Novel Screening Tool for Stroke Using Artificial Neural Network

Vida Abedi, Nitin Goyal, Georgios Tsivgoulis, Niyousha Hosseinichimeh, Raquel Hontecillas, Josep Bassaganya-Riera, Lucas Elijovich, E. Metter, Anne Alexandrov, David S. Liebeskind, Andrei Alexandrov, Ramin Zand

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Background and Purpose-The timely diagnosis of stroke at the initial examination is extremely important given the disease morbidity and narrow time window for intervention. The goal of this study was to develop a supervised learning method to recognize acute cerebral ischemia (ACI) and differentiate that from stroke mimics in an emergency setting. Methods-Consecutive patients presenting to the emergency department with stroke-like symptoms, within 4.5 hours of symptoms onset, in 2 tertiary care stroke centers were randomized for inclusion in the model. We developed an artificial neural network (ANN) model. The learning algorithm was based on backpropagation. To validate the model, we used a 10-fold cross-validation method. Results-A total of 260 patients (equal number of stroke mimics and ACIs) were enrolled for the development and validation of our ANN model. Our analysis indicated that the average sensitivity and specificity of ANN for the diagnosis of ACI based on the 10-fold cross-validation analysis was 80.0% (95% confidence interval, 71.8-86.3) and 86.2% (95% confidence interval, 78.7-91.4), respectively. The median precision of ANN for the diagnosis of ACI was 92% (95% confidence interval, 88.7-95.3). Conclusions-Our results show that ANN can be an effective tool for the recognition of ACI and differentiation of ACI from stroke mimics at the initial examination.

Original languageEnglish (US)
Pages (from-to)1678-1681
Number of pages4
JournalStroke
Volume48
Issue number6
DOIs
StatePublished - Jun 1 2017

Fingerprint

Brain Ischemia
Stroke
Neural Networks (Computer)
Confidence Intervals
Learning
Tertiary Care Centers
Hospital Emergency Service
Emergencies
Morbidity
Sensitivity and Specificity

All Science Journal Classification (ASJC) codes

  • Clinical Neurology
  • Cardiology and Cardiovascular Medicine
  • Advanced and Specialized Nursing

Cite this

Abedi, V., Goyal, N., Tsivgoulis, G., Hosseinichimeh, N., Hontecillas, R., Bassaganya-Riera, J., ... Zand, R. (2017). Novel Screening Tool for Stroke Using Artificial Neural Network. Stroke, 48(6), 1678-1681. https://doi.org/10.1161/STROKEAHA.117.017033

Novel Screening Tool for Stroke Using Artificial Neural Network. / Abedi, Vida; Goyal, Nitin; Tsivgoulis, Georgios; Hosseinichimeh, Niyousha; Hontecillas, Raquel; Bassaganya-Riera, Josep; Elijovich, Lucas; Metter, E.; Alexandrov, Anne; Liebeskind, David S.; Alexandrov, Andrei; Zand, Ramin.

In: Stroke, Vol. 48, No. 6, 01.06.2017, p. 1678-1681.

Research output: Contribution to journalArticle

Abedi, V, Goyal, N, Tsivgoulis, G, Hosseinichimeh, N, Hontecillas, R, Bassaganya-Riera, J, Elijovich, L, Metter, E, Alexandrov, A, Liebeskind, DS, Alexandrov, A & Zand, R 2017, 'Novel Screening Tool for Stroke Using Artificial Neural Network', Stroke, vol. 48, no. 6, pp. 1678-1681. https://doi.org/10.1161/STROKEAHA.117.017033
Abedi V, Goyal N, Tsivgoulis G, Hosseinichimeh N, Hontecillas R, Bassaganya-Riera J et al. Novel Screening Tool for Stroke Using Artificial Neural Network. Stroke. 2017 Jun 1;48(6):1678-1681. https://doi.org/10.1161/STROKEAHA.117.017033
Abedi, Vida ; Goyal, Nitin ; Tsivgoulis, Georgios ; Hosseinichimeh, Niyousha ; Hontecillas, Raquel ; Bassaganya-Riera, Josep ; Elijovich, Lucas ; Metter, E. ; Alexandrov, Anne ; Liebeskind, David S. ; Alexandrov, Andrei ; Zand, Ramin. / Novel Screening Tool for Stroke Using Artificial Neural Network. In: Stroke. 2017 ; Vol. 48, No. 6. pp. 1678-1681.
@article{bee59263b3af430abc374cc42b50c51d,
title = "Novel Screening Tool for Stroke Using Artificial Neural Network",
abstract = "Background and Purpose-The timely diagnosis of stroke at the initial examination is extremely important given the disease morbidity and narrow time window for intervention. The goal of this study was to develop a supervised learning method to recognize acute cerebral ischemia (ACI) and differentiate that from stroke mimics in an emergency setting. Methods-Consecutive patients presenting to the emergency department with stroke-like symptoms, within 4.5 hours of symptoms onset, in 2 tertiary care stroke centers were randomized for inclusion in the model. We developed an artificial neural network (ANN) model. The learning algorithm was based on backpropagation. To validate the model, we used a 10-fold cross-validation method. Results-A total of 260 patients (equal number of stroke mimics and ACIs) were enrolled for the development and validation of our ANN model. Our analysis indicated that the average sensitivity and specificity of ANN for the diagnosis of ACI based on the 10-fold cross-validation analysis was 80.0{\%} (95{\%} confidence interval, 71.8-86.3) and 86.2{\%} (95{\%} confidence interval, 78.7-91.4), respectively. The median precision of ANN for the diagnosis of ACI was 92{\%} (95{\%} confidence interval, 88.7-95.3). Conclusions-Our results show that ANN can be an effective tool for the recognition of ACI and differentiation of ACI from stroke mimics at the initial examination.",
author = "Vida Abedi and Nitin Goyal and Georgios Tsivgoulis and Niyousha Hosseinichimeh and Raquel Hontecillas and Josep Bassaganya-Riera and Lucas Elijovich and E. Metter and Anne Alexandrov and Liebeskind, {David S.} and Andrei Alexandrov and Ramin Zand",
year = "2017",
month = "6",
day = "1",
doi = "10.1161/STROKEAHA.117.017033",
language = "English (US)",
volume = "48",
pages = "1678--1681",
journal = "Stroke",
issn = "0039-2499",
publisher = "Lippincott Williams and Wilkins",
number = "6",

}

TY - JOUR

T1 - Novel Screening Tool for Stroke Using Artificial Neural Network

AU - Abedi, Vida

AU - Goyal, Nitin

AU - Tsivgoulis, Georgios

AU - Hosseinichimeh, Niyousha

AU - Hontecillas, Raquel

AU - Bassaganya-Riera, Josep

AU - Elijovich, Lucas

AU - Metter, E.

AU - Alexandrov, Anne

AU - Liebeskind, David S.

AU - Alexandrov, Andrei

AU - Zand, Ramin

PY - 2017/6/1

Y1 - 2017/6/1

N2 - Background and Purpose-The timely diagnosis of stroke at the initial examination is extremely important given the disease morbidity and narrow time window for intervention. The goal of this study was to develop a supervised learning method to recognize acute cerebral ischemia (ACI) and differentiate that from stroke mimics in an emergency setting. Methods-Consecutive patients presenting to the emergency department with stroke-like symptoms, within 4.5 hours of symptoms onset, in 2 tertiary care stroke centers were randomized for inclusion in the model. We developed an artificial neural network (ANN) model. The learning algorithm was based on backpropagation. To validate the model, we used a 10-fold cross-validation method. Results-A total of 260 patients (equal number of stroke mimics and ACIs) were enrolled for the development and validation of our ANN model. Our analysis indicated that the average sensitivity and specificity of ANN for the diagnosis of ACI based on the 10-fold cross-validation analysis was 80.0% (95% confidence interval, 71.8-86.3) and 86.2% (95% confidence interval, 78.7-91.4), respectively. The median precision of ANN for the diagnosis of ACI was 92% (95% confidence interval, 88.7-95.3). Conclusions-Our results show that ANN can be an effective tool for the recognition of ACI and differentiation of ACI from stroke mimics at the initial examination.

AB - Background and Purpose-The timely diagnosis of stroke at the initial examination is extremely important given the disease morbidity and narrow time window for intervention. The goal of this study was to develop a supervised learning method to recognize acute cerebral ischemia (ACI) and differentiate that from stroke mimics in an emergency setting. Methods-Consecutive patients presenting to the emergency department with stroke-like symptoms, within 4.5 hours of symptoms onset, in 2 tertiary care stroke centers were randomized for inclusion in the model. We developed an artificial neural network (ANN) model. The learning algorithm was based on backpropagation. To validate the model, we used a 10-fold cross-validation method. Results-A total of 260 patients (equal number of stroke mimics and ACIs) were enrolled for the development and validation of our ANN model. Our analysis indicated that the average sensitivity and specificity of ANN for the diagnosis of ACI based on the 10-fold cross-validation analysis was 80.0% (95% confidence interval, 71.8-86.3) and 86.2% (95% confidence interval, 78.7-91.4), respectively. The median precision of ANN for the diagnosis of ACI was 92% (95% confidence interval, 88.7-95.3). Conclusions-Our results show that ANN can be an effective tool for the recognition of ACI and differentiation of ACI from stroke mimics at the initial examination.

UR - http://www.scopus.com/inward/record.url?scp=85018721447&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018721447&partnerID=8YFLogxK

U2 - 10.1161/STROKEAHA.117.017033

DO - 10.1161/STROKEAHA.117.017033

M3 - Article

VL - 48

SP - 1678

EP - 1681

JO - Stroke

JF - Stroke

SN - 0039-2499

IS - 6

ER -