Article Text

Download PDFPDF
Original research
Development of a machine learning-based real-time location system to streamline acute endovascular intervention in acute stroke: a proof-of-concept study
  1. Dee Zhen Lim1,
  2. Melissa Yeo2,
  3. Ariel Dahan1,
  4. Bahman Tahayori3,
  5. Hong Kuan Kok4,5,
  6. Mohammad Abbasi-Rad6,
  7. Julian Maingard7,8,
  8. Numan Kutaiba1,
  9. Jeremy Russell9,
  10. Vincent Thijs10,11,
  11. Ashu Jhamb12,
  12. Ronil V Chandra7,8,
  13. Mark Brooks1,5,
  14. Christen Barras13,14,
  15. Hamed Asadi1,5
  1. 1Department of Radiology, Austin Health, Heidelberg, Victoria, Australia
  2. 2Melbourne Medical School, The University of Melbourne Faculty of Medicine Dentistry and Health Sciences, Melbourne, Victoria, Australia
  3. 3Department of Biomedical Engineering, The University of Melbourne, Melbourne, Victoria, Australia
  4. 4Department of Radiology, Northern Health, Epping, Victoria, Australia
  5. 5School of Medicine, Faculty of Health, Deakin University, Burwood, Victoria, Australia
  6. 6Programmer, Melbourne, Victoria, Australia
  7. 7Department of Radiology, Monash Health, Clayton, Victoria, Australia
  8. 8Faculty of Medicine Nursing and Health Sciences, Monash University, Clayton, Victoria, Australia
  9. 9Department of Neurosurgery, Austin Health, Heidelberg, Victoria, Australia
  10. 10Department of Neurology, Austin Health, Heidelberg, Victoria, Australia
  11. 11Stroke Theme, Florey Neuroscience Institutes, Parkville, Victoria, Australia
  12. 12Department of Radiology, St Vincent Health, Fitzroy, Victoria, Australia
  13. 13School of Medicine, University of Adelaide, Adelaide, South Australia, Australia
  14. 14South Australian Health and Medical Research Institute, Adelaide, South Australia, Australia
  1. Correspondence to Dr Dee Zhen Lim, Department of Radiology, Austin Health, Heidelberg, Victoria, Australia; deezhenlim{at}gmail.com

Abstract

Background 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.

Methods 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.

Results 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.

Conclusions 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.

  • stroke
  • technology

Data availability statement

Data are available upon reasonable request.

Statistics from Altmetric.com

Data availability statement

Data are available upon reasonable request.

View Full Text

Footnotes

  • DZL and MY are joint first authors.

  • Contributors DZL is responsible for the initial study design, data collection, data analysis and manuscript drafting and revision. MY is responsible for the machine learning algorithm and important analysis, as well as manuscript drafting and revision. BT and MA-R are responsible for providing technical background and support, as well as manuscript drafting and revision. AD, HKK, JM, NK, JR, VT, AJ, RVC, MB and CB all made significant contributions to manuscript drafting and revision and have given approval for publication. HA is the supervising author who is responsible for the study conceptualization and design. He has been instrumental in the manuscript drafting and revision and has provided approval for the publication.

  • Funding The authors have not declared a specific grant for this research from any funding agency in the public, commercial or not-for-profit sectors.

  • Competing interests None declared.

  • Provenance and peer review Not commissioned; internally peer reviewed.

  • Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.