Prediction of symptomatic cerebral vasospasm after aneurysmal subarachnoid hemorrhage with an artificial neural network: Feasibility and comparison with logistic regression models

Travis M Dumont, Anand I. Rughani, Bruce I. Tranmer

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

Objective To create a simple artificial neural network (ANN) to predict the occurrence of symptomatic cerebral vasospasm (SCV) after aneurysmal subarachnoid hemorrhage (aSAH) based on clinical and radiographic factors and test its predictive ability against existing multiple logistic regression (MLR) models. Methods A retrospective database of patients admitted to a single academic medical center with confirmed aSAH between January 2002 and January 2007 (91 patients) was input to a back-propagation ANN program freely available to academicians on the Internet. The resulting ANN was prospectively tested against two previously published MLR prediction models for all patients admitted the following year (22 patients). The models were compared for their predictive accuracy with receiver operating characteristic (ROC) curve analysis. Results All models were accurate with their prediction of patients with SCV. The ANN had superior predictive value compared with the MLR models, with a significantly improved area under ROC curve (0.960 ± 0.044 vs 0.933 ± 0.54 and 0.897 ± 0.069 for MLR models). Conclusions A simple ANN model was more sensitive and specific than MLR models in prediction of SCV in patients with aSAH. The conception of ANN modeling for cerebral vasospasm is introduced for a neurosurgical audience. With advanced ANN modeling, the clinician may expect to build improved models with more powerful prediction capabilities.

Original languageEnglish (US)
Pages (from-to)57-63
Number of pages7
JournalWorld Neurosurgery
Volume75
Issue number1
DOIs
StatePublished - Jan 2011
Externally publishedYes

Fingerprint

Intracranial Vasospasm
Subarachnoid Hemorrhage
Logistic Models
ROC Curve
Neural Networks (Computer)
Internet
Databases

Keywords

  • Cerebral vasospasm
  • Neural network
  • Neurosurgery
  • Subarachnoid hemorrhage

ASJC Scopus subject areas

  • Clinical Neurology
  • Surgery

Cite this

@article{2601f487baf540eb94f6f5ff59526570,
title = "Prediction of symptomatic cerebral vasospasm after aneurysmal subarachnoid hemorrhage with an artificial neural network: Feasibility and comparison with logistic regression models",
abstract = "Objective To create a simple artificial neural network (ANN) to predict the occurrence of symptomatic cerebral vasospasm (SCV) after aneurysmal subarachnoid hemorrhage (aSAH) based on clinical and radiographic factors and test its predictive ability against existing multiple logistic regression (MLR) models. Methods A retrospective database of patients admitted to a single academic medical center with confirmed aSAH between January 2002 and January 2007 (91 patients) was input to a back-propagation ANN program freely available to academicians on the Internet. The resulting ANN was prospectively tested against two previously published MLR prediction models for all patients admitted the following year (22 patients). The models were compared for their predictive accuracy with receiver operating characteristic (ROC) curve analysis. Results All models were accurate with their prediction of patients with SCV. The ANN had superior predictive value compared with the MLR models, with a significantly improved area under ROC curve (0.960 ± 0.044 vs 0.933 ± 0.54 and 0.897 ± 0.069 for MLR models). Conclusions A simple ANN model was more sensitive and specific than MLR models in prediction of SCV in patients with aSAH. The conception of ANN modeling for cerebral vasospasm is introduced for a neurosurgical audience. With advanced ANN modeling, the clinician may expect to build improved models with more powerful prediction capabilities.",
keywords = "Cerebral vasospasm, Neural network, Neurosurgery, Subarachnoid hemorrhage",
author = "Dumont, {Travis M} and Rughani, {Anand I.} and Tranmer, {Bruce I.}",
year = "2011",
month = "1",
doi = "10.1016/j.wneu.2010.07.007",
language = "English (US)",
volume = "75",
pages = "57--63",
journal = "World Neurosurgery",
issn = "1878-8750",
publisher = "Elsevier Inc.",
number = "1",

}

TY - JOUR

T1 - Prediction of symptomatic cerebral vasospasm after aneurysmal subarachnoid hemorrhage with an artificial neural network

T2 - Feasibility and comparison with logistic regression models

AU - Dumont, Travis M

AU - Rughani, Anand I.

AU - Tranmer, Bruce I.

PY - 2011/1

Y1 - 2011/1

N2 - Objective To create a simple artificial neural network (ANN) to predict the occurrence of symptomatic cerebral vasospasm (SCV) after aneurysmal subarachnoid hemorrhage (aSAH) based on clinical and radiographic factors and test its predictive ability against existing multiple logistic regression (MLR) models. Methods A retrospective database of patients admitted to a single academic medical center with confirmed aSAH between January 2002 and January 2007 (91 patients) was input to a back-propagation ANN program freely available to academicians on the Internet. The resulting ANN was prospectively tested against two previously published MLR prediction models for all patients admitted the following year (22 patients). The models were compared for their predictive accuracy with receiver operating characteristic (ROC) curve analysis. Results All models were accurate with their prediction of patients with SCV. The ANN had superior predictive value compared with the MLR models, with a significantly improved area under ROC curve (0.960 ± 0.044 vs 0.933 ± 0.54 and 0.897 ± 0.069 for MLR models). Conclusions A simple ANN model was more sensitive and specific than MLR models in prediction of SCV in patients with aSAH. The conception of ANN modeling for cerebral vasospasm is introduced for a neurosurgical audience. With advanced ANN modeling, the clinician may expect to build improved models with more powerful prediction capabilities.

AB - Objective To create a simple artificial neural network (ANN) to predict the occurrence of symptomatic cerebral vasospasm (SCV) after aneurysmal subarachnoid hemorrhage (aSAH) based on clinical and radiographic factors and test its predictive ability against existing multiple logistic regression (MLR) models. Methods A retrospective database of patients admitted to a single academic medical center with confirmed aSAH between January 2002 and January 2007 (91 patients) was input to a back-propagation ANN program freely available to academicians on the Internet. The resulting ANN was prospectively tested against two previously published MLR prediction models for all patients admitted the following year (22 patients). The models were compared for their predictive accuracy with receiver operating characteristic (ROC) curve analysis. Results All models were accurate with their prediction of patients with SCV. The ANN had superior predictive value compared with the MLR models, with a significantly improved area under ROC curve (0.960 ± 0.044 vs 0.933 ± 0.54 and 0.897 ± 0.069 for MLR models). Conclusions A simple ANN model was more sensitive and specific than MLR models in prediction of SCV in patients with aSAH. The conception of ANN modeling for cerebral vasospasm is introduced for a neurosurgical audience. With advanced ANN modeling, the clinician may expect to build improved models with more powerful prediction capabilities.

KW - Cerebral vasospasm

KW - Neural network

KW - Neurosurgery

KW - Subarachnoid hemorrhage

UR - http://www.scopus.com/inward/record.url?scp=79952939089&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952939089&partnerID=8YFLogxK

U2 - 10.1016/j.wneu.2010.07.007

DO - 10.1016/j.wneu.2010.07.007

M3 - Article

C2 - 21492664

AN - SCOPUS:79952939089

VL - 75

SP - 57

EP - 63

JO - World Neurosurgery

JF - World Neurosurgery

SN - 1878-8750

IS - 1

ER -