Ensemble decision trees to predict if a profiled bystander can use an AED to deliver a shock

Raymond Bond, Peter O’Hare, Hannah Torney, Laura Davis, Bruno Delafont, Hannah McReynolds, Anna McLister, Ben McCartney, Rebecca Di Maio, Dewar Finlay, Daniel Guldenring, James McLaughlin, David McEneaney

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

BackgroundEach year cardiac arrest kills 60,000 people in the UK [1-2]. The use of an automatic external defibrillator (AED) in the first few minutes can increase the probability of survival from less than 5% to over 75%. However, there is a challenge to build AEDs that are ‘usable’ to all members of the public. This study investigated if we could predict whether a profiled bystander is likely to succeed in delivering a shock. MethodsA total of 362 subjects were recruited at a shopping mall and were asked to use an AED in a simulated emergency situation as facilitated by a ‘sensorised’ mannequin. During this we extracted a range of features (i.e. Age, Gender, Education, CPR/AED Training, Time-to-Place-Electrodes, Time-to-First-Shock). Using logistic regression, Odds ratios (ORs) were analysed to identify variables that decrease/increase the likelihood of delivering a shock. The dataset was also split into training (70%) and testing datasets (30%) to build and evaluate an ensemble C5.0 decision tree to predict if a person is likely to deliver a successful shock. ResultsThe variables (1) Time-to-First-Shock [OR= 8.97], (2) Prior Defibrillation Training [OR= 8.37], (3) Prior CPR Training [OR= 6.76], High school education [OR= 5.71]) have the largest ORs. This may indicate that users with these characteristics are likely to deliver a shock. However, no OR had statistical significance (p
LanguageEnglish
Title of host publicationUnknown Host Publication
Number of pages1
Publication statusPublished - 27 Oct 2015
Event7th Annual Translational Medicine Conference - Derry/Londonderry
Duration: 27 Oct 2015 → …

Conference

Conference7th Annual Translational Medicine Conference
Period27/10/15 → …

Fingerprint

Decision Trees
Defibrillators
Shock
Odds Ratio
Cardiopulmonary Resuscitation
Manikins
Education
Heart Arrest
Electrodes
Emergencies
Logistic Models
Survival

Keywords

  • machine learning
  • health informatics
  • human computer interaction

Cite this

Bond, R., O’Hare, P., Torney, H., Davis, L., Delafont, B., McReynolds, H., ... McEneaney, D. (2015). Ensemble decision trees to predict if a profiled bystander can use an AED to deliver a shock. In Unknown Host Publication
Bond, Raymond ; O’Hare, Peter ; Torney, Hannah ; Davis, Laura ; Delafont, Bruno ; McReynolds, Hannah ; McLister, Anna ; McCartney, Ben ; Di Maio, Rebecca ; Finlay, Dewar ; Guldenring, Daniel ; McLaughlin, James ; McEneaney, David. / Ensemble decision trees to predict if a profiled bystander can use an AED to deliver a shock. Unknown Host Publication. 2015.
@inproceedings{f20f33708a81461a9265883facde0157,
title = "Ensemble decision trees to predict if a profiled bystander can use an AED to deliver a shock",
abstract = "BackgroundEach year cardiac arrest kills 60,000 people in the UK [1-2]. The use of an automatic external defibrillator (AED) in the first few minutes can increase the probability of survival from less than 5{\%} to over 75{\%}. However, there is a challenge to build AEDs that are ‘usable’ to all members of the public. This study investigated if we could predict whether a profiled bystander is likely to succeed in delivering a shock. MethodsA total of 362 subjects were recruited at a shopping mall and were asked to use an AED in a simulated emergency situation as facilitated by a ‘sensorised’ mannequin. During this we extracted a range of features (i.e. Age, Gender, Education, CPR/AED Training, Time-to-Place-Electrodes, Time-to-First-Shock). Using logistic regression, Odds ratios (ORs) were analysed to identify variables that decrease/increase the likelihood of delivering a shock. The dataset was also split into training (70{\%}) and testing datasets (30{\%}) to build and evaluate an ensemble C5.0 decision tree to predict if a person is likely to deliver a successful shock. ResultsThe variables (1) Time-to-First-Shock [OR= 8.97], (2) Prior Defibrillation Training [OR= 8.37], (3) Prior CPR Training [OR= 6.76], High school education [OR= 5.71]) have the largest ORs. This may indicate that users with these characteristics are likely to deliver a shock. However, no OR had statistical significance (p",
keywords = "machine learning, health informatics, human computer interaction",
author = "Raymond Bond and Peter O’Hare and Hannah Torney and Laura Davis and Bruno Delafont and Hannah McReynolds and Anna McLister and Ben McCartney and {Di Maio}, Rebecca and Dewar Finlay and Daniel Guldenring and James McLaughlin and David McEneaney",
year = "2015",
month = "10",
day = "27",
language = "English",
booktitle = "Unknown Host Publication",

}

Bond, R, O’Hare, P, Torney, H, Davis, L, Delafont, B, McReynolds, H, McLister, A, McCartney, B, Di Maio, R, Finlay, D, Guldenring, D, McLaughlin, J & McEneaney, D 2015, Ensemble decision trees to predict if a profiled bystander can use an AED to deliver a shock. in Unknown Host Publication. 7th Annual Translational Medicine Conference, 27/10/15.

Ensemble decision trees to predict if a profiled bystander can use an AED to deliver a shock. / Bond, Raymond; O’Hare, Peter; Torney, Hannah; Davis, Laura; Delafont, Bruno; McReynolds, Hannah; McLister, Anna; McCartney, Ben; Di Maio, Rebecca; Finlay, Dewar; Guldenring, Daniel; McLaughlin, James; McEneaney, David.

Unknown Host Publication. 2015.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Ensemble decision trees to predict if a profiled bystander can use an AED to deliver a shock

AU - Bond, Raymond

AU - O’Hare, Peter

AU - Torney, Hannah

AU - Davis, Laura

AU - Delafont, Bruno

AU - McReynolds, Hannah

AU - McLister, Anna

AU - McCartney, Ben

AU - Di Maio, Rebecca

AU - Finlay, Dewar

AU - Guldenring, Daniel

AU - McLaughlin, James

AU - McEneaney, David

PY - 2015/10/27

Y1 - 2015/10/27

N2 - BackgroundEach year cardiac arrest kills 60,000 people in the UK [1-2]. The use of an automatic external defibrillator (AED) in the first few minutes can increase the probability of survival from less than 5% to over 75%. However, there is a challenge to build AEDs that are ‘usable’ to all members of the public. This study investigated if we could predict whether a profiled bystander is likely to succeed in delivering a shock. MethodsA total of 362 subjects were recruited at a shopping mall and were asked to use an AED in a simulated emergency situation as facilitated by a ‘sensorised’ mannequin. During this we extracted a range of features (i.e. Age, Gender, Education, CPR/AED Training, Time-to-Place-Electrodes, Time-to-First-Shock). Using logistic regression, Odds ratios (ORs) were analysed to identify variables that decrease/increase the likelihood of delivering a shock. The dataset was also split into training (70%) and testing datasets (30%) to build and evaluate an ensemble C5.0 decision tree to predict if a person is likely to deliver a successful shock. ResultsThe variables (1) Time-to-First-Shock [OR= 8.97], (2) Prior Defibrillation Training [OR= 8.37], (3) Prior CPR Training [OR= 6.76], High school education [OR= 5.71]) have the largest ORs. This may indicate that users with these characteristics are likely to deliver a shock. However, no OR had statistical significance (p

AB - BackgroundEach year cardiac arrest kills 60,000 people in the UK [1-2]. The use of an automatic external defibrillator (AED) in the first few minutes can increase the probability of survival from less than 5% to over 75%. However, there is a challenge to build AEDs that are ‘usable’ to all members of the public. This study investigated if we could predict whether a profiled bystander is likely to succeed in delivering a shock. MethodsA total of 362 subjects were recruited at a shopping mall and were asked to use an AED in a simulated emergency situation as facilitated by a ‘sensorised’ mannequin. During this we extracted a range of features (i.e. Age, Gender, Education, CPR/AED Training, Time-to-Place-Electrodes, Time-to-First-Shock). Using logistic regression, Odds ratios (ORs) were analysed to identify variables that decrease/increase the likelihood of delivering a shock. The dataset was also split into training (70%) and testing datasets (30%) to build and evaluate an ensemble C5.0 decision tree to predict if a person is likely to deliver a successful shock. ResultsThe variables (1) Time-to-First-Shock [OR= 8.97], (2) Prior Defibrillation Training [OR= 8.37], (3) Prior CPR Training [OR= 6.76], High school education [OR= 5.71]) have the largest ORs. This may indicate that users with these characteristics are likely to deliver a shock. However, no OR had statistical significance (p

KW - machine learning

KW - health informatics

KW - human computer interaction

M3 - Conference contribution

BT - Unknown Host Publication

ER -

Bond R, O’Hare P, Torney H, Davis L, Delafont B, McReynolds H et al. Ensemble decision trees to predict if a profiled bystander can use an AED to deliver a shock. In Unknown Host Publication. 2015