Neural networks as a tool to predict syncope risk in the Emergency Department

Giorgio Costantino, Greta Falavigna, Monica Solbiati, Ivo Casagranda, Benjamin Sun, Shamai A. Grossman, James V. Quinn, Matthew J. Reed, Andrea Ungar, Nicola Montano, Raffaello Furlan, Roberto Ippoliti

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The optimal disposition approach to patients presenting to an Emergency Department (ED) with syncope is unclear. Many low-risk patients with syncope are unnecessarily admitted to hospital. This may increase risk associated with hospitalization (including medication errors and hospital-acquired infections), and to an excessive use of resources.1 On the other hand, patients inappropriately discharged from the ED may experience serious adverse events or even death that may have been preventable with hospital-based interventions.2-4 This can partially explain the high heterogeneity in practice and hospitalization rate observed from multiple reports obtained from different countries.4,5 Despite many attempts to optimize ED syncope management, such as the use of structured management pathways and ED syncope observation units, a rigorous and effective approach remains elusive.6,7 Several syncope prediction tools have been developed to guide clinician decision-making in the ED.8-12 However, none has proved superior to clinical practice.5,6,13 Artificial neural networks (ANNs) are complex non-linear models inspired by the working of biological neural networks (i.e. the central nervous system). They are used to estimate complex functions (i.e. non-linear) that require a large number of inputs. Artificial neural networks are presented as systems of layers (multilayer) composed of neurons (also called perceptrons) which exchange messages between each other by synapsis (weights). The synapses have numeric weights that can be tuned based on experience, making neural nets adaptive to inputs and capable of learning. 14 As one of the major problems in syncope risk stratification is that syncope itself can be the final common presentation of several conditions which are very heterogeneous in terms of prognosis, the absence of linearity in such a context could make the application of ANNs appealing.15 The use of ANNs has already shown promising results in emergency medicine. For example, ANNs have been developed to reduce computed tomography imaging for suspected craniocervical junction injury in major head trauma patients.16 Artificial neural networks have also been used to predict risk ofmyocardial infarction in patients with chest pain.17 The aim of our study was to investigate the effectiveness of ANNs as a short-term risk stratification tool for syncope patients in the ED.

Original languageEnglish (US)
Pages (from-to)1891-1895
Number of pages5
JournalEuropace
Volume19
Issue number11
DOIs
StatePublished - Nov 1 2017
Externally publishedYes

Fingerprint

Syncope
Hospital Emergency Service
Hospitalization
Chromosome Pairing
Nervous System Trauma
Weights and Measures
Medication Errors
Neural Networks (Computer)
Nonlinear Dynamics
Emergency Medicine
Cross Infection
Craniocerebral Trauma
Synapses
Infarction
Decision Making
Thorax
Central Nervous System
Tomography
Observation
Learning

Keywords

  • Artificial neural networks
  • Calibration
  • Discrimination
  • Emergency Department
  • Risk stratification
  • Syncope

ASJC Scopus subject areas

  • Cardiology and Cardiovascular Medicine
  • Physiology (medical)

Cite this

Costantino, G., Falavigna, G., Solbiati, M., Casagranda, I., Sun, B., Grossman, S. A., ... Ippoliti, R. (2017). Neural networks as a tool to predict syncope risk in the Emergency Department. Europace, 19(11), 1891-1895. https://doi.org/10.1093/europace/euw336

Neural networks as a tool to predict syncope risk in the Emergency Department. / Costantino, Giorgio; Falavigna, Greta; Solbiati, Monica; Casagranda, Ivo; Sun, Benjamin; Grossman, Shamai A.; Quinn, James V.; Reed, Matthew J.; Ungar, Andrea; Montano, Nicola; Furlan, Raffaello; Ippoliti, Roberto.

In: Europace, Vol. 19, No. 11, 01.11.2017, p. 1891-1895.

Research output: Contribution to journalArticle

Costantino, G, Falavigna, G, Solbiati, M, Casagranda, I, Sun, B, Grossman, SA, Quinn, JV, Reed, MJ, Ungar, A, Montano, N, Furlan, R & Ippoliti, R 2017, 'Neural networks as a tool to predict syncope risk in the Emergency Department', Europace, vol. 19, no. 11, pp. 1891-1895. https://doi.org/10.1093/europace/euw336
Costantino G, Falavigna G, Solbiati M, Casagranda I, Sun B, Grossman SA et al. Neural networks as a tool to predict syncope risk in the Emergency Department. Europace. 2017 Nov 1;19(11):1891-1895. https://doi.org/10.1093/europace/euw336
Costantino, Giorgio ; Falavigna, Greta ; Solbiati, Monica ; Casagranda, Ivo ; Sun, Benjamin ; Grossman, Shamai A. ; Quinn, James V. ; Reed, Matthew J. ; Ungar, Andrea ; Montano, Nicola ; Furlan, Raffaello ; Ippoliti, Roberto. / Neural networks as a tool to predict syncope risk in the Emergency Department. In: Europace. 2017 ; Vol. 19, No. 11. pp. 1891-1895.
@article{b37b45c36034438cba497d6fcd6ed80b,
title = "Neural networks as a tool to predict syncope risk in the Emergency Department",
abstract = "The optimal disposition approach to patients presenting to an Emergency Department (ED) with syncope is unclear. Many low-risk patients with syncope are unnecessarily admitted to hospital. This may increase risk associated with hospitalization (including medication errors and hospital-acquired infections), and to an excessive use of resources.1 On the other hand, patients inappropriately discharged from the ED may experience serious adverse events or even death that may have been preventable with hospital-based interventions.2-4 This can partially explain the high heterogeneity in practice and hospitalization rate observed from multiple reports obtained from different countries.4,5 Despite many attempts to optimize ED syncope management, such as the use of structured management pathways and ED syncope observation units, a rigorous and effective approach remains elusive.6,7 Several syncope prediction tools have been developed to guide clinician decision-making in the ED.8-12 However, none has proved superior to clinical practice.5,6,13 Artificial neural networks (ANNs) are complex non-linear models inspired by the working of biological neural networks (i.e. the central nervous system). They are used to estimate complex functions (i.e. non-linear) that require a large number of inputs. Artificial neural networks are presented as systems of layers (multilayer) composed of neurons (also called perceptrons) which exchange messages between each other by synapsis (weights). The synapses have numeric weights that can be tuned based on experience, making neural nets adaptive to inputs and capable of learning. 14 As one of the major problems in syncope risk stratification is that syncope itself can be the final common presentation of several conditions which are very heterogeneous in terms of prognosis, the absence of linearity in such a context could make the application of ANNs appealing.15 The use of ANNs has already shown promising results in emergency medicine. For example, ANNs have been developed to reduce computed tomography imaging for suspected craniocervical junction injury in major head trauma patients.16 Artificial neural networks have also been used to predict risk ofmyocardial infarction in patients with chest pain.17 The aim of our study was to investigate the effectiveness of ANNs as a short-term risk stratification tool for syncope patients in the ED.",
keywords = "Artificial neural networks, Calibration, Discrimination, Emergency Department, Risk stratification, Syncope",
author = "Giorgio Costantino and Greta Falavigna and Monica Solbiati and Ivo Casagranda and Benjamin Sun and Grossman, {Shamai A.} and Quinn, {James V.} and Reed, {Matthew J.} and Andrea Ungar and Nicola Montano and Raffaello Furlan and Roberto Ippoliti",
year = "2017",
month = "11",
day = "1",
doi = "10.1093/europace/euw336",
language = "English (US)",
volume = "19",
pages = "1891--1895",
journal = "Europace : European pacing, arrhythmias, and cardiac electrophysiology : journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology",
issn = "1099-5129",
publisher = "Oxford University Press",
number = "11",

}

TY - JOUR

T1 - Neural networks as a tool to predict syncope risk in the Emergency Department

AU - Costantino, Giorgio

AU - Falavigna, Greta

AU - Solbiati, Monica

AU - Casagranda, Ivo

AU - Sun, Benjamin

AU - Grossman, Shamai A.

AU - Quinn, James V.

AU - Reed, Matthew J.

AU - Ungar, Andrea

AU - Montano, Nicola

AU - Furlan, Raffaello

AU - Ippoliti, Roberto

PY - 2017/11/1

Y1 - 2017/11/1

N2 - The optimal disposition approach to patients presenting to an Emergency Department (ED) with syncope is unclear. Many low-risk patients with syncope are unnecessarily admitted to hospital. This may increase risk associated with hospitalization (including medication errors and hospital-acquired infections), and to an excessive use of resources.1 On the other hand, patients inappropriately discharged from the ED may experience serious adverse events or even death that may have been preventable with hospital-based interventions.2-4 This can partially explain the high heterogeneity in practice and hospitalization rate observed from multiple reports obtained from different countries.4,5 Despite many attempts to optimize ED syncope management, such as the use of structured management pathways and ED syncope observation units, a rigorous and effective approach remains elusive.6,7 Several syncope prediction tools have been developed to guide clinician decision-making in the ED.8-12 However, none has proved superior to clinical practice.5,6,13 Artificial neural networks (ANNs) are complex non-linear models inspired by the working of biological neural networks (i.e. the central nervous system). They are used to estimate complex functions (i.e. non-linear) that require a large number of inputs. Artificial neural networks are presented as systems of layers (multilayer) composed of neurons (also called perceptrons) which exchange messages between each other by synapsis (weights). The synapses have numeric weights that can be tuned based on experience, making neural nets adaptive to inputs and capable of learning. 14 As one of the major problems in syncope risk stratification is that syncope itself can be the final common presentation of several conditions which are very heterogeneous in terms of prognosis, the absence of linearity in such a context could make the application of ANNs appealing.15 The use of ANNs has already shown promising results in emergency medicine. For example, ANNs have been developed to reduce computed tomography imaging for suspected craniocervical junction injury in major head trauma patients.16 Artificial neural networks have also been used to predict risk ofmyocardial infarction in patients with chest pain.17 The aim of our study was to investigate the effectiveness of ANNs as a short-term risk stratification tool for syncope patients in the ED.

AB - The optimal disposition approach to patients presenting to an Emergency Department (ED) with syncope is unclear. Many low-risk patients with syncope are unnecessarily admitted to hospital. This may increase risk associated with hospitalization (including medication errors and hospital-acquired infections), and to an excessive use of resources.1 On the other hand, patients inappropriately discharged from the ED may experience serious adverse events or even death that may have been preventable with hospital-based interventions.2-4 This can partially explain the high heterogeneity in practice and hospitalization rate observed from multiple reports obtained from different countries.4,5 Despite many attempts to optimize ED syncope management, such as the use of structured management pathways and ED syncope observation units, a rigorous and effective approach remains elusive.6,7 Several syncope prediction tools have been developed to guide clinician decision-making in the ED.8-12 However, none has proved superior to clinical practice.5,6,13 Artificial neural networks (ANNs) are complex non-linear models inspired by the working of biological neural networks (i.e. the central nervous system). They are used to estimate complex functions (i.e. non-linear) that require a large number of inputs. Artificial neural networks are presented as systems of layers (multilayer) composed of neurons (also called perceptrons) which exchange messages between each other by synapsis (weights). The synapses have numeric weights that can be tuned based on experience, making neural nets adaptive to inputs and capable of learning. 14 As one of the major problems in syncope risk stratification is that syncope itself can be the final common presentation of several conditions which are very heterogeneous in terms of prognosis, the absence of linearity in such a context could make the application of ANNs appealing.15 The use of ANNs has already shown promising results in emergency medicine. For example, ANNs have been developed to reduce computed tomography imaging for suspected craniocervical junction injury in major head trauma patients.16 Artificial neural networks have also been used to predict risk ofmyocardial infarction in patients with chest pain.17 The aim of our study was to investigate the effectiveness of ANNs as a short-term risk stratification tool for syncope patients in the ED.

KW - Artificial neural networks

KW - Calibration

KW - Discrimination

KW - Emergency Department

KW - Risk stratification

KW - Syncope

UR - http://www.scopus.com/inward/record.url?scp=85034838221&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85034838221&partnerID=8YFLogxK

U2 - 10.1093/europace/euw336

DO - 10.1093/europace/euw336

M3 - Article

C2 - 28017935

AN - SCOPUS:85034838221

VL - 19

SP - 1891

EP - 1895

JO - Europace : European pacing, arrhythmias, and cardiac electrophysiology : journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology

JF - Europace : European pacing, arrhythmias, and cardiac electrophysiology : journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology

SN - 1099-5129

IS - 11

ER -