Noninvasive feature-based detection of delayed gastric emptying in humans using neural networks

Jiande Chen, Zhiyue Lin, Richard W. McCallum

Research output: Contribution to journalArticle

Abstract

Radioscintigraphy is currently the gold standard for gastric emptying test which involves radiation exposure and is considerably expensive. We present a feature-based detection approach using neural networks for the noninvasive diagnosis of delayed gastric emptying from the cutaneous electrogastrogram (EGG). Simultaneous recordings of the EGG and scintigraphic gastric emptying test were made in 152 patients with symptoms suggestive of delayed gastric emptying. Spectral analyses were performed to derive EGG parameters which were used as the input of the neural network. The result of scintigraphic gastric emptying was used as the gold standard for the training and testing of the neural network. A correct classification of 85% (a specificity of 89% and a sensitivity of 82%) was achieved using the proposed method.

Original languageEnglish (US)
Pages (from-to)409-412
Number of pages4
JournalIEEE Transactions on Biomedical Engineering
Volume47
Issue number3
DOIs
StatePublished - 2000
Externally publishedYes

Fingerprint

Neural networks
Radiation
Testing

Keywords

  • Artificial neural networks
  • Electrogastrogram
  • Gastric emptying
  • Spectral analysis

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Noninvasive feature-based detection of delayed gastric emptying in humans using neural networks. / Chen, Jiande; Lin, Zhiyue; McCallum, Richard W.

In: IEEE Transactions on Biomedical Engineering, Vol. 47, No. 3, 2000, p. 409-412.

Research output: Contribution to journalArticle

@article{de0f6da7352c4db8a549a6492b7e03b2,
title = "Noninvasive feature-based detection of delayed gastric emptying in humans using neural networks",
abstract = "Radioscintigraphy is currently the gold standard for gastric emptying test which involves radiation exposure and is considerably expensive. We present a feature-based detection approach using neural networks for the noninvasive diagnosis of delayed gastric emptying from the cutaneous electrogastrogram (EGG). Simultaneous recordings of the EGG and scintigraphic gastric emptying test were made in 152 patients with symptoms suggestive of delayed gastric emptying. Spectral analyses were performed to derive EGG parameters which were used as the input of the neural network. The result of scintigraphic gastric emptying was used as the gold standard for the training and testing of the neural network. A correct classification of 85{\%} (a specificity of 89{\%} and a sensitivity of 82{\%}) was achieved using the proposed method.",
keywords = "Artificial neural networks, Electrogastrogram, Gastric emptying, Spectral analysis",
author = "Jiande Chen and Zhiyue Lin and McCallum, {Richard W.}",
year = "2000",
doi = "10.1109/10.827310",
language = "English (US)",
volume = "47",
pages = "409--412",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "3",

}

TY - JOUR

T1 - Noninvasive feature-based detection of delayed gastric emptying in humans using neural networks

AU - Chen, Jiande

AU - Lin, Zhiyue

AU - McCallum, Richard W.

PY - 2000

Y1 - 2000

N2 - Radioscintigraphy is currently the gold standard for gastric emptying test which involves radiation exposure and is considerably expensive. We present a feature-based detection approach using neural networks for the noninvasive diagnosis of delayed gastric emptying from the cutaneous electrogastrogram (EGG). Simultaneous recordings of the EGG and scintigraphic gastric emptying test were made in 152 patients with symptoms suggestive of delayed gastric emptying. Spectral analyses were performed to derive EGG parameters which were used as the input of the neural network. The result of scintigraphic gastric emptying was used as the gold standard for the training and testing of the neural network. A correct classification of 85% (a specificity of 89% and a sensitivity of 82%) was achieved using the proposed method.

AB - Radioscintigraphy is currently the gold standard for gastric emptying test which involves radiation exposure and is considerably expensive. We present a feature-based detection approach using neural networks for the noninvasive diagnosis of delayed gastric emptying from the cutaneous electrogastrogram (EGG). Simultaneous recordings of the EGG and scintigraphic gastric emptying test were made in 152 patients with symptoms suggestive of delayed gastric emptying. Spectral analyses were performed to derive EGG parameters which were used as the input of the neural network. The result of scintigraphic gastric emptying was used as the gold standard for the training and testing of the neural network. A correct classification of 85% (a specificity of 89% and a sensitivity of 82%) was achieved using the proposed method.

KW - Artificial neural networks

KW - Electrogastrogram

KW - Gastric emptying

KW - Spectral analysis

UR - http://www.scopus.com/inward/record.url?scp=0034056737&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034056737&partnerID=8YFLogxK

U2 - 10.1109/10.827310

DO - 10.1109/10.827310

M3 - Article

C2 - 10743784

AN - SCOPUS:0034056737

VL - 47

SP - 409

EP - 412

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 3

ER -