Accurate real time localization tracking in a clinical environment using Bluetooth Low Energy and deep learning

Zohaib Iqbal, Da Luo, Peter Henry, Samaneh Kazemifar, Timothy Rozario, Yulong Yan, Kenneth Westover, Weiguo Lu, Dan Nguyen, Troy Long, Jing Wang, Hak Choy, Steve Jiang

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Deep learning has started to revolutionize several different industries, and the applications of these methods in medicine are now becoming more commonplace. This study focuses on investigating the feasibility of tracking patients and clinical staff wearing Bluetooth Low Energy (BLE) tags in a radiation oncology clinic using artificial neural networks (ANNs) and convolutional neural networks (CNNs). The performance of these networks was compared to relative received signal strength indicator (RSSI) thresholding and triangulation. By utilizing temporal information, a combined CNN+ANN network was capable of correctly identifying the location of the BLE tag with an accuracy of 99.9%. It outperformed a CNN model (accuracy = 94%), a thresholding model employing majority voting (accuracy = 95%), and a triangulation classifier utilizing majority voting (accuracy = 95%). Future studies will seek to deploy this affordable real time location system in hospitals to improve clinical workflow, efficiency, and patient safety.

Original languageEnglish (US)
Article numbere0205392
JournalPLoS One
Volume13
Issue number10
DOIs
StatePublished - Oct 1 2018

Fingerprint

Bluetooth
Politics
neural networks
learning
Patient Identification Systems
Learning
Neural networks
Radiation Oncology
Neural Networks (Computer)
Workflow
energy
Computer Systems
Triangulation
Patient Safety
Industry
Medicine
Efficiency
Oncology
Classifiers
application methods

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Accurate real time localization tracking in a clinical environment using Bluetooth Low Energy and deep learning. / Iqbal, Zohaib; Luo, Da; Henry, Peter; Kazemifar, Samaneh; Rozario, Timothy; Yan, Yulong; Westover, Kenneth; Lu, Weiguo; Nguyen, Dan; Long, Troy; Wang, Jing; Choy, Hak; Jiang, Steve.

In: PLoS One, Vol. 13, No. 10, e0205392, 01.10.2018.

Research output: Contribution to journalArticle

Iqbal, Zohaib ; Luo, Da ; Henry, Peter ; Kazemifar, Samaneh ; Rozario, Timothy ; Yan, Yulong ; Westover, Kenneth ; Lu, Weiguo ; Nguyen, Dan ; Long, Troy ; Wang, Jing ; Choy, Hak ; Jiang, Steve. / Accurate real time localization tracking in a clinical environment using Bluetooth Low Energy and deep learning. In: PLoS One. 2018 ; Vol. 13, No. 10.
@article{4e085e93bd3644bd9b1d333327c6e585,
title = "Accurate real time localization tracking in a clinical environment using Bluetooth Low Energy and deep learning",
abstract = "Deep learning has started to revolutionize several different industries, and the applications of these methods in medicine are now becoming more commonplace. This study focuses on investigating the feasibility of tracking patients and clinical staff wearing Bluetooth Low Energy (BLE) tags in a radiation oncology clinic using artificial neural networks (ANNs) and convolutional neural networks (CNNs). The performance of these networks was compared to relative received signal strength indicator (RSSI) thresholding and triangulation. By utilizing temporal information, a combined CNN+ANN network was capable of correctly identifying the location of the BLE tag with an accuracy of 99.9{\%}. It outperformed a CNN model (accuracy = 94{\%}), a thresholding model employing majority voting (accuracy = 95{\%}), and a triangulation classifier utilizing majority voting (accuracy = 95{\%}). Future studies will seek to deploy this affordable real time location system in hospitals to improve clinical workflow, efficiency, and patient safety.",
author = "Zohaib Iqbal and Da Luo and Peter Henry and Samaneh Kazemifar and Timothy Rozario and Yulong Yan and Kenneth Westover and Weiguo Lu and Dan Nguyen and Troy Long and Jing Wang and Hak Choy and Steve Jiang",
year = "2018",
month = "10",
day = "1",
doi = "10.1371/journal.pone.0205392",
language = "English (US)",
volume = "13",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "10",

}

TY - JOUR

T1 - Accurate real time localization tracking in a clinical environment using Bluetooth Low Energy and deep learning

AU - Iqbal, Zohaib

AU - Luo, Da

AU - Henry, Peter

AU - Kazemifar, Samaneh

AU - Rozario, Timothy

AU - Yan, Yulong

AU - Westover, Kenneth

AU - Lu, Weiguo

AU - Nguyen, Dan

AU - Long, Troy

AU - Wang, Jing

AU - Choy, Hak

AU - Jiang, Steve

PY - 2018/10/1

Y1 - 2018/10/1

N2 - Deep learning has started to revolutionize several different industries, and the applications of these methods in medicine are now becoming more commonplace. This study focuses on investigating the feasibility of tracking patients and clinical staff wearing Bluetooth Low Energy (BLE) tags in a radiation oncology clinic using artificial neural networks (ANNs) and convolutional neural networks (CNNs). The performance of these networks was compared to relative received signal strength indicator (RSSI) thresholding and triangulation. By utilizing temporal information, a combined CNN+ANN network was capable of correctly identifying the location of the BLE tag with an accuracy of 99.9%. It outperformed a CNN model (accuracy = 94%), a thresholding model employing majority voting (accuracy = 95%), and a triangulation classifier utilizing majority voting (accuracy = 95%). Future studies will seek to deploy this affordable real time location system in hospitals to improve clinical workflow, efficiency, and patient safety.

AB - Deep learning has started to revolutionize several different industries, and the applications of these methods in medicine are now becoming more commonplace. This study focuses on investigating the feasibility of tracking patients and clinical staff wearing Bluetooth Low Energy (BLE) tags in a radiation oncology clinic using artificial neural networks (ANNs) and convolutional neural networks (CNNs). The performance of these networks was compared to relative received signal strength indicator (RSSI) thresholding and triangulation. By utilizing temporal information, a combined CNN+ANN network was capable of correctly identifying the location of the BLE tag with an accuracy of 99.9%. It outperformed a CNN model (accuracy = 94%), a thresholding model employing majority voting (accuracy = 95%), and a triangulation classifier utilizing majority voting (accuracy = 95%). Future studies will seek to deploy this affordable real time location system in hospitals to improve clinical workflow, efficiency, and patient safety.

UR - http://www.scopus.com/inward/record.url?scp=85054751164&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054751164&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0205392

DO - 10.1371/journal.pone.0205392

M3 - Article

C2 - 30307999

AN - SCOPUS:85054751164

VL - 13

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 10

M1 - e0205392

ER -