests},
Author = {Adrian Derungs and Julia Seiter and Corina Schuster-Amft and Oliver Amft},
Booktitle = {ISWC 2015: Proceedings of the 2015 ACM International Symposium on Wearable Computers},
Year = {In press},
Publisher = {ACM},
Abstract = {We estimate the Extended Barthel Index (EBI) in patients after stroke using inertial sensor measurements acquired during daily activity, rather than specific assessments. The EBI is a standard clinical assessment showing patient independence in handling everyday tasks. Our work aims at providing a continuous ability estimate for patients and therapists that could be used without expert supervision. We extract nine activity primitives (AP), including sit, stand, transition, etc. from the continuous sensor data using basic rules that do not require data-based training. Using the relative duration of activity primitives, we evaluate the EBI score estimation using two regression methods: Generalised Linear Models (GLM) and Support-Vector Regression (SVR). We evaluated our approaches in full-day study recordings from 11 stroke patients with totally 102 days in ambulatory rehabilitation in a daycare centre. Our results show that EBI can be estimated from the activity primitives with approx. 12\% relative error on average for all study participants using SVR. For GLM 7 out of 11 patient estimates show relative RMSE below 20\%, while for SVR yields below 15\% for 8 out of 11 patients. Our results indicate that EBI can be estimated in daily life activity, thus supporting patients and therapists in tracking rehab progress.},
File = {Derungs2015-P_ISWC.pdf:Derungs2015-P_ISWC.pdf:PDF},
Owner = {oamft},
Timestamp = {2015/05/16}
}
Downloads: 0
{"_id":"yk7KM8DaxwgjNqhbJ","bibbaseid":"derungs-seiter-schusteramft-amft-estimatingphysicalabilityofstrokepatientswithoutspecifictests-inpress","downloads":0,"creationDate":"2016-03-10T09:24:25.389Z","title":"Estimating physical ability of stroke patients without specific tests","author_short":["Derungs, A.","Seiter, J.","Schuster-Amft, C.","Amft, O."],"year":null,"bibtype":"inproceedings","biburl":"http://cl94754.tmweb.ru/fish/files/neuesFile.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Estimating physical ability of stroke patients without specific tests","author":[{"firstnames":["Adrian"],"propositions":[],"lastnames":["Derungs"],"suffixes":[]},{"firstnames":["Julia"],"propositions":[],"lastnames":["Seiter"],"suffixes":[]},{"firstnames":["Corina"],"propositions":[],"lastnames":["Schuster-Amft"],"suffixes":[]},{"firstnames":["Oliver"],"propositions":[],"lastnames":["Amft"],"suffixes":[]}],"booktitle":"ISWC 2015: Proceedings of the 2015 ACM International Symposium on Wearable Computers","year":"In press","publisher":"ACM","abstract":"We estimate the Extended Barthel Index (EBI) in patients after stroke using inertial sensor measurements acquired during daily activity, rather than specific assessments. The EBI is a standard clinical assessment showing patient independence in handling everyday tasks. Our work aims at providing a continuous ability estimate for patients and therapists that could be used without expert supervision. We extract nine activity primitives (AP), including sit, stand, transition, etc. from the continuous sensor data using basic rules that do not require data-based training. Using the relative duration of activity primitives, we evaluate the EBI score estimation using two regression methods: Generalised Linear Models (GLM) and Support-Vector Regression (SVR). We evaluated our approaches in full-day study recordings from 11 stroke patients with totally 102 days in ambulatory rehabilitation in a daycare centre. Our results show that EBI can be estimated from the activity primitives with approx. 12% relative error on average for all study participants using SVR. For GLM 7 out of 11 patient estimates show relative RMSE below 20%, while for SVR yields below 15% for 8 out of 11 patients. Our results indicate that EBI can be estimated in daily life activity, thus supporting patients and therapists in tracking rehab progress.","file":"Derungs2015-P_ISWC.pdf:Derungs2015-P_ISWC.pdf:PDF","owner":"oamft","timestamp":"2015/05/16","bibtex":"@InProceedings{Derungs2015-P_ISWC,\n Title = {Estimating physical ability of stroke patients without specific tests},\n Author = {Adrian Derungs and Julia Seiter and Corina Schuster-Amft and Oliver Amft},\n Booktitle = {ISWC 2015: Proceedings of the 2015 ACM International Symposium on Wearable Computers},\n Year = {In press},\n Publisher = {ACM},\n\n Abstract = {We estimate the Extended Barthel Index (EBI) in patients after stroke using inertial sensor measurements acquired during daily activity, rather than specific assessments. The EBI is a standard clinical assessment showing patient independence in handling everyday tasks. Our work aims at providing a continuous ability estimate for patients and therapists that could be used without expert supervision. We extract nine activity primitives (AP), including sit, stand, transition, etc. from the continuous sensor data using basic rules that do not require data-based training. Using the relative duration of activity primitives, we evaluate the EBI score estimation using two regression methods: Generalised Linear Models (GLM) and Support-Vector Regression (SVR). We evaluated our approaches in full-day study recordings from 11 stroke patients with totally 102 days in ambulatory rehabilitation in a daycare centre. Our results show that EBI can be estimated from the activity primitives with approx. 12\\% relative error on average for all study participants using SVR. For GLM 7 out of 11 patient estimates show relative RMSE below 20\\%, while for SVR yields below 15\\% for 8 out of 11 patients. Our results indicate that EBI can be estimated in daily life activity, thus supporting patients and therapists in tracking rehab progress.},\n File = {Derungs2015-P_ISWC.pdf:Derungs2015-P_ISWC.pdf:PDF},\n Owner = {oamft},\n Timestamp = {2015/05/16}\n}\n\n","author_short":["Derungs, A.","Seiter, J.","Schuster-Amft, C.","Amft, O."],"key":"Derungs2015-P_ISWC","id":"Derungs2015-P_ISWC","bibbaseid":"derungs-seiter-schusteramft-amft-estimatingphysicalabilityofstrokepatientswithoutspecifictests-inpress","role":"author","urls":{},"downloads":0,"html":""},"search_terms":["estimating","physical","ability","stroke","patients","without","specific","tests","derungs","seiter","schuster-amft","amft"],"keywords":[],"authorIDs":["56e13d4802df45160b0000aa"],"dataSources":["LsXrfomMC874zbKcK"]}