Please use this identifier to cite or link to this item: https://ahro.austin.org.au/austinjspui/handle/1/30620
Title: Development of a machine learning-based real-time location system to streamline acute endovascular intervention in acute stroke: a proof-of-concept study.
Austin Authors: Lim, Dee Zhen;Yeo, Melissa;Dahan, Ariel ;Tahayori, Bahman;Kok, Hong Kuan;Abbasi-Rad, Mohammad;Maingard, Julian;Kutaiba, Numan ;Russell, Jeremy H ;Thijs, Vincent N ;Jhamb, Ashu;Chandra, Ronil V;Brooks, Mark;Barras, Christen;Asadi, Hamed 
Affiliation: Radiology
Melbourne Medical School, The University of Melbourne Faculty of Medicine Dentistry and Health Sciences, Melbourne, Victoria, Australia..
School of Medicine, Faculty of Health, Deakin University, Burwood, Victoria, Australia..
Department of Biomedical Engineering, The University of Melbourne, Melbourne, Victoria, Australia..
Department of Radiology, Northern Health, Epping, Victoria, Australia..
Programmer, Melbourne, Victoria, Australia..
Department of Radiology, Monash Health, Clayton, Victoria, Australia..
The Florey Institute of Neuroscience and Mental Health
Neurosurgery
Neurology
Department of Radiology, St Vincent Health, Fitzroy, Victoria, Australia..
Department of Radiology, Monash Health, Clayton, Victoria, Australia..
South Australian Health and Medical Research Institute, Adelaide, South Australia, Australia..
School of Medicine, University of Adelaide, Adelaide, South Australia, Australia..
Faculty of Medicine Nursing and Health Sciences, Monash University, Clayton, Victoria, Australia..
Issue Date: Aug-2022
Date: 2021
Publication information: Journal of neurointerventional surgery 2022; 14(8): 799-803
Abstract: Delivery of acute stroke endovascular intervention can be challenging because it requires complex coordination of patient and staff across many different locations. In this proof-of-concept paper we (a) examine whether WiFi fingerprinting is a feasible machine learning (ML)-based real-time location system (RTLS) technology that can provide accurate real-time location information within a hospital setting, and (b) hypothesize its potential application in streamlining acute stroke endovascular intervention. We conducted our study in a comprehensive stroke care unit in Melbourne, Australia that offers a 24-hour mechanical thrombectomy service. ML algorithms including K-nearest neighbors, decision tree, random forest, support vector machine and ensemble models were trained and tested on a public WiFi dataset and the study hospital WiFi dataset. The hospital dataset was collected using the WiFi explorer software (version 3.0.2) on a MacBook Pro (AirPort Extreme, Broadcom BCM43x×1.0). Data analysis was implemented in the Python programming environment using the scikit-learn package. The primary statistical measure for algorithm performance was the accuracy of location prediction. ML-based WiFi fingerprinting can accurately predict the different hospital zones relevant in the acute endovascular intervention workflow such as emergency department, CT room and angiography suite. The most accurate algorithms were random forest and support vector machine, both of which were 98% accurate. The algorithms remain robust when new data points, which were distinct from the training dataset, were tested. ML-based RTLS technology using WiFi fingerprinting has the potential to streamline delivery of acute stroke endovascular intervention by efficiently tracking patient and staff movement during stroke calls.
URI: https://ahro.austin.org.au/austinjspui/handle/1/30620
DOI: 10.1136/neurintsurg-2021-017858
ORCID: http://orcid.org/0000-0001-9848-6077
http://orcid.org/0000-0001-5568-7303
http://orcid.org/0000-0003-3205-425X
http://orcid.org/0000-0003-4627-9847
http://orcid.org/0000-0003-3692-120X
http://orcid.org/0000-0002-6614-8417
http://orcid.org/0000-0001-5034-570X
http://orcid.org/0000-0003-2475-9727
Journal: Journal of neurointerventional surgery
PubMed URL: 34426539
PubMed URL: https://pubmed.ncbi.nlm.nih.gov/34426539/
Type: Journal Article
Subjects: stroke
technology
Appears in Collections:Journal articles

Show full item record

Page view(s)

50
checked on Mar 28, 2024

Google ScholarTM

Check


Items in AHRO are protected by copyright, with all rights reserved, unless otherwise indicated.