Artificial neural networks and risk stratification in emergency departments

Greta Falavigna, Giorgio Costantino, Raffaello Furlan, James V. Quinn, Andrea Ungar, Roberto Ippoliti

Research output: Contribution to journalArticle

Abstract

Emergency departments are characterized by the need for quick diagnosis under pressure. To select the most appropriate treatment, a series of rules to support decision-making has been offered by scientific societies. The effectiveness of these rules affects the appropriateness of treatment and the hospitalization of patients. Analyzing a sample of 1844 patients and focusing on the decision to hospitalize a patient after a syncope event to prevent severe short-term outcomes, this work proposes a new algorithm based on neural networks. Artificial neural networks are a non-parametric technique with the well-known ability to generalize behaviors, and they can thus predict severe short-term outcomes with pre-selected levels of sensitivity and specificity. This innovative technique can outperform the traditional models, since it does not require a specific functional form, i.e., the data are not supposed to be distributed following a specific design. Based on our results, the innovative model can predict hospitalization with a sensitivity of 100% and a specificity of 79%, significantly increasing the appropriateness of medical treatment and, as a result, hospital efficiency. According to Garson’s Indexes, the most significant variables are exertion, the absence of symptoms, and the patient’s gender. On the contrary, cardio-vascular history, hypertension, and age have the lowest impact on the determination of the subject’s health status. The main application of this new technology is the adoption of smart solutions (e.g., a mobile app) to customize the stratification of patients admitted to emergency departments (ED)s after a syncope event. Indeed, the adoption of these smart solutions gives the opportunity to customize risk stratification according to the specific clinical case (i.e., the patient’s health status) and the physician’s decision-making process (i.e., the desired levels of sensitivity and specificity). Moreover, a decision-making process based on these smart solutions might ensure a more effective use of available resources, improving the management of syncope patients and reducing the cost of inappropriate treatment and hospitalization.

Original languageEnglish
Pages (from-to)291-299
JournalInternal and Emergency Medicine
Volume14
Issue number2
DOIs
Publication statusPublished - 2019

Fingerprint

Hospital Emergency Service
Syncope
Decision Making
Hospitalization
Health Status
Mobile Applications
Sensitivity and Specificity
Aptitude
Health Care Costs
Blood Vessels
Therapeutics
History
Hypertension
Technology
Physicians
Efficiency
Pressure

Keywords

  • Artificial neural networks (ANNs)
  • Decision processes
  • Emergency departments (ERs)
  • Risk stratification
  • Syncope

ASJC Scopus subject areas

  • Internal Medicine
  • Emergency Medicine

Cite this

Artificial neural networks and risk stratification in emergency departments. / Falavigna, Greta; Costantino, Giorgio; Furlan, Raffaello; Quinn, James V.; Ungar, Andrea; Ippoliti, Roberto.

In: Internal and Emergency Medicine, Vol. 14, No. 2, 2019, p. 291-299.

Research output: Contribution to journalArticle

Falavigna, Greta ; Costantino, Giorgio ; Furlan, Raffaello ; Quinn, James V. ; Ungar, Andrea ; Ippoliti, Roberto. / Artificial neural networks and risk stratification in emergency departments. In: Internal and Emergency Medicine. 2019 ; Vol. 14, No. 2. pp. 291-299.
@article{b900ddef571445c68636dc58b0c48607,
title = "Artificial neural networks and risk stratification in emergency departments",
abstract = "Emergency departments are characterized by the need for quick diagnosis under pressure. To select the most appropriate treatment, a series of rules to support decision-making has been offered by scientific societies. The effectiveness of these rules affects the appropriateness of treatment and the hospitalization of patients. Analyzing a sample of 1844 patients and focusing on the decision to hospitalize a patient after a syncope event to prevent severe short-term outcomes, this work proposes a new algorithm based on neural networks. Artificial neural networks are a non-parametric technique with the well-known ability to generalize behaviors, and they can thus predict severe short-term outcomes with pre-selected levels of sensitivity and specificity. This innovative technique can outperform the traditional models, since it does not require a specific functional form, i.e., the data are not supposed to be distributed following a specific design. Based on our results, the innovative model can predict hospitalization with a sensitivity of 100{\%} and a specificity of 79{\%}, significantly increasing the appropriateness of medical treatment and, as a result, hospital efficiency. According to Garson’s Indexes, the most significant variables are exertion, the absence of symptoms, and the patient’s gender. On the contrary, cardio-vascular history, hypertension, and age have the lowest impact on the determination of the subject’s health status. The main application of this new technology is the adoption of smart solutions (e.g., a mobile app) to customize the stratification of patients admitted to emergency departments (ED)s after a syncope event. Indeed, the adoption of these smart solutions gives the opportunity to customize risk stratification according to the specific clinical case (i.e., the patient’s health status) and the physician’s decision-making process (i.e., the desired levels of sensitivity and specificity). Moreover, a decision-making process based on these smart solutions might ensure a more effective use of available resources, improving the management of syncope patients and reducing the cost of inappropriate treatment and hospitalization.",
keywords = "Artificial neural networks (ANNs), Decision processes, Emergency departments (ERs), Risk stratification, Syncope",
author = "Greta Falavigna and Giorgio Costantino and Raffaello Furlan and Quinn, {James V.} and Andrea Ungar and Roberto Ippoliti",
year = "2019",
doi = "10.1007/s11739-018-1971-2",
language = "English",
volume = "14",
pages = "291--299",
journal = "Internal and Emergency Medicine",
issn = "1828-0447",
publisher = "Springer-Verlag Italia s.r.l.",
number = "2",

}

TY - JOUR

T1 - Artificial neural networks and risk stratification in emergency departments

AU - Falavigna, Greta

AU - Costantino, Giorgio

AU - Furlan, Raffaello

AU - Quinn, James V.

AU - Ungar, Andrea

AU - Ippoliti, Roberto

PY - 2019

Y1 - 2019

N2 - Emergency departments are characterized by the need for quick diagnosis under pressure. To select the most appropriate treatment, a series of rules to support decision-making has been offered by scientific societies. The effectiveness of these rules affects the appropriateness of treatment and the hospitalization of patients. Analyzing a sample of 1844 patients and focusing on the decision to hospitalize a patient after a syncope event to prevent severe short-term outcomes, this work proposes a new algorithm based on neural networks. Artificial neural networks are a non-parametric technique with the well-known ability to generalize behaviors, and they can thus predict severe short-term outcomes with pre-selected levels of sensitivity and specificity. This innovative technique can outperform the traditional models, since it does not require a specific functional form, i.e., the data are not supposed to be distributed following a specific design. Based on our results, the innovative model can predict hospitalization with a sensitivity of 100% and a specificity of 79%, significantly increasing the appropriateness of medical treatment and, as a result, hospital efficiency. According to Garson’s Indexes, the most significant variables are exertion, the absence of symptoms, and the patient’s gender. On the contrary, cardio-vascular history, hypertension, and age have the lowest impact on the determination of the subject’s health status. The main application of this new technology is the adoption of smart solutions (e.g., a mobile app) to customize the stratification of patients admitted to emergency departments (ED)s after a syncope event. Indeed, the adoption of these smart solutions gives the opportunity to customize risk stratification according to the specific clinical case (i.e., the patient’s health status) and the physician’s decision-making process (i.e., the desired levels of sensitivity and specificity). Moreover, a decision-making process based on these smart solutions might ensure a more effective use of available resources, improving the management of syncope patients and reducing the cost of inappropriate treatment and hospitalization.

AB - Emergency departments are characterized by the need for quick diagnosis under pressure. To select the most appropriate treatment, a series of rules to support decision-making has been offered by scientific societies. The effectiveness of these rules affects the appropriateness of treatment and the hospitalization of patients. Analyzing a sample of 1844 patients and focusing on the decision to hospitalize a patient after a syncope event to prevent severe short-term outcomes, this work proposes a new algorithm based on neural networks. Artificial neural networks are a non-parametric technique with the well-known ability to generalize behaviors, and they can thus predict severe short-term outcomes with pre-selected levels of sensitivity and specificity. This innovative technique can outperform the traditional models, since it does not require a specific functional form, i.e., the data are not supposed to be distributed following a specific design. Based on our results, the innovative model can predict hospitalization with a sensitivity of 100% and a specificity of 79%, significantly increasing the appropriateness of medical treatment and, as a result, hospital efficiency. According to Garson’s Indexes, the most significant variables are exertion, the absence of symptoms, and the patient’s gender. On the contrary, cardio-vascular history, hypertension, and age have the lowest impact on the determination of the subject’s health status. The main application of this new technology is the adoption of smart solutions (e.g., a mobile app) to customize the stratification of patients admitted to emergency departments (ED)s after a syncope event. Indeed, the adoption of these smart solutions gives the opportunity to customize risk stratification according to the specific clinical case (i.e., the patient’s health status) and the physician’s decision-making process (i.e., the desired levels of sensitivity and specificity). Moreover, a decision-making process based on these smart solutions might ensure a more effective use of available resources, improving the management of syncope patients and reducing the cost of inappropriate treatment and hospitalization.

KW - Artificial neural networks (ANNs)

KW - Decision processes

KW - Emergency departments (ERs)

KW - Risk stratification

KW - Syncope

UR - http://www.scopus.com/inward/record.url?scp=85055719531&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055719531&partnerID=8YFLogxK

U2 - 10.1007/s11739-018-1971-2

DO - 10.1007/s11739-018-1971-2

M3 - Article

AN - SCOPUS:85055719531

VL - 14

SP - 291

EP - 299

JO - Internal and Emergency Medicine

JF - Internal and Emergency Medicine

SN - 1828-0447

IS - 2

ER -