Queue-based modelling and detection of parameters involved in stroke outcome

Adnan Vilic; John Asger Petersen; Troels Wienecke; Troels W Kjaer; Helge B D Sorensen

doi:10.1109/EMBC.2017.8037384

Queue-based modelling and detection of parameters involved in stroke outcome

Adnan Vilic, John Asger Petersen, Troels Wienecke, Troels W Kjaer, Helge B D Sorensen

Department of Clinical Medicine

Abstract

We designed a queue-based model, and investigated which parameters are of importance when predicting stroke outcome. Medical record forms have been collected for 57 ischemic stroke patients, including medical history and vital sign measurement along with neurological scores for the first twenty-four hours of admission. The importance of each parameter is identified using multiple regression combined with a circular queue to iteratively fit outcome. Out of 39 parameters, the model isolated 14 which combined could estimate outcome with a root mean square error of 1.69 on the Scandinavian Stroke Scale, where outcome for patients were 36.75 ± 10.99. The queue-based model integrating multiple linear regression shows promising results for automatic selection of significant medically relevant parameters.

Original language	English
Journal	I E E E Engineering in Medicine and Biology Society. Conference Proceedings
Volume	2017
Pages (from-to)	2578-2581
Number of pages	4
ISSN	2375-7477
DOIs	https://doi.org/10.1109/EMBC.2017.8037384
Publication status	Published - 13 Sept 2017

Access to Document

10.1109/EMBC.2017.8037384

Cite this

@inproceedings{0daf8f7782e54cfebec7ae335af8e0a5,

title = "Queue-based modelling and detection of parameters involved in stroke outcome",

abstract = "We designed a queue-based model, and investigated which parameters are of importance when predicting stroke outcome. Medical record forms have been collected for 57 ischemic stroke patients, including medical history and vital sign measurement along with neurological scores for the first twenty-four hours of admission. The importance of each parameter is identified using multiple regression combined with a circular queue to iteratively fit outcome. Out of 39 parameters, the model isolated 14 which combined could estimate outcome with a root mean square error of 1.69 on the Scandinavian Stroke Scale, where outcome for patients were 36.75 ± 10.99. The queue-based model integrating multiple linear regression shows promising results for automatic selection of significant medically relevant parameters.",

author = "Adnan Vilic and Petersen, {John Asger} and Troels Wienecke and Kjaer, {Troels W} and Sorensen, {Helge B D}",

year = "2017",

month = sep,

day = "13",

doi = "10.1109/EMBC.2017.8037384",

language = "English",

volume = "2017",

pages = "2578--2581",

journal = "I E E E Engineering in Medicine and Biology Society. Conference Proceedings",

issn = "2375-7477",

publisher = "IEEE Signal Processing Society",

}

TY - GEN

T1 - Queue-based modelling and detection of parameters involved in stroke outcome

AU - Vilic, Adnan

AU - Petersen, John Asger

AU - Wienecke, Troels

AU - Kjaer, Troels W

AU - Sorensen, Helge B D

PY - 2017/9/13

Y1 - 2017/9/13

N2 - We designed a queue-based model, and investigated which parameters are of importance when predicting stroke outcome. Medical record forms have been collected for 57 ischemic stroke patients, including medical history and vital sign measurement along with neurological scores for the first twenty-four hours of admission. The importance of each parameter is identified using multiple regression combined with a circular queue to iteratively fit outcome. Out of 39 parameters, the model isolated 14 which combined could estimate outcome with a root mean square error of 1.69 on the Scandinavian Stroke Scale, where outcome for patients were 36.75 ± 10.99. The queue-based model integrating multiple linear regression shows promising results for automatic selection of significant medically relevant parameters.

AB - We designed a queue-based model, and investigated which parameters are of importance when predicting stroke outcome. Medical record forms have been collected for 57 ischemic stroke patients, including medical history and vital sign measurement along with neurological scores for the first twenty-four hours of admission. The importance of each parameter is identified using multiple regression combined with a circular queue to iteratively fit outcome. Out of 39 parameters, the model isolated 14 which combined could estimate outcome with a root mean square error of 1.69 on the Scandinavian Stroke Scale, where outcome for patients were 36.75 ± 10.99. The queue-based model integrating multiple linear regression shows promising results for automatic selection of significant medically relevant parameters.

U2 - 10.1109/EMBC.2017.8037384

DO - 10.1109/EMBC.2017.8037384

M3 - Conference article

C2 - 29060426

SN - 2375-7477

VL - 2017

SP - 2578

EP - 2581

JO - I E E E Engineering in Medicine and Biology Society. Conference Proceedings

JF - I E E E Engineering in Medicine and Biology Society. Conference Proceedings

ER -

Queue-based modelling and detection of parameters involved in stroke outcome

Abstract

Access to Document

Fingerprint

Cite this